Various embodiments are disclosed for detecting, tracking and counting objects of interest in video. In an embodiment, a method of detecting and tracking objects of interest comprises: obtaining, by a computing device, multiple frames of images from an image capturing device; detecting, by the computing device, objects of interest in each frame; accumulating, by the computing device, multiple frames of object detections; creating, by the computing device, object tracks based on a batch of object detections over multiple frames; and associating, by the computing device, the object tracks over consecutive batches.

Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

A method of enhancing an image includes increasing sampling rate of a first image to a target sampling rate to form an interpolated image. The method also includes processing a second image through a high pass filter to form a high pass features image, wherein the second image is at the target sampling rate. The method also includes extracting detail from the high pass features image relevant to the first image, merging the detail from the high pass features image with the interpolated image to form a prediction image at the target sampling rate, and outputting the prediction image.

An information processing apparatus includes: a plurality of stereo cameras arranged so that directions of baseline lengths of the stereo cameras intersect each other; a depth estimation unit that estimates, from captured images captured by the plurality of stereo cameras, a depth of an object included in the captured images; and an object detection unit that detects the object based on the depth estimated by the depth estimation unit and reliability of the depth, the reliability being determined in accordance with an angle of a direction of an edge line of the object with respect to the directions of the baseline lengths of the plurality of stereo cameras.

A better basis for a further processing such as virtual view rendering, in form of a disparity map is achieved. To this end, the disparity map generation is done in two separate steps, namely the generation of two depth/disparity map estimates based on two different pairs of views of the scene in a manner independent from each other, with then comparing both depth/disparity map estimates so as to obtain a reliability measure for one or both of the depth/disparity map estimates.

A method for providing a model file to a user. The user acquires a plurality of images using a device, such as a smart phone, with at least a monocular image capture device. The plurality of images are then processed to provide the user with a model file. The model file is created by a minimization of an energy which is done using a primal-dual hybrid gradient. The model file may be used in a printer capable of printing in three dimensions. The user is either charged a fee for uploading the plurality of images, downloading the model file, or both.

Disclosed are an object positioning method and an object positioning device based on object detection results of plural stereo cameras. The method comprises a step of obtaining, when each of the plural stereo cameras continuously carries out tracking and detection with respect to each of objects, positional information of the corresponding object; a step of generating, based on the positional information of the corresponding object, a trajectory of the corresponding object; and a step of carrying out a merging process with respect to the trajectories generated corresponding to the plural stereo cameras so as to determine at least one object position.

Techniques related to 3D image capture with dynamic cameras.

The present disclosure describes structured-stereo imaging assemblies including separate imagers for different wavelengths. The imaging assembly can include, for example, multiple imager sub-arrays, each of which includes a first imager to sense light of a first wavelength or range of wavelengths and a second imager to sense light of a different second wavelength or range of wavelengths. Images acquired from the imagers can be processed to obtain depth information and/or improved accuracy. Various techniques are described that can facilitate determining whether any of the imagers or sub-arrays are misaligned.

One embodiment may take the form of a method for providing security for access to a goal including storing a first image and receiving a second image comprising polarized data. The method also includes comparing the first image with the second image to determine if the first image and the second image are substantially the same. In the event the first and second images are not substantially the same, the method includes denying access to the goal. In the event the first and second images are substantially the same, the method includes determining, utilizing the polarized information, if the second image is of a three-dimensional object. Further, in the event the second image is not of a three-dimensional object, the method includes denying access to the goal and, in the event the second image is of a three-dimensional object, permitting access to the goal.