Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
This work provides an incremental improvement in data augmentation for collision-free space detection, benefiting autonomous vehicle perception systems.
This paper addresses the challenge of limited labeled training data for collision-free space detection in autonomous vehicles by proposing a data augmentation technique. By leveraging homography matrices to transform multi-view images into a reference view, the method effectively generates additional training data, leading to improved performance across six state-of-the-art DCNNs and achieving the best results on the KITTI road benchmark for stereo vision-based detection.
Collision-free space detection is a critical component of autonomous vehicle perception. The state-of-the-art algorithms are typically based on supervised learning. The performance of such approaches is always dependent on the quality and amount of labeled training data. Additionally, it remains an open challenge to train deep convolutional neural networks (DCNNs) using only a small quantity of training samples. Therefore, this paper mainly explores an effective training data augmentation approach that can be employed to improve the overall DCNN performance, when additional images captured from different views are available. Due to the fact that the pixels of the collision-free space (generally regarded as a planar surface) between two images captured from different views can be associated by a homography matrix, the scenario of the target image can be transformed into the reference view. This provides a simple but effective way of generating training data from additional multi-view images. Extensive experimental results, conducted with six state-of-the-art semantic segmentation DCNNs on three datasets, demonstrate the effectiveness of our proposed training data augmentation algorithm for enhancing collision-free space detection performance. When validated on the KITTI road benchmark, our approach provides the best results for stereo vision-based collision-free space detection.