Abstract: Provided are methods for a track refinement network. In examples, center boxes are obtained from a record of driving data, wherein a center box is a center of a sequence of boxes along a track, and the track is associated with a tracked object detected within the sequence of boxes, each respective box comprising a center, a size, and an orientation. Track windows are generated around respective center boxes, wherein a track window corresponds to a respective center box along the track. Track windows are cropped and normalized with respect to center boxes to enable single refinement model for multiple object classes. Point cloud features and trajectory features are extracted from the cropped and normalized track windows. The point cloud features and trajectory features are input into a track refinement network, wherein the track refinement network uses features from the entire track to output a refined center, a refined size, and a refined orientation of each respective center box.

Abstract: A high-definition map building method includes determining a key node describing information about a key position of a lane attribute change, determining a key node layer based on a position of the key node and an attribute of the key node, and determining a high-definition map based on a navigation map and the key node layer. The navigation map provides road-level navigation information, and the high-definition map provides lane-level navigation information.

Abstract: The present disclosure discloses a display apparatus, a stereoscopic display apparatus, and an application terminal thereof. The display apparatus includes a display panel and a light collimation module. The display panel includes an RGB pixel array. The RGB pixel array includes multiple RGB pixels disposed at intervals. The light collimation module includes a control electrode layer, a first transparent substrate, a liquid crystal layer, and a second transparent substrate. The control electrode layer is disposed within the intervals between the RGB pixels or at positions that are on the display panel and that are corresponding to the intervals between the RGB pixels. The first transparent substrate is disposed on the display panel and covers the control electrode. The liquid crystal layer is disposed on the first transparent substrate. The second transparent substrate is disposed on the liquid crystal layer.

Abstract: The present invention provides a stereoscopic imaging apparatus (100), including: a display module (130), including a display pixel layer (131) and a first substrate (132), where the display pixel layer (131) includes a pixel array (133), and the first substrate (132) is disposed on the display pixel layer (131); a second substrate (120), disposed opposite to the first substrate (132); and a first lens layer (110), including a lens array (111), where the first lens layer (110) is disposed between the first substrate (132) and the second substrate (120), and the lens array (111) is configured to receive light transmitted by the pixel array (133), and deflect light, which is transmitted by a corresponding pixel in the pixel array (133), to a different projection direction to implement stereoscopic parallax.

Abstract: Embodiments of the present disclosure disclose a static object reconstruction method and system that are applied to the field of graph and image processing technologies. In the embodiments of the present disclosure, when a static object reconstruction system does not obtain, by means of calculation, an extrinsic camera parameter in a preset time when calculating the extrinsic camera parameter based on a three-dimensional feature point, it indicates that depth data collected by a depth camera is lost or damaged, and a two-dimensional feature point is used to calculate the extrinsic camera parameter to implement alignment of point clouds of a frame of image according to the extrinsic camera parameter. In this way, a two-dimensional feature point and a three-dimensional feature point are mixed, which can implement that a static object can also be successfully reconstructed when depth data collected by a depth camera is lost or damaged.

Abstract: The present disclosure discloses a display apparatus, a stereoscopic display apparatus, and an application terminal thereof. The display apparatus includes a display panel and a light collimation module. The display panel includes an RGB pixel array. The RGB pixel array includes multiple RGB pixels disposed at intervals. The light collimation module includes a control electrode layer, a first transparent substrate, a liquid crystal layer, and a second transparent substrate. The control electrode layer is disposed within the intervals between the RGB pixels or at positions that are on the display panel and that are corresponding to the intervals between the RGB pixels. The first transparent substrate is disposed on the display panel and covers the control electrode. The liquid crystal layer is disposed on the first transparent substrate. The second transparent substrate is disposed on the liquid crystal layer.

Abstract: A stereoscopic imaging apparatus and method, a display, and a terminal are disclosed. A stereoscopic imaging apparatus (100) includes: a display panel (110), including a pixel array and configured to display images; and at least two lens layers (120, 130), disposed in a position corresponding to the pixel array, and configured to alternately deflect, according to applied time-multiplexing electric fields, light rays of the images displayed by all pixels (111 to 116) in the pixel array to at least four different projection directions, where a deflection angle corresponding to the at least four different projection directions is a sum of deflection angles of all of the at least two lens layers (120, 130), so that multiple persons can simultaneously view a three-dimensional stereoscopic image.

Abstract: Embodiments of the present invention provide a method for presenting communication information in video communication, including: controlling collection of audio information and video information of a video communication site; determining a position of a speaker in the video communication site according to the audio information, where the speaker is a person of participants in the video communication site that speaks; acquiring speech video information from the video information according to the position of the speaker, where the speech video information is video information of the speaker within a speaking period; and controlling presentation of the speech video information.

Abstract: Embodiments of the present invention relate to a display apparatus including: a display layer including a pixel array, a first lens layer, and a second lens layer. The second lens layer is disposed between the first lens layer and the display layer. The first lens layer includes a first lens array, where the first lens array is configured to deflect lights passing through the first lens array in different projection directions, so as to achieve stereoscopic parallax. The second lens layer includes a second lens array, and the second lens array is configured to project beams, emitted from the pixel array, onto the first lens array. A structure of the display apparatus can reduce impact of a phenomenon of crosstalk between pixels of the display apparatus, thereby improving a resolution and a display effect of the display apparatus.

Abstract: The present invention provides a stereoscopic imaging apparatus (100), including: a display module (130), including a display pixel layer (131) and a first substrate (132), where the display pixel layer (131) includes a pixel array (133), and the first substrate (132) is disposed on the display pixel layer (131); a second substrate (120), disposed opposite to the first substrate (132); and a first lens layer (110), including a lens array (111), where the first lens layer (110) is disposed between the first substrate (132) and the second substrate (120), and the lens array (111) is configured to receive light transmitted by the pixel array (133), and deflect light, which is transmitted by a corresponding pixel in the pixel array (133), to a different projection direction to implement stereoscopic parallax.

Abstract: Embodiments of the present disclosure disclose a static object reconstruction method and system that are applied to the field of graph and image processing technologies. In the embodiments of the present disclosure, when a static object reconstruction system does not obtain, by means of calculation, an extrinsic camera parameter in a preset time when calculating the extrinsic camera parameter based on a three-dimensional feature point, it indicates that depth data collected by a depth camera is lost or damaged, and a two-dimensional feature point is used to calculate the extrinsic camera parameter to implement alignment of point clouds of a frame of image according to the extrinsic camera parameter. In this way, a two-dimensional feature point and a three-dimensional feature point are mixed, which can implement that a static object can also be successfully reconstructed when depth data collected by a depth camera is lost or damaged.

Abstract: The present invention discloses a method and an apparatus for detecting a convex polygon image block, and a device. The method includes: acquiring an image collected by an image sensor; acquiring a corner set, where the corner set includes a corner in the image, and the corner is an intersection point at which any two straight line sides that are not parallel to each other in the image intersect; and detecting a convex polygon image block in the image according to the corner set, where a shape of the convex polygon image block is a preset shape and a similarity between the convex polygon image block and a preset image block exceeds a preset first threshold. The apparatus includes: a first acquiring module, a second acquiring module, and a detecting module. In the present invention, the convex polygon image block can be detected from the image.

Abstract: Embodiments of the present invention disclose an incoming call processing method and a mobile terminal, where the method includes: when a signal for an incoming call is received, acquiring an image by using a preset shooting apparatus; each time after an image is acquired, performing human face detection on the image, and determining a variation of a distance between the mobile terminal and a detected human face; and performing corresponding processing on the incoming call according to the variation of the distance. According to the embodiments of the present invention, an instruction of a user may be accurately analyzed according to a distance between a mobile terminal and a human face, and corresponding incoming call processing may be performed, thereby reducing a probability of mistakenly answering an incoming call and improving accuracy of incoming call processing.

Abstract: Embodiments of the present disclosure provide a stereoscopic imaging apparatus and method, and a display. The stereoscopic imaging apparatus includes: a display panel, which includes multiple pixel units, and is configured to display images in a time division multiplexing scheme; and an electro-optic modulation layer, which includes multiple electro-optic modulation units respectively arranged at positions corresponding to the multiple pixel units, and is configured to alternately deflect light rays of the images displayed on the multiple pixel units into different projection directions under the effect of electric fields that change in a time division multiplexing scheme, where the electric fields that change in a time division multiplexing scheme change synchronously with the images displayed in a time division multiplexing scheme. The technical solutions of the embodiments of the present disclosure can improve resolution of auto-stereoscopic display.

Abstract: A computation system comprising an orientation detection device configured to detect position information comprising a position and an orientation of the computation system, a multi-sensor system coupled to the orientation detection device, wherein the multi-sensor system is configured to capture environmental input data, wherein the multi-sensor system comprises at least one of an audio capturing system and a three-dimensional (3D) image capturing system, and wherein the environmental input data comprises at least one of audio and an image, and at least one signal processing component coupled to the orientation detection device and to the multi-sensor system, wherein the processor is configured to modify the captured environmental input data based on the position information.

Abstract: Embodiments of the present invention provide a method for presenting communication information in video communication, including: controlling collection of audio information and video information of a video communication site; determining a position of a speaker in the video communication site according to the audio information, where the speaker is a person of participants in the video communication site that speaks; acquiring speech video information from the video information according to the position of the speaker, where the speech video information is video information of the speaker within a speaking period; and controlling presentation of the speech video information.

Abstract: A computation system comprising an orientation detection device configured to detect position information comprising a position and an orientation of the computation system, a multi-sensor system coupled to the orientation detection device, wherein the multi-sensor system is configured to capture environmental input data, wherein the multi-sensor system comprises at least one of an audio capturing system and a three-dimensional (3D) image capturing system, and wherein the environmental input data comprises at least one of audio and an image, and at least one signal processing component coupled to the orientation detection device and to the multi-sensor system, wherein the processor is configured to modify the captured environmental input data based on the position information.

Abstract: The present invention discloses a method and an apparatus for detecting a convex polygon image block, and a device. The method includes: acquiring an image collected by an image sensor; acquiring a corner set, where the corner set includes a corner in the image, and the corner is an intersection point at which any two straight line sides that are not parallel to each other in the image intersect; and detecting a convex polygon image block in the image according to the corner set, where a shape of the convex polygon image block is a preset shape and a similarity between the convex polygon image block and a preset image block exceeds a preset first threshold. The apparatus includes: a first acquiring module, a second acquiring module, and a detecting module. In the present invention, the convex polygon image block can be detected from the image.

Abstract: An encoding device can achieve both highly effective encoding/decoding and high-quality decoding audio when executing a scalable stereo audio encoding by using MDCT and ICP. In the encoding device, an MDCT converter executes an MDCT conversion on a residual signal of left channel/right channel subjected to window processing. An MDCT converter executes an MDCT conversion on the monaural residual signal which has been subjected to the window processing. An ICP analyzer executes an ICP analysis by using the correlation between a frequency coefficient of a high-band portion of the left channel/right channel and a frequency coefficient of a high-band portion of the monaural residual signal so as to generate an ICP parameter of the left channel/right channel residual signal. An ICP parameter quantizes each of the ICP parameters. A low-band encoding unit encoder executes highly-accurate encoding on the frequency coefficient of the low-band portion of the left channel/right channel residual signal.

Abstract: A deceleration mechanism comprises a base, a transmission device rotatably connected to the base, and a driving device fixed to the base. The transmission device includes a driving assembly having a driving wheel and a driven assembly having a driven wheel. Diameter of the driven wheel is greater than that of the driving wheel. The driving device provides power to rotate the driving wheel. The transmission device further includes a transmission member wound on the driving wheel and the driven wheel. The transmission member winds on the driving wheel at least one winding, then criss-crosses and winds on the driven wheel.