# Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation

arXiv: https://arxiv.org/abs/2012.07890 · HTML: https://mlsanity.com/paper/2012.07890/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching](https://mlsanity.com/paper/2103.07094/) (2021)
- [Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation](https://mlsanity.com/paper/2104.12861/) (2021)
- [Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms](https://mlsanity.com/paper/2103.02433/) (2021)
- [SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection](https://mlsanity.com/paper/2107.14599/) (2021)
- [Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms](https://mlsanity.com/paper/2204.13590/) (2022)
- [End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving](https://mlsanity.com/paper/2104.08862/) (2021)
- [SNE-RoadSegV2: Advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection](https://mlsanity.com/paper/2402.18918/) (2024)
- [ROD: RGB-Only Fast and Efficient Off-road Freespace Detection](https://mlsanity.com/paper/2508.08697/) (2025)
- [Maximum and Leaky Maximum Propagation](https://mlsanity.com/paper/2105.10277/) (2021)
- [SCV-Stereo: Learning Stereo Matching from a Sparse Cost Volume](https://mlsanity.com/paper/2107.08187/) (2021)
- [Exploiting Low-level Representations for Ultra-Fast Road Segmentation](https://mlsanity.com/paper/2402.02430/) (2024)
- [SkipcrossNets: Adaptive Skip-cross Fusion for Road Detection](https://mlsanity.com/paper/2308.12863/) (2023)
- [Computer-Aided Road Inspection: Systems and Algorithms](https://mlsanity.com/paper/2203.02355/) (2022)
- [E3CM: Epipolar-Constrained Cascade Correspondence Matching](https://mlsanity.com/paper/2308.16555/) (2023)
- [CodingHomo: Bootstrapping Deep Homography With Video Coding](https://mlsanity.com/paper/2504.12165/) (2025)
- [Co-Teaching: An Ark to Unsupervised Stereo Matching](https://mlsanity.com/paper/2107.08186/) (2021)
- [StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection](https://mlsanity.com/paper/2407.08277/) (2024)
- [Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matching](https://mlsanity.com/paper/2508.01275/) (2025)
- [Structured prototype regularization for synthetic-to-real driving scene parsing](https://mlsanity.com/paper/2603.16083/) (2026)

## Abstract (arXiv)

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.