Hilbert stereo reconstruction algorithm based on depth feature and stereo matching

Abstract

This paper proposes a Hilbert stereo reconstruction algorithm based on depth feature and stereo matching to solve the problem of occlusive region matching errors, namely, the Hilbert stereo network. The traditional stereo network pays more attention to disparity itself, leading to the inaccuracy of disparity estimation. Our design network studies the effective disparity matching and refinement through reconstruction representation of Hilbert’s disparity coefficient. Since the Hilbert coefficient is not affected by the occlusion and texture in the image, stereo disparity matching can conducted effectively. Our network includes three sub-modules, namely, depth feature representation, Hilbert cost volume fusion, and Hilbert refinement reconstruction. Separately, texture features of different depth levels of the image were extracted through Hilbert filtering operation. Next, stereoscopic disparity fusion was performed, and then Hilbert designed to refine the difference regression stereo matching solution was used. Based on the end-to-end design, the structure is refined by combining the depth feature extraction module and Hilbert coefficient disparity. Finally, the Hilbert stereo matching algorithm achieves excellent performance on standard big data set and is compared with other advanced stereo networks. Experiments show that our network has high accuracy and high performance.

Use of Digital Twins‐Based Intelligent Navigation Visual Sensing Technology in Environmental Art Design of Scenic Spots

“…According to the relevant working principle of ODVS and the relevant definition of epipolar geometry, the radiation whose origin is the center point of the panoramic image can correspond to the epipolar line of the stereo image pair obtained by ODVS. rough the above methods, it can become a constraint condition for stereo matching [4]. e active stereo vision can simplify the epipolar matching step in passive panoramic stereo vision.…”

Research on binocular stereo matching algorithm based on dynamic tilt window

“…Phuc et al [8] proposed a matching method based on absolute difference and rank sum census transformation, which solved the problem of imperfect correction for large-resolution images. Kong et al [9] performed disparity matching and refinement by reconstructing the Hilbert disparity coefficient, which effectively solved the influence of occlusion and texture in the image. Yao et al [10] combined the MeshStereo (MS) and Cross-Scale Cost Filtering (CSCF) models, which significantly improved the running speed, but did not improve much in reducing the false matching rate.…”