Ambarella International LP

Shanghai Koito Automotive Lamp Co., Ltd.

Liangliang Wang

Bo Yu

Sicong Lyu

Wenhai Gao

Lei Niu

Juejing Yang

An apparatus comprises an interface and a processor. The interface may be configured to receive pixel data representing a first field of view of a camera and four-dimensional (4D) point cloud data representing a second field of view of a 4D imaging radar sensor. The first field of view of the camera and the second field of view of the 4D imaging radar sensor generally overlap. The processor may be configured to process the pixel data and the 4D point cloud data arranged as video frames and perform an extrinsic parameter calibration for the 4D imaging radar sensor and the camera based on adaptive projection error. The extrinsic parameter calibration may comprise applying a pose calibration process to the video frames. The pose calibration process may use (i) a respective translate vector and a respective rotation matrix for each of the 4D imaging radar sensor and the camera and (ii) a radar corner reflector to obtain configuration parameters for the first field of view of the camera and the second field of view of the 4D imaging radar sensor. The pose calibration process generally comprises capturing data for a plurality of positions of the radar corner reflector between a near-distance value and a long-distance value, and modifying a scale of a projection error of the radar corner reflector based on a size of the radar corner reflector in an image captured by the camera.

Extrinsic parameter calibration for 4D millimeter-wave radar and camera based on adaptive projection error

An apparatus comprises an interface and a processor. The interface may be configured to receive pixel data. The processor may be configured to (i) process the pixel data arranged as video frames, (ii) decompose each of the video frames comprising a high-resolution two-dimensional (2D) image into a plurality of 2D sub-images using a decomposition offset, (iii) decompose each of the video frames comprising a high-resolution depth map image into a plurality of depth map sub-images using the decomposition offset, (iv) calculate a respective alignment matrix for each of the plurality of 2D sub-images and a corresponding one of the plurality of depth map sub-images using the decomposition offset, (v) perform matrix operations on the plurality of 2D sub-images and the plurality of depth map sub-images using the respective alignment matrices to obtain a plurality of aligned 2D sub-images and depth map sub-images, (v) determine projection coordinates and depth values of the plurality of aligned 2D sub-images and depth map sub-images based on the high-resolution 2D image, and (vi) generate an aligned high-resolution depth map using the projection coordinates and depth values.

Accelerated alignment of high-resolution image and depth map for low-bit-width floating-point representation

An apparatus comprising an interface, a light projector and a processor. The interface may be configured to receive pixel data. The light projector may be configured to generate a structured light pattern. The processor may be configured to process the pixel data arranged as video frames and generate disparity and depth maps. The processor may comprise convolutional neural network hardware that may arrange reference images into a tensor, perform logical operations on one of the video frames in a depth direction of the tensor to generate a tensor of feature maps of the video frames, use a convolution to reduce an amount of calculations performed in the depth direction of the tensor of feature maps, perform convolution filtering on the tensor of the feature maps, determine an index map location, and search lookup data based on the index map location to determine the disparity and depth maps.

Accelerating speckle image block matching using convolution techniques

An apparatus comprising an interface, a structured light projector and a processor. The interface may receive pixel data. The structured light projector may generate a structured light pattern. The processor may process the pixel data arranged as video frames, perform operations using a convolutional neural network to determine a binarization result and an offset value and generate disparity and depth maps in response to the video frames, the structured light pattern, the binarization result, the offset value and a removal of error points. The convolutional neural network may perform a partial block summation to generate a convolution result, compare the convolution result to a speckle value to determine the offset value, generate an adaptive result in response to performing a convolution operation, compare the video frames to the adaptive result to generate the binarization result for the video frames, and remove the error points from the binarization result.

Adding an adaptive offset term using convolution techniques to a local adaptive binarization expression

An intelligent automotive headlamp module with combined functions comprises a three-color laser light source array (), a beam combination lens assembly () used for converging three-color laser light, an electric-controlled deflecting reflector unit () arranged in the light emergence direction of the laser beam combination lens assembly (), and a transmission-type fluorescent material (), wherein the reflecting surfaces (A-, B-) of the reflector unit rotate around the axes in a reciprocating mode at a high speed, and thus a reciprocating scanning segment is formed; the transmission-type fluorescent material () converts blue single-wavelength light irradiating the front side of the transmission-type fluorescent material () into white complex-wavelength light, and the white complex-wavelength light is output from the back side of the transmission-type fluorescent material ().

Growing community of inventors

Shanghai, China

Liangliang Wang