Applying Surface Normal Information in Drivable Area and Road Anomaly Detection for Ground Mobile Robots
This work addresses the need for more accurate and efficient detection for ground mobile robots, representing an incremental improvement over existing methods.
The paper tackles the problem of improving drivable area and road anomaly detection for ground mobile robots by developing a Normal Inference Module (NIM) that generates surface normal information from depth images, resulting in enhanced segmentation performance when integrated into existing CNNs, with NIM-RTFNet achieving 8th place on the KITTI road benchmark and real-time inference.
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.