Mask-Guided Attention Network for Occluded Pedestrian Detection
Citations Over TimeTop 1% of 2019 papers
Abstract
Pedestrian detection relying on deep convolution neural networks has made significant progress. Though promising results have been achieved on standard pedestrians, the performance on heavily occluded pedestrians remains far from satisfactory. The main culprits are intra-class occlusions involving other pedestrians and inter-class occlusions caused by other objects, such as cars and bicycles. These results in a multitude of occlusion patterns. We propose an approach for occluded pedestrian detection with the following contributions. First, we introduce a novel mask-guided attention network that fits naturally into popular pedestrian detection pipelines. Our attention network emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features. Second, we empirically demonstrate that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts. Experiments are performed on CityPersons and Caltech datasets. Our approach sets a new state-of-the-art on both datasets. Our approach obtains an absolute gain of 9.5% in log-average miss rate, compared to the best reported results [32] on the heavily occluded HO pedestrian set of CityPersons test set. Further, on the HO pedestrian set of Caltech dataset, our method achieves an absolute gain of 5.0% in log-average miss rate, compared to the best reported results [13]. Code and models are available at: https://github.com/Leotju/MGAN.
Related Papers
- → Improvement of Pedestrian Crossing Safety on Urban Roads(2010)8 cited
- → Pedestrian Conflicts, Pedestrian Comfort Levels, and Current Pedestrian Levels of Service(2013)2 cited
- → Review on Microscopic Pedestrian Simulation Model(2016)53 cited
- THE POSITION OF THE PEDESTRIAN ON CROSSINGS LOCATIONS. MAIN REPORT AND APPENDICES REPORT(1996)
- Analysis on Influence of Design of Pedestrian Bridge to Pedestrian Traffic(2013)