Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots

TL;DR

This paper introduces a novel Normal Inference Module (NIM) that enhances the accuracy of drivable area and road anomaly detection in ground mobile robots by integrating surface normal information into existing CNNs, achieving improved performance and real-time inference.

Contribution

The paper presents a new NIM that accurately generates surface normal data from dense depth images and effectively improves segmentation performance when integrated into CNNs.

Findings

NIM significantly boosts detection accuracy across multiple CNN architectures.

NIM-RTFNet ranks 8th on the KITTI road benchmark.

The method achieves real-time inference speed.

Abstract

The joint detection of drivable areas and road anomalies is a crucial task for ground mobile robots. In recent years, many impressive semantic segmentation networks, which can be used for pixel-level drivable area and road anomaly detection, have been developed. However, the detection accuracy still needs improvement. Therefore, we develop a novel module named the Normal Inference Module (NIM), which can generate surface normal information from dense depth images with high accuracy and efficiency. Our NIM can be deployed in existing convolutional neural networks (CNNs) to refine the segmentation performance. To evaluate the effectiveness and robustness of our NIM, we embed it in twelve state-of-the-art CNNs. The experimental results illustrate that our NIM can greatly improve the performance of the CNNs for drivable area and road anomaly detection. Furthermore, our proposed NIM-RTFNet ranks 8th on the KITTI road benchmark and exhibits a real-time inference speed.