Perspective Aware Road Obstacle Detection

TL;DR

This paper introduces a perspective-aware approach to road obstacle detection that uses a scale map to improve training data generation and detection accuracy, outperforming existing methods.

Contribution

It proposes a novel perspective map encoding apparent obstacle size, enhancing detection through synthetic data augmentation and network guidance.

Findings

Significant performance boost on standard benchmarks

Outperforms state-of-the-art obstacle detection methods

Effective use of perspective information in detection pipeline

Abstract

While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. In this paper, we account for this by computing a scale map encoding the apparent size of a hypothetical object at every image location. We then leverage this perspective map to (i) generate training data by injecting onto the road synthetic objects whose size corresponds to the perspective foreshortening; and (ii) incorporate perspective information in the decoding part of the detection network to guide the obstacle detector. Our results on standard benchmarks show that, together, these two strategies significantly boost the obstacle detection performance, allowing our approach to consistently outperform state-of-the-art methods in terms of instance-level obstacle detection.