Point Features (e.g., Spatial Coordinate Descriptors) Patents (Class 382/201)
-
Patent number: 8989506Abstract: Systems, methods, and computer storage mediums are provided for matching multiple photographs together. An example method includes receiving a first collection of photographic images. The photographic images in the first collection are clustered into one or more composite sets of photographic images based on a comparison of the metadata associated with each photographic image in the first collection meeting a predetermined similarity threshold. An image overlap is determined between each photographic image within each of the one or composite sets of photographic images. When the image overlap exceeds a predetermined image overlap threshold, a pair of photographic images are matched, for all of the photographic images within each composite set of photographic images to form one or more composite images.Type: GrantFiled: July 1, 2014Date of Patent: March 24, 2015Assignee: Google Inc.Inventors: Chase Hensel, Guiheng Zhou
-
Publication number: 20150078669Abstract: In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of a first image and a second image of a scene comprising one or more objects. The method includes detecting the objects in the first image by detecting object point of the objects in the first image. The method includes detecting the object points of the objects in the second image based on detection of the object points of the objects in the first image. Detection of an object point in the second image that corresponds to an object point of the first image comprises searching for the object point on an epipolar line in the second image corresponding to the object point of the first image. The method includes determining disparity values between the objects points in the first image and the object points in the second image.Type: ApplicationFiled: July 17, 2014Publication date: March 19, 2015Inventors: Soumik Ukil, Veldandi Muninder, Krishna Annasagar Govindarao
-
Patent number: 8983205Abstract: Disclosed herein is a method for auto-depicting trends in object contours (referred to as ADTOC). At the heart of ADTOC is a sifting process to determine a significant angular value via evaluating a plurality of angular values in a predefined range. ADTOC is characterized in that a probe-ahead concept is applied to obtain a reference angular value along the current route, and then the probed angular value is used to modify the significant angular value in order to timely correct the subsequent trace direction, thus achieving more accurate trace result. Contours with discontinuous segments caused by noise, obstacles, illumination, shading variations, etc. can also be auto-depicted without requiring a predefined auxiliary route.Type: GrantFiled: August 23, 2013Date of Patent: March 17, 2015Assignees: IEI Integration Corp., Armorlink SH Corp.Inventors: Chun-Shun Tseng, Jung-Hua Wang, Shan-Chun Tsai, Chiao-Wei Lin, Chang-Te Lin, Yi-Hua Wang
-
Publication number: 20150071552Abstract: A system and method to detect similarities between images. The system and method allow comparisons between a query image and one or more catalog images in a manner that is resilient to scanning, scaling, rotating, cropping and other distortions of the query image. The system includes an image processing module that determines and/or calculates principle features of a catalog image and constructs a feature vector using one or more of the principle features. The system also includes a matching module that matches a query image to one or more catalog images. The system finds matches based on a distance measure of features present in the query image and features present in the catalog images.Type: ApplicationFiled: November 11, 2014Publication date: March 12, 2015Inventors: Uri Lavi, Eli Goz, Gregory Begelman
-
Publication number: 20150071553Abstract: An image processing device includes a candidate point extracting unit configured to extract a plurality of candidate points belonging to a predetermined structure from image data, a shape model storing unit configured to store a shape model representing a known shape of the predetermined structure, the shape model being formed by a plurality of model labels having a predetermined connection relationship, and a corresponding point selecting unit configured to select a mapping relationship between the candidate points and the model labels from a set of candidate mapping relationships.Type: ApplicationFiled: November 14, 2014Publication date: March 12, 2015Inventor: Yoshiro KITAMURA
-
Patent number: 8971610Abstract: A method of compiling an image database for a three-dimensional object recognition including the steps of: when a plurality of images each showing an object from different viewpoint are inputted, extracting local features from each of the images, and expressing the local features using feature vectors; forming sets of the feature vectors, each set representing a same part of the object from a series of the viewpoints, and generating subspaces, each subspace representing a characteristic of each set; and storing each subspace to the image database with an identifier of the object to perform a recognition process that is realized by the steps of: when at least one image of an object is given as a query, extracting query feature vectors; determining the subspace most similar to each query feature vector; and executing a counting process to the identifiers to retrieve an object most similar to the query.Type: GrantFiled: April 27, 2011Date of Patent: March 3, 2015Assignees: Osaka Prefecture University Public Corporation, Olympus CorporationInventors: Takahiro Kashiwagi, Takumi Toyama, Koichi Kise, Yukihito Furuhashi, Taiji Mine
-
Patent number: 8971638Abstract: A method and an apparatus search an image using a feature point. The image search method extracts at least one feature point from an image and describes the extracted at least one feature point in stages, thereby generating a hierarchical feature point descriptor. In addition, the method may search for information matching the feature point descriptor from a local database (DB) included in a terminal or a remote DB included in a server.Type: GrantFiled: August 22, 2011Date of Patent: March 3, 2015Assignee: Samsung Electronics Co., Ltd.Inventors: Sang-Wook Kim, Seon Min Rhee, Yong Beom Lee
-
Publication number: 20150055873Abstract: Provided are an image alignment apparatus and an image alignment method using the same. The image alignment apparatus includes a first conversion function estimation unit for estimating a first conversion function based on feature point information that is extracted from a first image, which is captured by using a first image sensor, and a second image, which is captured by using a second image; and a second conversion function estimation unit for estimating a second conversion function based on motion information that is extracted from the first image and the second image.Type: ApplicationFiled: February 11, 2014Publication date: February 26, 2015Applicant: Samsung Techwin Co., Ltd.Inventors: Joon Sung LEE, Jae Yoon OH, Gon Soo KIM
-
Patent number: 8965133Abstract: An image processing apparatus to obtain highly reliable local feature point and local feature amount. With the number of local feature points as a factor of an image local feature amount description size, the reproducibility of the local feature point and local feature amount is estimated, and description is made by the local amount description size, sequentially from local feature point and local feature amount with the highest reproducibility. It is possible to ensure a local feature amount description size and search accuracy.Type: GrantFiled: October 5, 2012Date of Patent: February 24, 2015Assignee: Canon Kabushiki KaishaInventor: Hirotaka Shiiyama
-
Patent number: 8959022Abstract: A method for determining a relatedness between a query video and a database video is provided. A processor extracts an audio stream from the query video to produce a query audio stream, extracts an audio stream from the database video to produce a database audio stream, produces a first-sized snippet from the query audio stream, and produces a first-sized snippet from the database audio stream. An estimation is made of a first most probable sequence of latent evidence probability vectors generating the first-sized audio snippet of the query audio stream. An estimation is made of a second most probable sequence of latent evidence probability vectors generating the first-sized audio snippet of the database audio stream. A similarity is measured between the first sequence and the second sequence producing a score of relatedness between the two snippets. Finally a relatedness is determined between the query video and a database video.Type: GrantFiled: November 19, 2012Date of Patent: February 17, 2015Assignee: Motorola Solutions, Inc.Inventors: Yang M. Cheng, Dusan Macho
-
Publication number: 20150043828Abstract: A method for extracting characteristic points from an image, includes extracting characteristic points from a first image, generating for each characteristic point a descriptor with several components describing an image region around the characteristic point, and comparing two by two the descriptors of the first image, the characteristic points whose descriptors have a proximity between them greater than an ambiguity threshold, being considered ambiguous.Type: ApplicationFiled: August 6, 2014Publication date: February 12, 2015Inventor: Stéphane Valente
-
Patent number: 8953887Abstract: A method for processing geospatial datasets corresponding to geospatial objects, the method having the steps of extracting geospatial attributes from the geospatial datasets, locating extracted geospatial attributes corresponding to a particular geospatial object at a particular point in time, and generating output indicative of the particular geospatial object at the particular point in time utilizing the located geospatial attributes.Type: GrantFiled: December 10, 2010Date of Patent: February 10, 2015Assignee: Terrago Technologies, Inc.Inventors: Ching-Chien Chen, Craig A. Knoblock, Cyrus Shahabi
-
Publication number: 20150036939Abstract: The disclosure relates to a method for processing an image, the method comprising: providing a set of key points from the image; describing location information of the set of key points in form of a binary matrix; and scanning the binary matrix according to a pre-determined order, thereby creating a new representation of the location information of the set of key points.Type: ApplicationFiled: October 20, 2014Publication date: February 5, 2015Inventors: Giovanni Cordara, Imed Bouazizi, Lukasz Kondrad
-
Publication number: 20150036936Abstract: A method for processing an image including: identifying a first group of keypoints in the image; for each keypoint of the first group, identifying at least one corresponding keypoint local feature related to the each keypoint; for the at least one keypoint local feature, calculating a corresponding local feature relevance probability; calculating a keypoint relevance probability based on the local feature relevance probabilities of the at least one local feature; selecting keypoints, among the keypoints of the first group, having the highest keypoint relevance probabilities to form a second group of keypoints, and exploiting the keypoints of the second group for analyzing the image. The local feature relevance probability calculated for a local feature of a keypoint is obtained by comparing the value assumed by the local feature with a corresponding reference statistical distribution of values of the local feature.Type: ApplicationFiled: December 20, 2012Publication date: February 5, 2015Applicant: TELECOM ITALIA S.p.A.Inventors: Massimo Balestri, Gianluca Francini, Skjalg Lepsoy
-
Publication number: 20150036937Abstract: The present invention relates to an ‘image correction method using creation of feature points’, and the method includes the steps of: (a) mapping a plurality of feature points on an image; (b) mapping an additional feature point on the image; and (c) changing arrangement of the feature points according to mapping of the additional feature point, in which the plurality of feature points can be set as a feature point of forced position and a feature point of unforced position, respectively, and only feature points of unforced position are moved at step (c).Type: ApplicationFiled: July 31, 2014Publication date: February 5, 2015Inventors: Hwan Chul KIM, Su Ryeon Kang
-
Publication number: 20150036938Abstract: Disclosed are object recognizing method and apparatus. The method may comprise extracting a feature point of an object to be recognized in an input image; generating a plurality of feature images by extracting orientation information of a region adjacent to the feature point and normalizing the region based in the orientation information; deriving a covariance descriptor based on the feature images; and recognizing the object in the input image by comparing the covariance descriptor with a reference covariance descriptor stored in advance. Thus, the object can be recognized fast and robustly to changes on the size of the input image, rotations of the input image, and illumination, whereby the recognition performance can be enhanced.Type: ApplicationFiled: August 1, 2014Publication date: February 5, 2015Inventors: Dai Jin Kim, Jae Sik Yun, In Su Kim
-
Patent number: 8948513Abstract: Methods, systems, and apparatus, including computer program products, for identifying regions of interest in an image and identifying a barcode in a degraded image are provided. A region of interest is identified by pre-processing an image, generating a binary image based on a metric calculated on the pre-processed image, and analyzing regions of the image identified using connected components and other analysis. A barcode is identified by searching a population of barcodes, degrading ideal image intensity profiles of candidate barcodes, and comparing the degraded ideal image intensity profiles to an image intensity profile of the degraded image.Type: GrantFiled: January 27, 2009Date of Patent: February 3, 2015Assignee: Apple Inc.Inventors: Rudolph van der Merwe, Richard Eugene Crandall, Samuel Gordon Noble, Bertrand Serlet, Stanislav Kounitski
-
Patent number: 8948518Abstract: A system and a method for progressive queries, which are a sequence of queries for visual search of an image, sent from a sender to a receiver of a communication network, are disclosed. Queries based on a set of feature points and their associated locations of an image may be selected in sequence. A sender sends a first query to a receiver, wherein the first query comprises a number of feature points which is a subset of the set of feature points of the image invariant to rotation and scaling in creating the image. The sender receives a feedback from the receiver, wherein the feedback is generated by the receiver based on searching an image repository using information from the first query. The sender then decides whether there is a match of the image in the image repository based on the received feedback.Type: GrantFiled: December 29, 2011Date of Patent: February 3, 2015Assignee: FutureWei Technologies, Inc.Inventors: Xin Xin, Zhu Li, Aggelos K. Katsaggelos
-
Publication number: 20150029465Abstract: A projection system includes projection units configured to project an image on a projection body; a preparing unit configured to prepare calibration-use images; an extraction unit configured to extract, from each of the calibration-use images, at least grating points indicating a distortion in a projected image of one of the projection units and alignment points of the projected image of the one of the projection units or another one of the projection units; a conversion unit configured to convert, onto a common coordinate system, the grating points of the projected images of the projection units extracted from the calibration-use images, based on alignment points common to the calibration-use images; and a geometric correction coefficient calculation unit configured to calculate a geometric correction coefficient for providing a projection image to be projected from the projection units, based on the grating points on the common coordinate system.Type: ApplicationFiled: July 25, 2014Publication date: January 29, 2015Inventors: Masaaki ISHIKAWA, Yukinaka UCHIYAMA
-
Patent number: 8942485Abstract: An electronic device stores haar-like features and geometrical features of an object. A reference image of the object is created according to the geometrical features of the object. An outline image is obtained from each image of the object. The electronic device calculates derivatives of each two adjacent points on the reference image and each outline image. A derivative matrix of the reference image and a derivative matrix of each outline image are generated. The electronic device generates a first derivative curve corresponding to the derivative matrix of the reference image and a second derivative curve corresponding to each derivative matrix of the outline image. When all the second derivative curves are the same as the first derivative curve, the electronic device determines whether each outline image is corresponding to the object by using the haar-like features of the object.Type: GrantFiled: August 30, 2013Date of Patent: January 27, 2015Assignees: Hong Fu Jin Precision Industry (ShenZhen) Co., Ltd., Hon Hai Precision Industry Co., Ltd.Inventor: Guang-Jian Wang
-
Patent number: 8942515Abstract: An efficient image retrieval method utilizing topological order distance (TOD) algorithm is disclosed. In one aspect, an image recognition method may include steps of receiving one or more input images; extracting one or more key features on the input images; determining an origin and one or more feature points on the key features on the input images; establishing a topological relationship in each dimension between the feature points on the key features; and utilizing the topological relationship in each dimension between the feature points to identify the input images in an image database. Comparing with the conventional image retrieval techniques, the TOD algorithm is advantageous because it is more efficient, scale and rotation invariant, and tolerant to affine and perspective transformation.Type: GrantFiled: October 26, 2012Date of Patent: January 27, 2015Inventor: Lida Huang
-
Patent number: 8934721Abstract: The present disclosure provides a microscopic vision measurement method based on the adaptive positioning of the camera coordinate frame which includes: calibrating parameters of a microscopic stereo vision measurement model (201); acquiring pairs of synchronical images and transmitting the acquired images to a computer through an image acquisition card (202); calculating 3D coordinates of feature points in a scene according to the matched pairs of feature points in the scene obtained from the synchronical images and the calibrated parameters of the microscopic stereo vision measurement model (203); and performing specific measurement according to the 3D coordinates of the feature points in the scene (204). With the method, the nonlinearity of the objective function in the microscopic vision calibration optimization is effectively decreased and a better calibration result is obtained.Type: GrantFiled: April 25, 2011Date of Patent: January 13, 2015Assignee: Beihang UniversityInventors: Guangjun Zhang, Zhenzhong Wei, Weixian Li, Zhipeng Cao, Yali Wang
-
Patent number: 8923623Abstract: The invention provides a method and apparatus for acquiring descriptive information of a plurality of images and an image matching method. The method for acquiring descriptive information of a plurality of images includes: performing a feature point detection with respect to each image of the plurality of images, so as to obtain a plurality of feature points of each image; acquiring 0-level descriptive information of the plurality of images; and the following steps are performed for each image: performing a division of the image for the (n?1)th time, so as to obtain a plurality of (n?1)-level sub-images of the image; and (n?1)-level descriptive information of the image is generated in accordance with a plurality of nth local feature descriptors for the image and a plurality of nth visual words, where n=2,3, . . . , K+1, and K is a positive integer.Type: GrantFiled: March 29, 2012Date of Patent: December 30, 2014Assignee: Fujitsu LimitedInventors: Qiong Cao, Rujie Liu, Hao Yu, Masahiko Sugimura, Yusuke Uehara
-
Publication number: 20140369608Abstract: Apparatuses, methods and storage medium associated with processing an image are disclosed herein. In embodiments, a method for processing one or more images may include generating a plurality of pairs of keypoint features for a pair of images. Each pair of keypoint features may include a keypoint feature from each image. Further, for each pair of keypoint features, corresponding adjoin features may be generated. Additionally, for each pair of keypoint features, whether the adjoin features are similar may be determined. Whether the pair of images have at least one similar object may also be determined, based at least in part on a result of the determination of similarity between the corresponding adjoin features. Other embodiments may be described and claimed.Type: ApplicationFiled: June 14, 2013Publication date: December 18, 2014Inventors: Tao Wang, Lianrui Fu, Qiang Li, Jianguo Li, Yurong Chen, Ya-ti Peng, Yimin Zhang, Anbang Yao
-
Publication number: 20140369607Abstract: An improved object recognition method is provided that enables the recognition of many objects in a single image. Multiple instances of an object in an image can now be detected with high accuracy. The method receives a plurality of matches of feature points between a database image and a query image and determines a kernel bandwidth based on statistics of the database image. The kernel bandwidth is used in clustering the matches. The clustered matches are then analyzed to determine the number of instances of the object within each cluster. A recursive geometric fitting can be applied to each cluster to further improve accuracy.Type: ApplicationFiled: June 12, 2013Publication date: December 18, 2014Inventors: ANKUR R. PATEL, BOAZ J. SUPER
-
Patent number: 8913806Abstract: An image identifying device includes a mechanism that sets an evaluation area whose category is to be identified in an in-vivo image; a mechanism that acquires texture components from the evaluation area in the in-vivo image; a mechanism that calculates an evaluation value indicating homogeneity of the texture components; and a mechanism that identifies the category of the evaluation area on the basis of the evaluation value.Type: GrantFiled: November 23, 2011Date of Patent: December 16, 2014Assignee: Olympus CorporationInventors: Takashi Kono, Yamato Kanda, Makoto Kitamura, Masashi Hirota
-
Patent number: 8908930Abstract: A primary object of the present invention is to extract a difference in shading of a blood vessel image in a picked up image as information to be used for authentication, and to acquire a larger number of pieces of biometric information from one image. An individual authentication device to be used to authenticate an individual using feature information of a vascular pattern acquired from a living body includes an imaging unit that images a region of the living body serving as an object of authentication, and an arithmetic unit that acquires the picked up image as an authentication image. The arithmetic unit extracts a vascular pattern from the authentication image, and acquires a degree of shading of the vascular pattern as the feature information.Type: GrantFiled: September 6, 2011Date of Patent: December 9, 2014Assignee: Hitachi, Ltd.Inventors: Yusuke Matsuda, Akio Nagasaka, Naoto Miura, Harumi Kiyomizu, Takafumi Miyatake
-
Patent number: 8908016Abstract: A system, apparatus and method of performing 3-D object profile inter-planar estimation and/or range inter-planar estimation of objects within a scene, including: providing a predefined finite set of distinct types of features, resulting in feature types, each feature type being distinguishable according to a unique bi-dimensional formation; providing a coded light pattern having multiple appearances of the feature types; projecting the coded light pattern, having axially varying intensity, on objects within a scene, the scene having at least two planes, resulting in a first plane and a second plane; capturing a 2-D image of the objects having the projected coded light pattern projected thereupon, resulting in a captured 2-D image, the captured 2-D image including reflected feature types; determining intensity values of the 2-D captured image; and performing 3-D object profile inter-planar estimation and/or range inter-planar estimation of objects within the scene based on determined intensity values.Type: GrantFiled: October 11, 2009Date of Patent: December 9, 2014Assignee: Mantivision Ltd.Inventors: Eyal Gordon, Zeev Zalevsky, Hamootal Duadi
-
Publication number: 20140355888Abstract: Methods for pattern recognition and corresponding systems and computer-readable mediums. A method includes receiving a set of two-dimensional (2D) points. The method includes identifying neighbor points for each of a plurality of points in the set and finding at least one indicated pattern between points in the set. The indicated pattern can be one of a linear pattern, a rectangular pattern, a skew pattern, or a circular pattern. The method includes storing pattern data corresponding to the found indicated pattern.Type: ApplicationFiled: May 31, 2013Publication date: December 4, 2014Applicant: SIEMENS PRODUCT LIFECYCLE MANAGEMENT SOFTWARE INC.Inventors: Howard Charles Duncan Mattson, Douglas Joseph King, Daniel C. Staples
-
Publication number: 20140355879Abstract: The disclosure describes novel technology for inferring scenes from images. In one example, the technology includes a system that can determine partition regions from one or more factors that are independent of the image data, for an image depicting a scene; receive image data including pixels forming the image; classify pixels of the image into one or more pixel types based on one or more pixel-level features; determine, for each partition region, a set of pixel characteristic data describing a portion of the image included in the partition region based on the one or more pixel types of pixels in the partition region; and classify a scene of the image based on the set of pixel characteristic data of each of the partition regions.Type: ApplicationFiled: February 3, 2014Publication date: December 4, 2014Inventors: John Mark Agosta, Preeti Pillai, Kentaro Oguchi, Ganesh Yalla
-
Patent number: 8903179Abstract: A method, computer program product, and computer system for identifying a first reference point on a display. A second reference point of an object of an application is identified, wherein the object is on the display. A distance is determined of the first reference point on the display from the second reference point of the object on the display. One or more properties of the application is adjusted based upon, at least in part, the distance of the first reference point on the display from the second reference point of the object on the display.Type: GrantFiled: October 1, 2013Date of Patent: December 2, 2014Assignee: International Business Machines CorporationInventors: Szymon Brandys, Malgorzata Janczarska, Pawel Pogorzelski, Tomasz Zama
-
Patent number: 8903178Abstract: A method, computer program product, and computer system for identifying a first reference point on a display. A second reference point of an object of an application is identified, wherein the object is on the display. A distance is determined of the first reference point on the display from the second reference point of the object on the display. One or more properties of the application is adjusted based upon, at least in part, the distance of the first reference point on the display from the second reference point of the object on the display.Type: GrantFiled: November 2, 2012Date of Patent: December 2, 2014Assignee: International Business Machines CorporationInventors: Szymon Brandys, Malgorzata Janczarska, Pawel Pogorzelski, Tomasz Zarna
-
Patent number: 8903137Abstract: Systems and methods for associating geographic coordinates with one or more points in a digital geographic image, such as a satellite image, aerial image, ground based image, street level image or other suitable geographic image are provided. More particularly, a digital geographic image can be analyzed to identify one or more features that may be suitable as measurement points for collecting measured ground truth data. The one or more features can be described as a mathematical model that defines image coordinates along the feature depicted in the digital geographic image with sub-pixel accuracy. Image coordinates can be assigned to the measurement points with sub-pixel accuracy using the mathematical model. Collected ground truth data can then be associated with the identified image coordinates to allow for the more precise association of geographic coordinate information to points in the digital geographic imagery.Type: GrantFiled: October 26, 2012Date of Patent: December 2, 2014
-
Patent number: 8903177Abstract: The invention in particular relates to the hybrid tracking of representations of objects in a sequence of images using at least one key image. After acquiring a first and second images including a representation of the tracked object, a first image portion is identified in the first image, and a second image portion is retrieved from the key image. A relative pose of a first image portion of said second image, similar to the first image portion of the first image, is estimated. A second image portion of the first or second image, similar to the second image portion of the key image, is sought. The relative pose of the object is then estimated according to the relative poses of the first image portions and the second image portions.Type: GrantFiled: October 12, 2010Date of Patent: December 2, 2014Assignee: Total ImmersionInventors: Nicolas Livet, Thomas Pasquier, Jérémy Chamoux
-
Patent number: 8903161Abstract: A method for estimating a location of a device uses a color image and a depth image. The method includes matching the color image to the depth image, generating a 3D reference image based on the matching, generating a 3D object image based on the matching, extracting a 2D reference feature point from the reference image, extracting a 2D reference feature point from the object image, matching the extracted reference feature point from the reference image to the extracted reference feature point from the object image, extracting a 3D feature point from the object image using the matched 2D reference feature point, and estimating the location of the device based on the extracted 3D feature point.Type: GrantFiled: December 21, 2012Date of Patent: December 2, 2014Assignee: Samsung Electronics Co., Ltd.Inventors: No San Kwak, Kyung Shik Roh, Sung Hwan Ahn, Suk June Yoon, Seung Yong Hyung
-
Publication number: 20140348432Abstract: There is provided an image processing apparatus which calculates a feature value of an image. The apparatus comprises first obtaining means for obtaining an image; calculation means for calculating a set of numerical values formed from degrees of contributions of each of a plurality of order, wherein the degree of contributions of each order indicate contributions of monomials of the order for intensity values which are calculated using an approximation polynomial, and wherein the approximation polynomial provides a relationship between a pixel position of the image and an intensity value at the pixel position and is formed from a plurality of the monomials each having an order out of the plurality of orders; and first output means for outputting the set of the calculated numerical values as the feature value of the image.Type: ApplicationFiled: September 26, 2012Publication date: November 27, 2014Inventors: Ryo Ishikawa, Kiyohide Satoh, Katsushi Ikeuchi, Bo Zheng, Yonggi Sun
-
Patent number: 8885923Abstract: A recognition task executing means 11 that provides a feature point selecting system which can select an adequate feature point matching a recognition algorithm in a recognition task executes the recognition task using an importance of each of a plurality of feature point candidates on a three-dimensional shape model for a plurality of evaluation images. A recognition error evaluating means 12 evaluates a recognition error related to all evaluation images from a difference between a recognition result of the recognition task and correct data of the recognition task for each evaluation image. A feature point importance determining means 13 sets a cost function which is represented as a function obtained by adding a restriction condition that an importance of an unimportant feature point candidate becomes close to zero, to the recognition error related to all evaluation images, and calculating the importance of each feature point candidate which minimizes a value of the cost function.Type: GrantFiled: January 11, 2011Date of Patent: November 11, 2014Assignee: NEC CorporationInventors: Rui Ishiyama, Hiroyoshi Miyano, Hidekata Hontani, Fumihiko Sakaue
-
Publication number: 20140328543Abstract: An object of the present invention is to reduce a size of a feature descriptor while maintaining accuracy of object identification.Type: ApplicationFiled: November 15, 2012Publication date: November 6, 2014Applicant: NEC CORPORATIONInventors: Kota Iwamoto, Ryota Mase
-
Patent number: 8879850Abstract: An image stabilization method and an image stabilization device are provided. In the method, each of images to be processed is detected by a feature point detection method to detect a plurality of feature points. The relationship of the same feature points in adjacent images to be processed is analyzed. According to the relationship of the feature points, a homography transform matrix of adjacent images to be processed is calculated. Based on the known feature points and the homography transform matrix, a stabilization matrix and a plurality of adjustment matrices corresponding to each image to be processed are calculated. Compensation is performed on each image to be processed by the adjustment matrices, so as to produce a plurality of corrected images. A first image of adjacent corrected images multiplied by the same stabilization matrix is transformed to a second image of the adjacent corrected images.Type: GrantFiled: December 15, 2011Date of Patent: November 4, 2014Assignee: Industrial Technology Research InstituteInventor: Yu-Feng Hsu
-
Patent number: 8873112Abstract: A signal value representing at least one of a plurality of types of optical characteristics are calculated for each pixel from the read signal obtained and output by reading light reflected by a document placed on a document table and a document table cover while the document is covered with the cover. It is determined, based on the signal value calculated, whether or not a target pixel is a pixel in a document region. A document region is detected from the determination result.Type: GrantFiled: September 11, 2012Date of Patent: October 28, 2014Assignee: Canon Kabushiki KaishaInventors: Tetsuya Suwa, Minako Kato, Yugo Mochizuki, Takashi Nakamura, Masao Kato
-
Patent number: 8873846Abstract: A feature tracking technique for detecting and tracking feature points with primary colors. An energy value may be computed for each color channel of a feature. If the energy of all the channels is above a threshold, then the feature may be tracked according to a feature tracking method using all channels. Otherwise, if the energy of all of the channels is below the threshold, then the feature is not tracked. If the energy of at least one (but not all) of the channels is below the threshold, then the feature is considered to have primary color, and the feature may be tracked according to the feature tracking method using only the one or more channels with energy above the threshold. The feature tracking techniques may, for example, be used to establish point trajectories in an image sequence for various Structure from Motion (SFM) techniques.Type: GrantFiled: December 21, 2012Date of Patent: October 28, 2014Assignee: Adobe Systems IncorporatedInventor: Hailin Jin
-
Publication number: 20140314326Abstract: A method and system for generating and using open sky data is described. A vehicle equipped with a range-finding device travels on a road network in a geographic region. The range-finding device transmits a pulse at a given position and obtains range data associated with the position. The system uses the range data to generate data representing visibility of open sky at the given position and at other positions along the road network. For example, the system may determine transmission angles of pulses transmitted at positions that did not encounter a physical object and then use the determined transmission angles to generate data representing visibility of open sky at these positions. The system then stores the data representing the visibility of open sky. The system then associates the data representing the visibility of open sky with data representing physical features.Type: ApplicationFiled: June 30, 2014Publication date: October 23, 2014Inventor: James D. Lynch
-
Patent number: 8866888Abstract: A 3D positioning apparatus is used for an object that includes feature points and a reference point. The object undergoes movement from a first to a second position. The 3D positioning apparatus includes: an image sensor for capturing images of the object; and a processor for calculating, based on the captured images, initial coordinates of each feature point when the object is in the first position, initial coordinates of the reference point, final coordinates of the reference point when the object is in the second position, and final coordinates of each feature point. The processor calculates 3D translational information of the feature points using the initial and final coordinates of the reference point, and 3D rotational information of the feature points using the initial and final coordinates of each feature point. A 3D positioning method is also disclosed.Type: GrantFiled: December 29, 2009Date of Patent: October 21, 2014Assignee: National Taiwan UniversityInventors: Homer H. Chen, Ping-Cheng Chi
-
Patent number: 8867806Abstract: Methods and systems are disclosed for correcting segmentation errors in pre-existing contours and surfaces. Techniques are disclosed for receiving one or more edit contours from a user, identifying pre-existing data points that should be eliminated, and generating a new corrected surface. Embodiments disclosed herein relate to using received edit contours to generate a set of points on a pre-existing surface, and applying a proximity test to eliminate pre-existing constraint points that are undesirable.Type: GrantFiled: August 1, 2011Date of Patent: October 21, 2014Assignee: Impac Medical Systems, Inc.Inventor: Lyndon S. Hibbard
-
Patent number: 8861834Abstract: A recognition processing method and an image processing device ends recognition of an object within a predetermined time while maintaining the recognition accuracy. The device extracts combinations of three points defining a triangle whose side length satisfy predetermined criterion values from feature points of the model of a recognition object, registers the extracted combinations as model triangles, and similarly extracts combinations of three points defining a triangle whose side lengths satisfy predetermined criterion values from feature points of the recognition object. The combinations are used as comparison object triangles and associated with the respective model triangles.Type: GrantFiled: March 5, 2008Date of Patent: October 14, 2014Assignee: Omron CorporationInventor: Shiro Fujieda
-
Publication number: 20140301645Abstract: An approach is provided for mapping a point of interest (POI) based on user-captured images. One or more user-captured images are queried based, at least in part, on a POI data record. One or more identifying features of a POI associated with the POI data record are recognized in the one or more user-captured images and a position of the one or more identifying features is determined in the one or more user-captured images. The POI is mapped based, at least in part, on the position of the one or more identifying features and image metadata associated with the one or more user-captured images.Type: ApplicationFiled: April 3, 2013Publication date: October 9, 2014Applicant: Nokia CorporationInventor: Ville-Veikko Mattila
-
Publication number: 20140301650Abstract: An image processing device comprises a part-point specifying unit configured to specify a part point of an object; a feature-quantity extracting unit configured to extract one or a plurality of feature quantities from a pixel of a sampling point or from a pixel group including the pixel of the sampling point, for each of a plurality of sampling points, and extract candidate feature quantities corresponding to the part point constituted by the extracted plurality of feature quantities corresponding to the respective sampling points, the plurality of sampling points comprising the part point specified by the part-point specifying unit and at least one point on the image other than the part point; and a feature-quantity generating unit configured to generate one or a plurality of comparison feature quantities corresponding to the part points based on a predetermined standard by using the candidate feature quantities extracted by the feature-quantity extracting unit.Type: ApplicationFiled: March 19, 2014Publication date: October 9, 2014Applicant: OMRON CorporationInventor: Atsushi IRIE
-
Patent number: 8855819Abstract: A SLAM of a robot is provided. The position of a robot and the position of feature data may be estimated by acquiring an image of the robot's surroundings, extracting feature data from the image, and matching the extracted feature data with registered feature data. Furthermore, measurement update is performed in a camera coordinate system and an appropriate assumption is added upon coordinate conversion, thereby reducing non-linear components and thus improving the SLAM performance.Type: GrantFiled: July 22, 2009Date of Patent: October 7, 2014Assignee: Samsung Electronics Co., Ltd.Inventors: Ki-wan Choi, Hyoung-ki Lee, Ji-young Park
-
Patent number: 8850305Abstract: Methods, systems, and articles of manufacture for the automatic determining of calls to action in a webpage are disclosed. These include, rendering a web page in a browser, capturing the rendered web page as an image, filtering the image using one or more image filters, and identifying the calls to action in the filtered image using at least one call to action selection criteria.Type: GrantFiled: February 28, 2012Date of Patent: September 30, 2014Assignee: Google Inc.Inventor: James Kent
-
Publication number: 20140270502Abstract: Techniques for making, using and updating a Modeled Atmospheric Correction Object (MACO) cluster and the MACO sites that are selected from within a given MACO cluster. The MACO construct is a novel application of a Model of Reality (MOR) that provides synthetic ground truth essential to converting imagery from top-of-the-atmosphere radiance to surface reflectance given a variety of spatial, spectral and radiance effects involving non-uniform distributions of opaque clouds, cirrus clouds, aerosols, water vapor, surface ice, surface snow, shadows and bidirectional reflectance distribution function (BRDF) effects.Type: ApplicationFiled: March 15, 2013Publication date: September 18, 2014Applicant: DIGITALGLOBE, INC.Inventor: DIGITALGLOBE, INC.