Search

Your search keyword '"Zhang, ZhiMin"' showing total 82 results
Start Over Author "Zhang, ZhiMin" Publisher mdpi ag
82 results on '"Zhang, ZhiMin"'

22. Feed Restriction Alleviates Chronic Thermal Stress-Induced Liver Oxidation and Damages via Reducing Lipid Accumulation in Channel Catfish (Ictalurus punctatus)

Author

Lu, Qisheng, primary, Gong, Yulong, additional, Xi, Longwei, additional, Liu, Yulong, additional, Xu, Wenjie, additional, Liu, Haokun, additional, Jin, Junyan, additional, Zhang, Zhimin, additional, Yang, Yunxia, additional, Zhu, Xiaoming, additional, Xie, Shouqi, additional, and Han, Dong, additional

Published
2022
Full Text
View/download PDF

50. A Semi-Supervised Monocular Stereo Matching Method

Author

Jianzhong Qiao, Shukuan Lin, and Zhang Zhimin

Subjects
semi-supervised learning, 0209 industrial biotechnology, Physics and Astronomy (miscellaneous), Computer science, General Mathematics, Pipeline (computing), KITTI dataset, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, monocular depth estimation, 02 engineering and technology, Semi-supervised learning, 020901 industrial engineering & automation, Depth map, 0202 electrical engineering, electronic engineering, information engineering, Computer Science (miscellaneous), Computer vision, stereo matching, Network model, Ground truth, Monocular, business.industry, lcsh:Mathematics, Process (computing), lcsh:QA1-939, View synthesis, view synthesis, Chemistry (miscellaneous), 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

Supervised monocular depth estimation methods based on learning have shown promising results compared with the traditional methods. However, these methods require a large number of high-quality corresponding ground truth depth data as supervision labels. Due to the limitation of acquisition equipment, it is expensive and impractical to record ground truth depth for different scenes. Compared to supervised methods, the self-supervised monocular depth estimation method without using ground truth depth is a promising research direction, but self-supervised depth estimation from a single image is geometrically ambiguous and suboptimal. In this paper, we propose a novel semi-supervised monocular stereo matching method based on existing approaches to improve the accuracy of depth estimation. This idea is inspired by the experimental results of the paper that the depth estimation accuracy of a stereo pair as input is better than that of a monocular view as input in the same self-supervised network model. Therefore, we decompose the monocular depth estimation problem into two sub-problems, a right view synthesized process followed by a semi-supervised stereo matching process. In order to improve the accuracy of the synthetic right view, we innovate beyond the existing view synthesis method Deep3D by adding a left-right consistency constraint and a smoothness constraint. To reduce the error caused by the reconstructed right view, we propose a semi-supervised stereo matching model that makes use of disparity maps generated by a self-supervised stereo matching model as the supervision cues and joint self-supervised cues to optimize the stereo matching network. In the test, the two networks are able to predict the depth map directly from a single image by pipeline connecting. Both procedures not only obey geometric principles, but also improve estimation accuracy. Test results on the KITTI dataset show that this method is superior to the current mainstream monocular self-supervised depth estimation methods under the same condition.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results