Journal
SIGNAL PROCESSING-IMAGE COMMUNICATION
Volume 95, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.image.2021.116285
Keywords
Stereo matching; Cost volume; Multiscale features; Dense convolutional neural network
Categories
Funding
- National Key Research and Development Program of China [2020YFC2003800]
- National Natu-ral Science Foundation of China [61866026, 61772255, 61866025]
- Advantage Subject Team Project of Jiangxi Province [20165BCB19007, 20152BCB24004]
- Outstanding Young Talents Program of Jiangxi Province [20192BCB23011]
- National Natural Science Foundation of Jiangxi Province [20202ACB214007]
- Aero-nautical Science Foundation of China [2018ZC56008]
- China Postdoctoral Science Foundation [2019M650894]
Ask authors/readers for more resources
The Dense-CNN stereo matching method proposed in this paper utilizes a novel densely connected network with multiscale convolutional layers and a new loss-function strategy to address image feature loss issues. Experimental results show superior performance in computational accuracy and robustness compared to state-of-the-art approaches.
In spite of the fact that convolutional neural network-based stereo matching models have shown good performance in both accuracy and robustness, the issue of image feature loss in regions of texture-less, complex scenes and occlusions remains. In this paper, we present a dense convolutional neural network-based stereo matching method with multiscale feature connection, named Dense-CNN. First, we construct a novel densely connected network with multiscale convolutional layers to extract rich image features, in which the merged multiscale features with context information are utilized to estimate the cost volume for stereo matching. Second, we plan a novel loss-function strategy to learn the network parameters more reasonably, which can develop the performance of the proposed Dense-CNN model on disparity computation. Finally, we run our Dense-CNN model on the Middlebury and KITTI databases to conduct a comprehensive comparison with several state-of-the-art approaches. The experimental results demonstrate that the proposed method achieved superior performance on computational accuracy and robustness of disparity estimation, especially achieving the significant benefit of feature preservation in ill-posed regions.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available