Abstract: Techniques are provided for tracking different types of subjects and labeling the tracks according to subject type. In an implementation, the tracking includes tracking first and second subject types using video, and also tracking subjects of the first type using Wi-Fi tags provided to the subjects of the first type. The video and Wi-Fi tracks can be compared in order to identify and label which video tracks are associated with subjects of the first type and which video tracks are associated with subjects of the second type. Upon the tracks having been labeled, interactions between the different subject types can be identified and analyzed.

Abstract: A lane boundary marking line detection device includes an imaging device, a lane boundary detection unit, a lane boundary marking line search unit. The lane boundary detection unit detects first and second lane boundaries based on image information in an imaging area. The lane boundary marking line search unit searches for a lane boundary marking line on a road surface on a second lane boundary's side based on a position of the first lane boundary, sets search lines on the road surface on the second lane boundary's side based on shape information on the first lane boundary, and acquires search line brightness information based on the image information. When not determining that there is the search line that is most probable as the lane boundary marking line, the lane boundary marking line search unit does not select any of the search lines as the lane boundary marking line candidate line.

Abstract: Described herein is a method and system for marker-less three-dimensional modelling, fitting and tracking of a skeletal representation of an object in a three-dimensional point cloud. In particular, it concerns the tracking of a human user skeletal representation with respect to time. The method comprises inputting a three-dimensional point cloud derived from a depth map; predetermining a set of control points representing the skeleton of the user, determining a start-up skeleton pose, obtaining an orthographic representation of the user 3D point cloud projected onto a grid by sampling the 3D point cloud with a predetermined static size, determining a set of curvature centers points approximating central axes of main parts of the user, determining the torso plane, and refining and/or defining the principal direction of the body.

Abstract: Methods, systems, and devices are described for determining an orientation of a mobile device. One method includes capturing, at the mobile device, an image of at least one illuminated object defining an illuminated reference axis; determining a first angle between the illuminated reference axis and a device reference axis of the mobile device; determining a second angle between the illuminated reference axis and a common reference axis; estimating a third angle between the device reference axis and the common reference axis; and determining an orientation of the mobile device based at least in part on the first angle, the second angle, and the third angle.

Abstract: A method and system for performing model-based registration and critical dimension measurement is disclosed. The method includes: utilizing an imaging device to obtain at least one optical image of a measurement site specified for a photomask; retrieving a design of photomask and utilizing a computer model of the imaging device to generate at least one simulated image of the measurement site; adjusting at least one parameter of the computer model to minimize dissimilarities between the simulated images and the optical images, wherein the parameters includes at least a pattern registration parameter or a critical dimension parameter; and reporting the pattern registration parameter or the critical dimension parameter of the computer model when dissimilarities between the simulated images and the optical images are minimized.

Abstract: An apparatus and a method for generating an image from N reception signal data sets of signals received by a plurality of coils of a magnetic resonance tomography appliance from a region of a body to be examined using an image processing computer are provided. The apparatus includes a degree-of-compression determining device. A ratio N/M of the number N of N reception signal data sets generated from the signals received by the plurality of coils to a smaller number M of mode data sets is defined taking account of a plurality of parameters. The plurality of parameters at least also represent system resources of the image processing computer. Using a compression computer, the N reception signal data sets are compressed into M mode data sets. After this, the M mode data sets are used by the image processing computer for generating the image of the region of the body.

Abstract: The present invention provides a method and an apparatus for detecting a traffic monitoring video. The method comprises: determining a background reference model; determining a target area image in the traffic monitoring video according to the background reference model; updating the background reference model by using the target area image; summating all target points in detection area of each frame of image in the traffic monitoring video according to the updated background reference model to obtain a total area of all the target points; segmenting the frame with the biggest total area to obtain a target area at the best position; and extracting vehicle information from the target area at the best position. By using the present invention, the accuracy of a detection result in a complex environment may be improved.

Abstract: Systems and methods for processing an image through an ordered series of image filters (i.e., an image filter chain) to produce an output image. The systems and methods of the present disclosure function to partition or break-up an image into dynamically sized tiles which are processed efficiently (e.g., using minimal memory), quickly and on-demand. The systems and methods allow tile sizes to be calculated dynamically based on what each image filter in an image filter chain needs. By processing each tile on-demand, significant memory and time savings are achieved because only the parts of an image required for display are processed. Further, such functionality allows for decoding of only a portion of the image, which requires less memory and operates much faster than if the entire image was decoded.

Abstract: A method for detecting a vehicle running a stop signal positioned at an intersection includes acquiring a sequence of frames from at least one video camera monitoring an intersection being signaled by the stop signal. The method includes defining a first region of interest (ROI) including a road region located before the intersection on the image plane. The method includes searching the first ROI for a candidate violating vehicle. In response to detecting the candidate violating vehicle, the method includes tracking at least one trajectory of the detected candidate violating vehicle across a number of frames. The method includes classifying the candidate violating vehicle as belonging to one of a violating vehicle and a non-violating vehicle based on the at least one trajectory.

Abstract: There is provided an image processing device including an image input unit configured to input captured image data of a portion of parking stalls that are compartmented at least by a first side line extending in a first direction and a second side line extending in the first direction, an image processing unit configured to generate edge image data by performing an edge extraction process on the captured image data, and a parking determination unit configured to obtain an integrated value of edge pixels of the first direction portion corresponding to the parking stalls in each position of a second direction that is orthogonal to the first direction based on the edge image data, and then to determine whether or not vehicles are parked in the parking stalls based on the obtained integrated value of each position of the second direction.

Abstract: The present invention provides a method and an apparatus for detecting traffic video information. The method includes: acquiring a traffic video stream; determining color features of each frame of image in the traffic video stream; calculating the inter-frame distance between adjacent frames according to the color features; calculating the boundary of an image clustered frames' group according to the inter-frame distance by adopting an image clustering evaluation standard in RGB space and an image clustering evaluation standard in YUV space respectively; and determining a final boundary of the image clustered frames' group according to the boundaries of the image clustered frames' group in RGB space and YUV space. By using the present invention, the stability of detection results in different environments may be improved.

Abstract: The disclosure herein describes a client-side system that enhances user experience on a remoting client without consuming additional network bandwidth. During operation, the system receives a sequence of frame updates for a display screen, and determines a sequence of frames corresponding to the frame updates. The system further adaptively applies one or more image enhancing techniques to the sequence of frames based on available network bandwidth, frame refresh rate, or image quality. The image enhancement techniques include predicting a frame based on previously received frames, interpolating a frame based on at least two buffered frames, and reducing appearance of artifacts in a received frame, thereby reducing visual artifacts.

Abstract: Image data, such as from a mobile phone camera, is analyzed to determine a colorfulness metric (e.g., saturation) or a contrast metric (e.g., Weber contrast). This metric is then used in deciding which of, or in which order, plural different image recognition processes should be invoked in order to present responsive information to a user. A great number of other features and arrangements are also detailed.

Abstract: A people counting system includes: a top-view, a first and a second side-view image-capturing device, capturing a top-view, a first and a second side-view image respectively; an image stitching module, stitching the top-view, the first and the second side-view image into an ultra wide-angle image; a ROI selecting module, selecting at least one recognition zone and a counting zone; a face recognition module, monitoring the recognition zone to determine a face location corresponding to a face through analyzing the recognition zone; a head recognition module, monitoring the counting zone to determine a head location corresponding to a head through analyzing the counting zone; an object tracking module, the head recognition module, generating a face track and a head track; and a people counting module, counting a first number of face tracks and a second number of head tracks passing through the counting zone and generating a counting result.

Abstract: Disclosed is a computer-implemented method for classifying a detected region of change of a video frame as indicating an abandoned object or a removed object, the detected region of change is classified as an removed object if the temporal change of the edge consistency is from a more consistent state to a less consistent state, and the detected region of change is classified as an abandoned object if the temporal change of the edge consistency if from a less consistent to a more consistent state.

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract: An X-ray CT apparatus according to an exemplary embodiment includes: a specifying unit that specifies the position of a lesion and the position of a surrounding site positioned in a surrounding of the lesion, from pieces of image data of the inside of the patient corresponding to the mutually-different temporal phases; a movement information calculating unit that calculates movement information related to movements of the lesion and the surrounding site, based on the positions of the lesion and the surrounding site specified by the specifying unit; and a relative relationship calculating unit that calculates a relative relationship between the movement information of the lesion and the movement information of the surrounding site calculated by the movement information calculating unit.

Abstract: The processing of remote sensing data, wherein first image data are processed with the use of second digital image data which, compared with the first image data, have a finer local resolution. The local resolution of the first digital image data is refined temporarily. The local resolution and every pixel of the temporarily refined first image data corresponds to the local resolution and each pixel of the second digital image data. Determining a weighting value for the pixels of the second digital image data which corresponds to a weighting of a image value of the pixel in the ratio of the image value of the pixel to image values of surrounding pixels. A smoothing of the local plot of the image values in the area of the pixel and its environment is implemented such that the weighting value of larger values is based on additional smoothing of image values.

Abstract: A method plans paths of a set of mobile sensors with changeable positions and orientations in an environment. Each sensor includes a processor, an imaging system and a communication system. A desired resolution of coverage of the environment is defined, and an achieved resolution of the coverage is initialized. For each time instant and each sensor, an image of the environment is acquired using the imaging system. The achieved resolution is updated according to the image. The sensor is moved to a next position and orientation based on the achieved resolution and the desired resolution. Then, local information of the sensor is distributed to other sensors using the communication system to optimize a coverage of the environment.

Abstract: A system for reviewing digitized images of pathology specimens includes an image processing system and an image display system adapted to communicate with the image processing system. The image processing system is configured to receive a whole-slide digital image of a pathology specimen, segment the whole-slide digital image into a tissue-particle image within the whole-slide digital image, and represent the tissue-particle image as a plurality of image tiles such that each of the plurality of image tiles can be displayed sequentially on the image display system to permit a substantially complete, tile-by-tile review of the tissue-particle image in a predefined order.