Disparity Map Estimation From Stereo Image Pair Using Deep Convolutional Network
| Autor: | Jui-Chiu Chiang, Hung-Ta Chiu, Wen-Nung Lie |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Feature fusion
Computer science business.industry 05 social sciences Feature extraction Pattern recognition 02 engineering and technology Solid modeling Convolutional neural network Feature (computer vision) Stereo image 020204 information systems 0502 economics and business 0202 electrical engineering electronic engineering information engineering 050211 marketing Artificial intelligence business Volume (compression) |
| Zdroj: | ICS |
| DOI: | 10.1109/ics51289.2020.00079 |
| Popis: | This paper presents a method to estimate a disparity map from a stereo image pair using deep convolutional neural network (CNN), which is mainly divided into three parts, including: feature extraction for each individual view, feature fusion, and disparity regression. We first design 2-D CNN networks to extract the feature maps from both the left and right-view images. Then, we combine the two feature maps into one 4- D feature volume by concatenating and packing them across distinct disparity levels. Finally, we use a 3-D CNN network (modified UNet++) to learn the disparity information from the 4-D feature volume. The whole CNN model is trained end-to-end without any post-processing. In other words, we let our model learn a mapping from input to output. Experimental results show that our method outperforms most of state-of-the-art methods on the publicly available datasets FlyingThings3D and KITTI Stereo 2015, demonstrating the feasibility of our algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|