Abstract: Techniques are disclosed for identifying discriminative, fine-grained features of an object in an image. In one example, an input device receives an image. A machine learning system includes a model comprising a first set, a second set, and a third set of filters. The machine learning system applies the first set of filters to the received image to generate an intermediate representation of the received image. The machine learning system applies the second set of filters to the intermediate representation to generate part localization data identifying sub-parts of an object and one or more regions of the image in which the sub-parts are located. The machine learning system applies the third set of filters to the intermediate representation to generate classification data identifying a subordinate category to which the object belongs. The system uses the part localization and classification data to perform fine-grained classification of the object.

Abstract: Embodiments of the disclosed technologies include a method of capturing, using a mobile device, a best-focused image of a skin surface of a subject, the method including: setting a camera of the mobile device to a fixed focal length; capturing, using the camera, a current image of a plurality of images of the skin surface, the plurality of images having a sequence and including a first previous image captured, using the camera, previously to the current image and a second previous image captured, using the camera, previously to the first previous image; producing a modified image from the current image; transforming the modified image, using a Laplacian pyramid, to produce a plurality of first luminance values from the modified image and a plurality of second luminance values from the plurality of first luminance values; averaging a plurality of first squared values, each including a square of a corresponding first luminance value of the plurality of first luminance values, to produce a first energy value; av

Abstract: Device logic in a mobile device configures a processor to capture a series of images, such as a video, using a consumer-grade camera, and to analyze the images to determine the best-focused image, of the series of images, that captures a region of interest. The images may be of a textured surface, such as facial skin of a mobile device user. The processor sets a focal length of the camera to a fixed position for collecting the images. The processor may guide the user to position the mobile device for capturing the images, using audible cues. For each image, the processor crops the image to the region of interest, extracts luminance information, and determines one or more energy levels of the luminance via a Laplacian pyramid. The energy levels may be filtered, and then are compared to energy levels of the other images to determine the best-focused image.

Abstract: Techniques are disclosed for identifying discriminative, fine-grained features of an object in an image. In one example, an input device receives an image. A machine learning system includes a model comprising a first set, a second set, and a third set of filters. The machine learning system applies the first set of filters to the received image to generate an intermediate representation of the received image. The machine learning system applies the second set of filters to the intermediate representation to generate part localization data identifying sub-parts of an object and one or more regions of the image in which the sub-parts are located. The machine learning system applies the third set of filters to the intermediate representation to generate classification data identifying a subordinate category to which the object belongs. The system uses the part localization and classification data to perform fine-grained classification of the object.

Abstract: Device logic in a mobile device configures a processor to capture a series of images, such as a video, using a consumer-grade camera, and to analyze the images to determine the best-focused image, of the series of images, that captures a region of interest. The images may be of a textured surface, such as facial skin of a mobile device user. The processor sets a focal length of the camera to a fixed position for collecting the images. The processor may guide the user to position the mobile device for capturing the images, using audible cues. For each image, the processor crops the image to the region of interest, extracts luminance information, and determines one or more energy levels of the luminance via a Laplacian pyramid. The energy levels may be filtered, and then are compared to energy levels of the other images to determine the best-focused image.

Abstract: The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.

Abstract: The present invention is a system and a method of segmenting and detecting objects which can be approximated by planar or nearly planar surfaces in order to detect one or more objects with threats or potential threats. The method includes capturing imagery of the scene proximate a platform, producing a depth map from the imagery and tessellating the depth map into a number of patches. The method also includes classifying the plurality of patches as threat patches and projecting the threat patches into a pre-generated vertical support histogram to facilitate selection of the projected threat patches having a score value within a sufficiency criterion. The method further includes grouping the selected patches having the score value using a plane fit to obtain a region of interest and processing the region of interest to detect said object.

Abstract: The present invention provides a collision avoidance apparatus and method employing stereo vision applications for adaptive vehicular control. The stereo vision applications are comprised of a road detection function and a vehicle detection and tracking function. The road detection function makes use of three-dimensional point data, computed from stereo image data, to locate the road surface ahead of a host vehicle. Information gathered by the road detection function is used to guide the vehicle detection and tracking function, which provides lead motion data to a vehicular control system of the collision avoidance apparatus. Similar to the road detection function, stereo image data is used by the vehicle detection and tracking function to determine the depth of image scene features, thereby providing a robust means for identifying potential lead vehicles in a headway direction of the host vehicle.

Abstract: A vision system for a vehicle that identifies and classifies objects (targets) located proximate a vehicle. The system comprises a sensor array that produces imagery that is processed to generate depth maps of the scene proximate a vehicle. The depth maps are processed and compared to pre-rendered templates of target objects that could appear proximate the vehicle. A target list is produced by matching the pre-rendered templates to the depth map imagery. The system processes the target list to produce target size and classification estimates. The target is then tracked as it moves near a vehicle and the target position, classification and velocity are determined. This information can be used in a number of ways. For example, the target information may be displayed to the driver, the information may be used for an obstacle avoidance system that adjusts the trajectory or other parameters of the vehicle to safely avoid the obstacle.

Abstract: The present invention relates to a system and method for detecting one or more targets belonging to a first class (e.g., moving and/or stationary people), from a moving platform in a 3D-rich environment. The framework described here is implemented using a number of monocular or stereo cameras distributed around the vehicle to provide 360 degrees coverage. Furthermore, the framework described here utilizes numerous filters to reduce the number of false positive identifications of the targets.

Abstract: The present invention is a system and a method of segmenting and detecting objects which can be approximated by planar or nearly planar surfaces in order to detect one or more objects with threats or potential threats. The method includes capturing imagery of the scene proximate a platform, producing a depth map from the imagery and tessellating the depth map into a number of patches. The method also includes classifying the plurality of patches as threat patches and projecting the threat patches into a pre-generated vertical support histogram to facilitate selection of the projected threat patches having a score value within a sufficiency criterion. The method further includes grouping the selected patches having the score value using a plane fit to obtain a region of interest and processing the region of interest to detect said object.

Abstract: A vision system for a vehicle that identifies and classifies objects (targets) located proximate a vehicle. The system comprises a sensor array that produces imagery that is processed to generate depth maps of the scene proximate a vehicle. The depth maps are processed and compared to pre-rendered templates of target objects that could appear proximate the vehicle. A target list is produced by matching the pre-rendered templates to the depth map imagery. The system processes the target list to produce target size and classification estimates. The target is then tracked as it moves near a vehicle and the target position, classification and velocity are determined. This information can be used in a number of ways. For example, the target information may be displayed to the driver, the information may be used for an obstacle avoidance system that adjusts the trajectory or other parameters of the vehicle to safely avoid the obstacle.

Abstract: A vehicle vision system that uses a depth map, image intensity data, and system calibration parameter to determine a target's dimensions and relative position. Initial target boundary information is projected onto the depth map and onto the image intensity. A visibility analysis determines whether the rear of a target is within the system's field of view. If so, the mapped image boundary is analyzed to determine an upper boundary of the target. Then, vertical image edges of the mapped image boundary are found by searching for a strongest pair of vertical image edges that are located at about the same depth. Then, the bottom of the mapped image boundary is found (or assumed from calibration parameters). Then, the target's position is found by an averaging technique. The height and width of the target are then computed.

Abstract: A vision system for a vehicle that identifies and classifies objects (targets) located proximate a vehicle. The system comprises a sensor array that produces imagery that is processed to generate depth maps of the scene proximate a vehicle. The depth maps are processed and compared to pre-rendered templates of target objects that could appear proximate the vehicle. A target list is produced by matching the pre-rendered templates to the depth map imagery. The system processes the target list to produce target size and classification estimates. The target is then tracked as it moves near a vehicle and the target position, classification and velocity are determined. This information can be used in a number of ways. For example, the target information may be displayed to the driver, the information may be used for an obstacle avoidance system that adjusts the trajectory or other parameters of the vehicle to safely avoid the obstacle.

Abstract: A vision system for a vehicle that identifies and classifies objects (targets) located proximate a vehicle. The system comprises a sensor array that produces imagery that is processed to generate depth maps of the scene proximate a vehicle. The depth maps are processed and compared to pre-rendered templates of target objects that could appear proximate the vehicle. A target list is produced by matching the pre-rendered templates to the depth map imagery. The system processes the target list to produce target size and classification estimates. The target is then tracked as it moves near a vehicle and the target position, classification and velocity are determined. This information can be used in a number of ways. For example, the target information may be displayed to the driver, the information may be used for an obstacle avoidance system that adjusts the trajectory or other parameters of the vehicle to safely avoid the obstacle.