Occluded Pedestrian Detection Techniques by Deformable Attention-Guided Network (DAGN)
- Title
- Occluded Pedestrian Detection Techniques by Deformable Attention-Guided Network (DAGN)
- Author
- 신현철
- Keywords
- pedestrian detection; feature extraction; computer vision; image processing
- Issue Date
- 2021-06
- Publisher
- MDPI
- Citation
- APPLIED SCIENCES-BASEL, v. 11, no. 13, Article no. 6025, 19pp
- Abstract
- Although many deep-learning-based methods have achieved considerable detection performance for pedestrians with high visibility, their overall performances are still far from satisfactory, especially when heavily occluded instances are included. In this research, we have developed a novel pedestrian detector using a deformable attention-guided network (DAGN). Considering that pedestrians may be deformed with occlusions or under diverse poses, we have designed a deformable convolution with an attention module (DCAM) to sample from non-rigid locations, and obtained the attention feature map by aggregating global context information. Furthermore, the loss function was optimized to get accurate detection bounding boxes, by adopting complete-IoU loss for regression, and the distance IoU-NMS was used to refine the predicted boxes. Finally, a preprocessing technique based on tone mapping was applied to cope with the low visibility cases due to poor illumination. Extensive evaluations were conducted on three popular traffic datasets. Our method could decrease the log-average miss rate (MR−2) by 12.44% and 7.8%, respectively, for the heavy occlusion and overall cases, when compared to the published state-of-the-art results of the Caltech pedestrian dataset. Of the CityPersons and EuroCity Persons datasets, our proposed method outperformed the current best results by about 5% in MR−2 for the heavy occlusion cases.
- URI
- https://www.proquest.com/docview/2549259228?accountid=11283https://repository.hanyang.ac.kr/handle/20.500.11754/166564
- ISSN
- 2076-3417
- DOI
- 10.3390/app11136025
- Appears in Collections:
- COLLEGE OF ENGINEERING SCIENCES[E](공학대학) > ELECTRICAL ENGINEERING(전자공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML