5041results about "Three-dimensional object recognition" patented technology

A camera system comprises an image capturing device, object detection module, object tracking module, and match classifier. The object detection module receives image data and detects objects appearing in one or more of the images. The object tracking module temporally associates instances of a first object detected in a first group of the images. The first object has a first signature representing features of the first object. The match classifier matches object instances by analyzing data derived from the first signature of the first object and a second signature of a second object detected in a second image. The second signature represents features of the second object derived from the second image. The match classifier determine whether the second signature matches the first signature. A training process automatically configures the match classifier using a set of possible object features.

In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. A great variety of other features and arrangements are also detailed.

A system for estimating orientation of a target based on real-time video data uses depth data included in the video to determine the estimated orientation. The system includes a time-of-flight camera capable of depth sensing within a depth window. The camera outputs hybrid image data (color and depth). Segmentation is performed to determine the location of the target within the image. Tracking is used to follow the target location from frame to frame. During a training mode, a target-specific training image set is collected with a corresponding orientation associated with each frame. During an estimation mode, a classifier compares new images with the stored training set to determine an estimated orientation. A motion estimation approach uses an accumulated rotation / translation parameter calculation based on optical flow and depth constrains. The parameters are reset to a reference value each time the image corresponds to a dominant orientation.

Techniques are provided for searching on three dimensional (3D) objects across large, distributed repositories of 3D models. 3D shapes are created for input to a search system; optionally user-defined similarity criterion is used, and search results are interactively navigated and feedback received for modifying the accuracy of the search results. Search input can also be given by picking 3D models from a cluster map or by providing the orthographic views for the 3D model. Feedback can be given by a searcher as to which models are similar and which are not. Various techniques adjust the search results according to the feedback given by the searcher and present the new search results to the searcher.

The technology of the 4D-GIS system deploys a GIS-based algorithm used to determine the location of a moving target through registering the terrain image obtained from a Moving Target Indication (MTI) sensor or small Unmanned Aerial Vehicle (UAV) camera with the digital map from GIS. For motion prediction the target state is estimated using an Extended Kalman Filter (EKF). In order to enhance the prediction of the moving target's trajectory a fuzzy logic reasoning algorithm is used to estimate the destination of a moving target through synthesizing data from GIS, target statistics, tactics and other past experience derived information, such as, likely moving direction of targets in correlation with the nature of the terrain and surmised mission.

Apparatus comprises a processor; a user interface enabling user interaction with one or more software applications associated with the processor; first and second sensors configured to detect, and generate signals corresponding to, objects located within respective first and second sensing zones remote from the apparatus, wherein the sensors are configured such that their respective sensing zones overlap spatially to define a third, overlapping, zone in which both the first and second sensors are able to detect a common object; and a gesture recognition system for receiving signals from the sensors, the gesture recognition system being responsive to detecting an object inside the overlapping zone to control a first user interface function in accordance with signals received from both sensors.

Methods and arrangements involving portable user devices such smartphones and wearable electronic devices are disclosed, as well as other devices and sensors distributed within an ambient environment. Some arrangements enable a user to perform an object recognition process in a computationally- and time-efficient manner. Other arrangements enable users and other entities to, either individually or cooperatively, register or enroll physical objects into one or more object registries on which an object recognition process can be performed. Still other arrangements enable users and other entities to, either individually or cooperatively, associate registered or enrolled objects with one or more items of metadata. A great variety of other features and arrangements are also detailed.

Image analysis techniques, including object recognition analysis, are applied to images obtained by one or more image capture devices deployed within inventory environments. The object recognition analysis provides object recognition data (that may include one or more recognized product instances) based on stored product (training) images. In turn, a variety of functionalities may be enabled based on the object recognition data. For example, a planogram may be extracted and compared to a target planogram, or at least one product display parameter for a product can be determined and used to assess presence of the product within the inventory environment, or to determine compliance of display of the product with a promotional objective. In yet another embodiment, comparisons may be made within a single image or between multiple images over time to detect potential conditions requiring response. In this manner, efficiency and effectiveness of many previously manually-implemented tasks may be improved.

A computer-implemented method is provided to automatically apply predefined privileges for identified and tracked users in a space having one or more media sources. The method includes an operation to define and save to memory, a user profile. The user profile may include data that identifies and tracks a user with a depth-sensing camera. In another operation privileges that define levels of access to particular media for the user profile are defined and saved. The method also includes an operation to capture image and depth data from the depth-sensing camera of a scene within the space. In yet another operation, the user is tracked and identified within the scene from the image and depth data. In still another operation the defined privileges are automatically applied to one or more media sources, so that the user is granted access to selected content from the one or more media sources when identified and tracked within the scene.

A method and apparatus for performing two-dimensional video alignment onto three-dimensional point clouds. The system recovers camera pose from camera video, determines a depth map, converts the depth map to a Euclidean video point cloud, and registers two-dimensional video to the three-dimensional point clouds.

An apparatus, method for detecting critical areas and a pedestrian detection apparatus using the same are provided. An application of the pedestrian detection system is provided to help limit critical urban environment to particular areas. Contrary to traditional pedestrian detection systems that localize every pedestrians appearing in front of the subject vehicle, the apparatus first finds critical areas from urban environment and performs a focused search of pedestrians. The environment is reconstructed using a standard laser scanner but the subsequent checking for the presence of pedestrians is performed by incorporating a vision system. The apparatus identifies pedestrians within substantially limited image areas and results in boosts of timing performance, since no evaluation of critical degrees is necessary until an actual pedestrian is informed to the driver or onboard computer.

A method and system analyzes data acquired by image systems to more rapidly identify objects of interest in the data. In one embodiment, z-depth data are segmented such that neighboring image pixels having similar z-depths are given a common label. Blobs, or groups of pixels with a same label, may be defined to correspond to different objects. Blobs preferably are modeled as primitives to more rapidly identify objects in the acquired image. In some embodiments, a modified connected component analysis is carried out where image pixels are pre-grouped into regions of different depth values preferably using a depth value histogram. The histogram is divided into regions and image cluster centers are determined. A depth group value image containing blobs is obtained, with each pixel being assigned to one of the depth groups.

A processor-based system operating according to digitally-embedded programming instructions performs a method including identifying a group of pixels corresponding to a face region within digital image data acquired by an image acquisition device. A set of face analysis parameter values is extacted from said face region, including a faceprint associated with the face region. First and second reference faceprints are determined for a person using reference images captured respectively in predetermined face-portrait conditions and using ambient conditions. The faceprints are analyzed to determine a baseline faceprint and a range of variability from the baseline associated with the person. Results of the analyzing are stored and used in subsequent recognition of the person in a subsequent image acquired under ambient conditions.

A method for determining the pose of a camera (22, 32) relative to a real environment (40) comprises the following steps: taking at least one image (50) of a real environment by means of a camera (22, 32), the image containing at least part of a real object (41), performing a tracking method that evaluates information with respect to correspondences between features associated with the real object (41) and corresponding features of the real object (41) as it is contained in the image (50) of the real environment, so as to obtain conclusions about the pose of the camera (22, 32), determining at least one parameter of an environmental situation, and performing the tracking method in accordance with the at least one parameter. Analogously, the method can also be utilized in a method for recognizing an object of a real environment in an image taken by a camera.

Aspects of the present invention relate to context based power management of a head-worn computer.

A method for three-dimensional shape and size measurement of a three-dimensional body surface comprising providing a three-dimensional scanner, providing a processor, providing a three-dimensional Computer Aided Design system, scanning in three dimensions with the three-dimensional scanner at least a portion of the three-dimensional body surface, creating a data file representative of the three-dimensional body surface, processing the data file with the processor, importing the data file into the three-dimensional Computer Aided Design System, employing the three-dimensional Computer Aided Design System relative to the data file to define and record three-dimensional measuring data relative to at least a portion of the three-dimensional body surface, A and employing the three-dimensional Computer Aided Design System to exploit the three-dimensional measuring data.

A system and method for performing object and class recognition that allows for wide changes of viewpoint and distance of objects is disclosed. The invention provides for choosing pose-invariant interest points of a three-dimensional (3D) image, and for computing pose-invariant feature descriptors of the image. The system and method also allows for the construction of three-dimensional (3D) object and class models from the pose-invariant interest points and feature descriptors of previously obtained scenes. Interest points and feature descriptors of a newly acquired scene may be compared to the object and / or class models to identify the presence of an object or member of the class in the new scene.

Systems and methods are provided for extracting various features from data having spatial coordinates. The systems and methods may identify and extract data points from a point cloud, where the data points are considered to be part of the ground surface, a building, or a wire (e.g. power lines). Systems and methods are also provided for enhancing a point cloud using external data (e.g. images and other point clouds), and for tracking a moving object by comparing images with a point cloud. An objects database is also provided which can be used to scale point clouds to be of similar size. The objects database can also be used to search for certain objects in a point cloud, as well as recognize unidentified objects in a point cloud.

A method comprising: obtaining a three-dimensional (3D) point cloud about at least one object of interest; detecting ground and / or building objects from 3D point cloud data using an unsupervised segmentation method; removing the ground and / or building objects from the 3D point cloud data; and detecting one or more vertical objects from the remaining 3D point cloud data using a supervised segmentation method.

This invention provides a system and method for determining the three-dimensional alignment of a modeledobject or scene. After calibration, a 3D (stereo) sensor system views the object to derive a runtime 3D representation of the scene containing the object. Rectified images from each stereo head are preprocessed to enhance their edge features. A stereo matching process is then performed on at least two (a pair) of the rectified preprocessed images at a time by locating a predetermined feature on a first image and then locating the same feature in the other image. 3D points are computed for each pair of cameras to derive a 3D point cloud. The 3D point cloud is generated by transforming the 3D points of each camera pair into the world 3D space from the world calibration. The amount of 3D data from the point cloud is reduced by extracting higher-level geometric shapes (HLGS), such as line segments. Found HLGS from runtime are corresponded to HLGS on the model to produce candidate 3D poses. A coarse scoring process prunes the number of poses. The remaining candidate poses are then subjected to a further more-refined scoring process. These surviving candidate poses are then verified by, for example, fitting found 3D or 2D points of the candidate poses to a larger set of corresponding three-dimensional or two-dimensional model points, whereby the closest match is the best refined three-dimensional pose.

Disclosed are provided an apparatus and a method of a user interface for manipulating multimedia contents for a vehicle. An apparatus of a user interface for manipulating multimedia contents for a vehicle according to an embodiment of the present invention includes: a transparent display module displaying an image including one or more multimedia objects; an ultrasonic detection module detecting a user indicating means by using an ultrasonic sensor in a 3D space close to the transparent display module; an image detection module tracking and photographing the user indicating means; and a head unit judging whether or not any one of the multimedia objects is selected by the user indicating means by using information received from at least one of the image detection module and the ultrasonic detection module and performing a control corresponding to the selected multimedia object.

A method of registering 3-dimensional digitized images to 2-dimensional digitized images during a medical procedure includes providing a pair of correctly-registered training images L={lr, lf} and their joint intensity distribution pl(ir, if), wherein ir and if are reference and floating images, respectively, providing a pair of observed images O={or, of} and their joint intensity distribution po(ir, if), mapping a marginal intensity distribution of the observed pair O={or, of} to a marginal intensity distribution of the training pair L={lr, lf}, and estimating a set of parameters T that registers image of to image or by maximizing a weighted sum of a Jensen-Shannon divergence (JSD) of a joint intensity distribution of the observed pair and a joint intensity distribution of the training pair and a similarity measure between the observed images.

Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

A system, method, and computer program product for estimating human body pose are described. According to one aspect, anatomical features are detected in a depth image of a human actor. The method detects a head, neck, and trunk (H-N-T) template in the depth image, and detects limbs in the depth image based on the H-N-T template. The anatomical features are detected based on the H-N-T template and the limbs. An estimated pose of a human model is estimated based on the detected features and kinematic constraints of the human model.

A database of faceprint data corresponding to detected face regions within images acquired with an image acquisition device and digitally-embedded within one or more digital storage media includes image, identity and face recognition data components. The image data component include acquired digital image data including content data and unique identifiers corresponding to individual acquired digital images or face regions therein, or both. The identity data component includes an identification listing of known identities to which identified face regions detected within the image data have been determined to correspond. The face recognition data component includes, for an individual known identity, one or more identity tables corresponding to one or more identity entries, and one or more face class tables corresponding to one or more face class entries of the one or more identity tables. Each face class table includes one or more faceprint entries corresponding to normalized face regions determined from the acquired digital image.

Techniques are provided for searching on three dimensional (3D) objects across large, distributed repositories of 3D models. 3D shapes are created for input to a search system; optionally user-defined similarity criterion is used, and search results are interactively navigated and feedback received for modifying the accuracy of the search results. Search input can also be given by picking 3D models from a cluster map or by providing the orthographic views for the 3D model. Feedback can be given by a searcher as to which models are similar and which are not. Various techniques adjust the search results according to the feedback given by the searcher and present the new search results to the searcher.