An apparatus for performing object recognition includes an image camera to capture a first resolution image and a depth map camera to capture a second resolution depth map. The first resolution is greater than the second resolution. The apparatus is configured to perform object recognition based on the image and the depth map.

Systems and methods for viewing stereoscopic video images are disclosed. The systems can include a first video camera configured to generate a first video feed of a subject, and a second video camera configured to generate a second video feed of the subject. The first video feed and the second video feed combined generate a near real-time stereoscopic video image. A tracking module can be associated with the first video camera and the second video camera, and can be configured to cause the first video camera and the second video camera to be directed to a desired convergent point relative to a selected tracking point to maintain stereopsis. The system may further include an array of video cameras, a gesture control module, an image adjustment module, a calibration module, or a 3-D modeling module, for example.

We disclose sensor systems, and associated calibration systems and methods, that provide efficient and reliable depth and texture fusion. One disclosed method includes transmitting a first light beam from a first perspective, transmitting a second light beam from a second perspective, aligning a visible light photodetector with the second perspective, aligning a depth sensor with the first perspective, and mutually registering the visible light photodetector and the depth sensor using a return of the first light beam, a return of the second light beam, and a reference map. The reference map can include a transform from a reference frame based on the first perspective and a reference frame based on the second perspective.

An exemplary data precision preservation system divides a depth representation into a first section and a second section separate from the first section. The system determines data bits representing numbers that correspond to a lowest non-null depth value and a highest non-null depth value represented in the first section, and converts an original set of depth values represented in the first section to a compressed set of depth values normalized based on the lowest and highest non-null depth values represented in the first section. The system then generates a dataset that includes data representative of the compressed set of depth values and an inverse view-projection transform that is based on the lowest and highest non-null depth values represented in the first section and is configured to facilitate conversion of the compressed set of depth values back to the original set of depth values. Corresponding systems and methods are also disclosed.

Described examples include an integrated circuit having depth fusion engine circuitry configured to receive stereoscopic image data and, in response to the received stereoscopic image data, generate at least: first and second focal perspective images for viewing by a first eye at multiple focal distances; and third and fourth focal perspective images for viewing by a second eye at multiple focal distances. The integrated circuit further includes display driver circuitry coupled to the depth fusion engine circuitry and configured to drive a display device for displaying at least the first, second, third and fourth focal perspective images.

This disclosure is directed to coding a multi-view signal, which includes processing a list of plurality of motion vector candidates associated with a coding block of a current picture in a dependent view of the multi-view signal. Such processing includes estimating a first motion vector based on a second motion vector associated with a reference block in a current picture of a reference view of the multi-view signal, the reference block corresponding to the coding block of the current picture in the dependent view. The first motion vector is added into the list, and an index is used that specifies at least one candidate from the list to be used for motion-compensated prediction. The coding block in the current picture is coded by performing the motion-compensated prediction based on the at least one candidate indicated by the index.

Using the same image sensor to capture both a two-dimensional (2D) image of a three-dimensional (3D) object and 3D depth measurements for the object. A laser point-scans the surface of the object with light spots, which are detected by a pixel array in the image sensor to generate the 3D depth profile of the object using triangulation. Each row of pixels in the pixel array forms an epipolar line of the corresponding laser scan line. Timestamping provides a correspondence between the pixel location of a captured light spot and the respective scan angle of the laser to remove any ambiguity in triangulation. An Analog-to-Digital Converter (ADC) in the image sensor generates a multi-bit output in the 2D mode and a binary output in the 3D mode to generate timestamps. Strong ambient light is rejected by switching the image sensor to a 3D logarithmic mode from a 3D linear mode.

Using the same image sensor to capture both a two-dimensional (2D) image of a three-dimensional (3D) object and 3D depth measurements for the object. A laser point-scans the surface of the object with light spots, which are detected by a pixel array in the image sensor to generate the 3D depth profile of the object using triangulation. Each row of pixels in the pixel array forms an epipolar line of the corresponding laser scan line. Timestamping provides a correspondence between the pixel location of a captured light spot and the respective scan angle of the laser to remove any ambiguity in triangulation. An Analog-to-Digital Converter (ADC) in the image sensor generates a multi-bit output in the 2D mode and a binary output in the 3D mode to generate timestamps. Strong ambient light is rejected by switching the image sensor to a 3D logarithmic mode from a 3D linear mode.

In a depth image compressing section of an image processing device, a depth image operation section generates a depth image by operation using photographed stereo images. A difference image obtaining section generates a difference image between an actually measured depth image and the computed depth image. In a depth image decompressing section of a content processing device, a depth image operation section generates a depth image by operation using the transmitted stereo images. A difference image adding section restores a depth image by adding the computed depth image to the transmitted difference image.

An imaging unit includes a light source and a pixel array. The light source projects a line of light that is scanned in a first direction across a field of view of the light source. The line of light oriented in a second direction that is substantially perpendicular to the first direction. The pixel array is arranged in at least one row of pixels that extends in a direction that is substantially parallel to the second direction. At least one pixel in a row is capable of generating two-dimensional color information of an object in the field of view based on a first light reflected from the object and is capable of generating three-dimensional (3D) depth information of the object based on the line of light reflecting from the object. The 3D-depth information includes time-of-flight information.