Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor
This work addresses the challenge of detecting pedestrians under occlusion, which is critical for autonomous driving systems, though it appears incremental as it builds on existing IoU methods.
The paper tackled the problem of occluded pedestrian detection by proposing a visible IoU to incorporate visible ratio in sample selection and a box sign predictor to improve localization accuracy, achieving state-of-the-art performance on the CityPersons benchmark.
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not consider the occluded region of the object and leads to improper training samples. To address such issue, a modification called visible IoU is proposed in this paper to explicitly incorporate the visible ratio in selecting samples. Then a newly designed box sign predictor is placed in parallel with box regressor to separately predict the moving direction of training samples. It leads to higher localization accuracy by introducing sign prediction loss during training and sign refining in testing. Following these novelties, we obtain state-of-the-art performance on CityPersons benchmark for occluded pedestrian detection.