Abstract: A system and method for identification of a landing site for aerial vehicles are provided. In one embodiment, the method includes processing image data pertaining to a potential site area. The method further includes identifying existing building infrastructure and defining boundaries of the identified existing building infrastructure in the potential site area, based on the processed image data. The method also includes identifying existing road infrastructure adjacent to the boundaries of the identified existing building infrastructure and defining boundaries of the identified existing road infrastructure, based on the processed image data. The method further includes calculating a feasibility score of the existing building infrastructure by analyzing the identified existing building infrastructure and the identified existing road infrastructure.

Abstract: Method and apparatus to match bounding boxes around text to align forms. The approach is less computationally intensive, and less prone to error than text recognition. For purposes of achieving alignment, information per se is not as important as information location. Information within the bounding boxes is not as critical as is the location of the area which the bounding boxes occupy. Scanning artifacts, missing characters, or noise generally do not affect bounding boxes themselves so much as they do the contents of the bounding boxes. Thus, for purposes of form alignment, the bounding boxes themselves are sufficient. Using bounding boxes also avoids misalignment issues that can result from stray marks on a page, for example, from holes punched in a sheet, or from handwritten notations.

Abstract: Face authentication can easily be performed based on an input image including a mirror region reflected by a mirror without increasing a storage capacity of a database. With the database, for each face of a person to be authenticated, only one real front image is to be registered as a reference face image. A mirror image processing circuitry detects the mirror region from the input image and to subject a detected mirror region to lateral inversion processing to produce a processed image. A face detection processing circuitry detects a face image from the processed image to generate a detected face image. A face authentication processing circuitry compares the detected face image with the reference face image, to thereby perform face authentication.

Abstract: An information processing method, device, cloud-based processing device, and computer program product are related to the field of data processing technologies and can cause an increased efficiency in detecting whether a road area contains a depression region. The information processing method includes: acquiring a depth image; processing the depth image to obtain a means-by-row graph, based on which a road area in the depth image is determined; determining a suspected depression region in the road area; and judging over the suspected depression region based on a depression threshold to determine whether the depth image contains a depression region.

Abstract: A system comprises a picture and metadata captured by a content capture system; a recognizable characteristic datastore configured to store recognizable characteristics of different users; a module configured to identify a time and a location associated with the picture based on the metadata, and to identify one or more potential target systems within a predetermined range of the location at the time; a characteristic recognition module configured to retrieve the recognizable characteristics of one or more potential users associated with the potential target systems, and evaluate whether the picture includes one or more representations of at least one actual target user from the potential users based on the recognizable characteristics of the potential users; a distortion module configured to distort a feature of the representations of the least one actual target user in response to the determination; a communication module configured to communicate the distorted picture to a computer network.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for face anti-spoofing. One computer-implemented method includes receiving, by a server and from a user device, a plurality of images of a user face, each of the plurality of images corresponding to a facial expression performed by a user in response to each interaction challenge of a plurality of interaction challenges. The plurality of images are concatenated into a concatenated image. A convolutional neural network (CNN) classifier is used to obtain a confidence score for the concatenated image. A liveness of the user face is determined based on a comparison of the confidence score and a threshold value.

Abstract: A signal processing system includes a central processing unit (CPU) in communication with an accelerator, and an instruction scheduler in communication with the accelerator. A first memory device including a first instruction set is configured to operate the accelerator, a second instruction set is configured to operate the CPU, and a second memory device is configured to receive a datafile. The accelerator includes a plurality of processing engines (PEs) and an instruction scheduler, the instruction set includes a plurality of operators, and the instruction scheduler is configured to implement the operators in the accelerator employing the PEs. The CPU employs the operators implemented in the accelerator to analyze the datafile to extract a feature therefrom.

Abstract: A visualization apparatus detects a change in the shape of a solid model of a human body part based on images obtained by capturing the solid model. Next, the visualization apparatus generates a three-dimensional model reproducing the shape of the human body part in virtual space based on three-dimensional model data representing the shape of the human body part in three dimensions. The visualization apparatus further transforms the shape of the three-dimensional model into a transformed three-dimensional model in accordance with the change in the shape of the solid model. Then, the visualization apparatus outputs images of the transformed three-dimensional model.

Abstract: An apparatus is provided. The apparatus receives a video feed and processes the video feed in real-time as the video feed is received. The apparatus performs object detection and recognition on the video feed to detect and classify objects therein, performs activity recognition to detect and classify activities of at least some of the objects, and outputs classified objects and classified activities in the video feed. The apparatus generates natural language text that describes the video feed, produces a semantic network, and stores the video feed, classified objects and classified activities, natural language text, and semantic network in a knowledge base. The apparatus generates a graphical user interface (GUI) configured to enable queries of the knowledge base, and presentation of selections of the video feed, classified objects and classified activities, natural language text, and semantic network.

Abstract: Face authentication can easily be performed based on an input image including a mirror region reflected by a mirror without increasing a storage capacity of a database. With the database, for each face of a person to be authenticated, only one real front image is to be registered as a reference face image. A mirror image processing circuitry detects the mirror region from the input image and to subject a detected mirror region to lateral inversion processing to produce a processed image. A face detection processing circuitry detects a face image from the processed image to generate a detected face image. A face authentication processing circuitry compares the detected face image with the reference face image, to thereby perform face authentication.

Abstract: There is disclosed an information processing system for effectively using information indicating the state of a store visitor at the time of a visit. The system includes a recognizer that recognizes a store visitor and a transporter at the time of a visit by analyzing video information captured by an outside-the-store camera provided outside a store. The system also includes a determiner that determines a moving range of each store visitor recognized by the recognizer. Furthermore, the system includes a deriving unit that derives a trading area of the store based on a determination result of the determiner.

Abstract: A computer-implemented technique uses one or more neural networks to identify at least one item name associated with an input image using a multi-modal fusion approach. The technique is said to be multi-modal because it collects and processes different kinds of evidence regarding each detected item name. The technique is said to adopt a fusion approach because it fuses the multi-modal evidence into an output conclusion that identifies at least one item name associated with the input image. In one example, a first mode collects evidence by identifying and analyzing regions in the input image that are likely to include item name-related information. A second mode collects and analyzes any text that appears as part of input image itself. A third mode collects and analyzes text that is not included in the input image itself, but is nonetheless associated with the input image.

Abstract: A product defect detection method, device and system are disclosed. The method comprises: constructing a defect detection framework including segmentation networks, a concatenating network and a classification network, and setting a quantity of the segmentation network according to product defect types, wherein each segmentation network corresponds to a defect type; concatenating the sample image with the mask image output by each segmentation network by using the concatenating network to obtain a concatenated image; training the classification network by using the concatenated images to obtain a classification network capable of correctly identifying a product defect and a defect type; and when performing product defect detection, inputting a product image acquired into the defect detection framework, and detecting a product defect and a defect type existing in the product by using the segmentation networks, the concatenating network and the classification network.

Abstract: A method and system to receive, one or more first images, one or more second images, one or more ambient weather related information, and one or more land related information, wherein the one or more land related information comprise vegetation features, terra firma topography, elevation, slope and aspect, of one or more regions of interest, of a geographical region; to map automatically, one or more risk areas of the one or more regions of interest; to recognize automatically, one or more smoke or fire related signals; and to predict computationally, existence of a fire causing smoke, a fire, a fire-growth and spread.

Abstract: Provided is an aerial line extraction system including: an area-of-interest cropping unit that crops a region where a point cloud data of aerial lines is assumed to exist as an area of interest by setting coordinates of utility poles as a reference from a three-dimensional point cloud data of a three-dimensional shape that includes the aerial lines and trees installed in the air via the utility poles; an aerial line candidate extraction unit that extracts a candidate point cloud data of the aerial lines from the three-dimensional point cloud data in the area of interest; and an aerial line model estimation unit that estimates a model of the aerial lines on the basis of the extracted candidate point cloud data of the aerial lines.

Abstract: A method for inspecting printed products of a machine for processing printing substrates includes recording and digitizing produced printed products by using at least one image sensor and analyzing the printed products by using a computer to find potential defects. Defects in the printed products are detected by the computer by comparing the recorded and digitized printed image with a digital reference image, analyzing occurring deviations, and marking defective printed products in a manner suitable for removal. The computer spatially subdivides every digitized printed image into regions with deviations, calculates the time required to analyze every one of the regions, and terminates the analysis of a digitized printed image when the time required to analyze the regions exceeds a predefined value of time per digitized printed image.

Abstract: A system and method are provided for aiding an operator in operating a vehicle. In one embodiment, a system includes a sensor system configured to generate sensor data sensed from an environment of the vehicle. The system further includes a control module configured to, by a processor, generate a bowl view image of the environment based on the sensor data, identify at least one of a double object and a missing object in the bowl view image, generate a second bowl view image of the environment by re-stitching the sensor data based on the at least one of double object and missing object, and generate display data based on the second bowl view image.

Abstract: A method for processing a three-dimensional (3D) image includes acquiring a frame of a color image and a frame of a depth image, and generating a frame by combining the acquired frame of the color image with the acquired frame of the depth image. The generating of the frame includes combining a line of the color image with a corresponding line of the depth image.

Abstract: A method for recognizing object nodes in an image includes: performing image detection on an original image, to determine a target image region that comprises a target image object, the original image being a two-dimensional image; performing image cropping on the original image according to the target image region, to obtain a subimage comprising the target image object; and performing node recognition on the subimage based on a preset node recognition model, to obtain image position information of each node of the target image object in the original image.

Abstract: An apparatus for training a classifying model comprises: a first obtaining unit configured to input a sample image to a first machine learning framework, to obtain a first classification probability and a first classification loss; a second obtaining unit configured to input a second image to a second machine learning framework, to obtain a second classification probability and a second classification loss, the two machine learning frameworks having identical structures and sharing identical parameters; a similarity loss calculating unit configured to calculate a similarity loss related to a similarity between the first classification probability and the second classification probability; a total loss calculating unit configured to calculate the sum of the similarity loss, the first classification loss and the second classification loss, as a total loss; and a training unit configured to adjust parameters of the two machine learning frameworks to obtain a trained classifying model.