A self-improving pyramid stereo network for intelligent transport systems

Researchers propose self-improving pyramid stereo network for intelligent transport systems
Structure of the proposed model, SPP represents for Spatial Pyramid Pooling. Credit: SIAT

In autonomous driving, stereo vision-based depth estimation technology can help to accurately estimate the distance of obstacles, which is crucial for correct path planning of the vehicle.

The stereo depth estimation problem has been formulated into a with . However, these models 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 labeling the true ground depth for real circumstances, training data for the system is limited.

A research team led by Dr. Zhang Qieshi from the Shenzhen Institutes of Advanced Technology (SIAT) of the Chinese Academy of Sciences has proposed a new technical solution to address the current depth estimation for autonomous driving.

The researchers proposed a self-improving pyramid stereo network that can get a direct regression disparity without complicated post-processing and is robust in ill-posed area.

Moreover, by , 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, it has the self-improving ability to new scenes, which could quickly adjust in time according to test data and improve the accuracy of prediction.

Experiments and benchmark testing have demonstrated that the proposed network could achieve depth with an error rate of 8.3%.

The study was published in IET Intelligent Transport Systems.


Explore further

New image recognition method proposed based on large-scale dataset

More information: Yanling Tian et al. Depth estimation for advancing intelligent transport systems based on self-improving pyramid stereo network, IET Intelligent Transport Systems (2020). DOI: 10.1049/iet-its.2019.0462
Citation: A self-improving pyramid stereo network for intelligent transport systems (2020, May 22) retrieved 3 December 2020 from https://techxplore.com/news/2020-05-self-improving-pyramid-stereo-network-intelligent.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
12 shares

Feedback to editors

User comments