@article{oai:kyutech.repo.nii.ac.jp:00007774,
 author = {Zhou,  Shi and Zhu,  Miaomiao and Li,  Zhen and Li,  He and Mizumachi, Mitsunori and 水町, 光徳 and Zhang, Lifeng and 張, 力峰},
 issue = {3},
 journal = {Artificial Life and Robotics},
 month = {May},
 note = {Depth estimation is one of the basic and important tasks in 3D vision. Recently, many works have been done in self-supervised depth estimation based on geometric consistency between frames. However, these research works still have difficulties in ill-posed areas, such as occlusion areas and texture-less areas. This work proposed a novel self-supervised monocular depth estimation method based on occlusion mask and edge awareness to overcome these difficulties. The occlusion mask divides the image into two classes, making the training of the network more reasonable. The edge awareness loss function is designed based on the edge obtained by the traditional method, so that the method has strong robustness to various lighting conditions. Furthermore, we evaluated the proposed method on the KITTI datasets. The occlusion mask and edge awareness are both beneficial to find corresponding points in ill-posed areas.},
 pages = {354--359},
 title = {Self-supervised monocular depth estimation with occlusion mask and edge awareness},
 volume = {26},
 year = {2021},
 yomi = {ミズマチ, ミツノリ and チョウ, リキホウ}
}