Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
This work addresses a gap in benchmarking for ground mobile robots like robotic wheelchairs, though it is incremental as it builds on existing semantic segmentation approaches.
The authors tackled the lack of a benchmark for drivable area and road anomaly detection in ground mobile robots by creating one and evaluating existing methods, and they proposed a dynamic fusion module that improves performance, with DFM-RTFNet outperforming state-of-the-art methods and achieving competitive results on KITTI.
Joint detection of drivable areas and road anomalies is very important for mobile robots. Recently, many semantic segmentation approaches based on convolutional neural networks (CNNs) have been proposed for pixel-wise drivable area and road anomaly detection. In addition, some benchmark datasets, such as KITTI and Cityscapes, have been widely used. However, the existing benchmarks are mostly designed for self-driving cars. There lacks a benchmark for ground mobile robots, such as robotic wheelchairs. Therefore, in this paper, we first build a drivable area and road anomaly detection benchmark for ground mobile robots, evaluating the existing state-of-the-art single-modal and data-fusion semantic segmentation CNNs using six modalities of visual features. Furthermore, we propose a novel module, referred to as the dynamic fusion module (DFM), which can be easily deployed in existing data-fusion networks to fuse different types of visual features effectively and efficiently. The experimental results show that the transformed disparity image is the most informative visual feature and the proposed DFM-RTFNet outperforms the state-of-the-arts. Additionally, our DFM-RTFNet achieves competitive performance on the KITTI road benchmark. Our benchmark is publicly available at https://sites.google.com/view/gmrb.