Art

J-GLOBAL ID：202002242941261574   Reference number：20A2181802

Proposal of unsupervised monocular depth estimation using multi-task learning by mutual conversion of depth and depth gradient.

深度と深度勾配の相互変換によるMulti-task learningを活用した教師なし単眼深度推定の提案

Author (2)： TAKAMINE MICHIRU (琉球大) ,  ENDO SATOSHI (琉球大)
Material： 情報科学技術フォーラム講演論文集  (FIT)
Volume： 19th  Issue： 第3分冊  Page： 1-4  Publication year： Aug. 18, 2020 
JST Material Number： L4664A  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： feature extraction ,  unsupervised learning ,  color space ,  *Machine Learning ,  learning model ,  range image ,  supervised learning ,  evaluation function ,  evaluation test ,  image synthesis ,  pixel ,  threshold ,  neural network (biomodel) ,  moving image ,  RGB-Depth ,  evaluation experiment ,  RGB
Semi thesaurus term： *教師なし単眼深度推定 ,  RGB Image ,  multitask learning ,  convolutional neural network

JST classification (2)： Graphic and image processing in general  (JE04010I) ,  Artificial intelligence  (JE08000Z)

Reference (13)：

• Wouter Van Gansbeke, Davy Neven, Bert De Brabandere, and Luc Van Gool. Sparse and noisy LiDAR completion with RGB guidance and uncertainty. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019, 2019.
• Satyarth Praveen. Efficient Depth Estimation Using Sparse Stereo-Vision with Other Perception Techniques, 2019.
• Chaoqiang Zhao. Monocular Depth Estimation Based On Deep Learning: An Overview. 2020.
• Tinghui Zhou, Matthew Brown, Noah Snavely, and David G. Lowe. Unsupervised learning of depth and ego-motion from video. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017.
• Omid Hosseini Jafari, Oliver Groth, Alexander Kirillov, Michael Ying Yang, and Carsten Rother. Analyzing modular CNN architectures for joint depth prediction and semantic segmentation. Proceedings - IEEE International Conference on Robotics and Automation, No. iv, pp. 4620-4627, 2017.

Terms in the title (8)： 深度 ,  勾配 ,  相互変換 ,  活用 ,  教師 ,  単眼 ,  推定 ,  提案