Detection of Occluded Road Signs on Autonomous Driving Vehicles
Jingda Guo, Xianwei Cheng, Qi Chen, Qing Yang · 2019
Autonomous driving vehicle relies heavily on its perception system to sense surrounding environments and make driving decisions. One important task on autonomous driving vehicles is to correctly recognize different traffic signs. However, the traffic signs in the wild can be in various conditions, e.g., occluded, deteriorated, or vandalized, and not all of them are recognizable. In this work, we propose a novel system that leverages the perception system on autonomous vehicle to identify occluded road signs in real time. Based on transfer learning, we propose the occluded sign classification network (OSCN) that is able to achieve a precision of 96.34% on a real-world dataset.