Researchers Propose Self-Improving Pyramid Stereo Network for Intelligent Transport Systems
In autonomous driving, stereo vision-based depth estimation technology can help to estimate the distance of obstacles accurately, which is crucial for correctly planning the path of the vehicle.
Recent work has formulated the stereo depth estimation problem into a deep learning model with convolutional neural networks. However, these methods need a lot of post-processing and do not have strong adaptive capabilities to ill-posed regions or new scenes. In addition, due to the difficulty of the labelling the ground truth depth for real circumstance, training data for the system is limited.
A research team led by Dr. ZHANG Qieshi from Shenzhen Institutes of Advanced Technology (SIAT) of Chinese Academy of Sciences has proposed a new technical solution, addressed the current depth estimation for autonomous driving.
In order to solve the problems of depth estimation, the researchers proposed a self-improving pyramid stereo network which can not only get a direct regression disparity without complicated post-processing but also be robust in ill-posed area.
Moreover, by online learning, the proposed model could not only address the data limitation problem but also save the time spent on training and hardware resources in practice. At the same time, the proposed model has a self-improving ability to new scenes, which could quickly adjust the model according to the test data in time and improve the accuracy of prediction.
Experiments and benchmark testing have demonstrated that the proposed network could achieve depth estimation at the error rates of 8.3 % with 0.5s on Scene Flow dataset and error in all ground truth of 2.01%.
The study was published in IET Intelligent Transport Systems.
Structure of the proposed model, SPP represents for Spatial Pyramid Pooling (Image by SIAT)