Viktor V. Varlashin
Received July 20, 2022
The issues of using a pair of orthogonally-divergent cameras with fisheye lenses in computer vision systems are considered. An algorithm has been developed for processing frames received from cameras to obtain a pair of rectified images. For a virtual model, the accuracy of constructing a scene depth map in the area of intersection of the cameras' fields of view was estimated.
Computer vision, stereo, fisheye lens, depth map, point cloud.
The reported study was funded by RFBR, project number 20-38-90094 «Study of methods for estimating distances to environmental objects using a surround-view system of mobile robots».
Varlashin, V.V., 2022. A technique for constructing depth map from images of orthogonally-divergent fisheye stereo. Robotics and Technical Cybernetics, 10(3), pp.236-240.