IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware
To at the low robustness of the existing model for occluded object detection, an occluded object detection algorithm based on fuzzy sample anchor box IoU Matching degree Deviation Aware(IoU_MDA)is proposed. Firstly, fuzzy samples are defined based on Anchor-based, which reflects the degree of object...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10463038/ |
| _version_ | 1827290002342543360 |
|---|---|
| author | Yuling Chen Xiaoxia Li Zhenxiang He Hang Chen Jinwei Chen Bin Wu |
| author_facet | Yuling Chen Xiaoxia Li Zhenxiang He Hang Chen Jinwei Chen Bin Wu |
| author_sort | Yuling Chen |
| collection | DOAJ |
| description | To at the low robustness of the existing model for occluded object detection, an occluded object detection algorithm based on fuzzy sample anchor box IoU Matching degree Deviation Aware(IoU_MDA)is proposed. Firstly, fuzzy samples are defined based on Anchor-based, which reflects the degree of object occlusion. Secondly, IoU_MDA is proposed to quantify the degree of interference experienced by fuzzy samples. Then, IoU_MDA_Loss is constructed based on IoU_MDA, combined with IoU and the balance parameter <inline-formula> <tex-math notation="LaTeX">$\Phi$ </tex-math></inline-formula>. To address class imbalance issues and enhance model generality, intra-class and inter-class fuzzy weights, and fuzzy sample focusing parameters are designed on the basis of the initial IoU_MDA_Loss. An occluded object training scheme is designed based on IoU perception, and non-fuzzy sample weight balancing parameters are constructed. Finally, IoU_MDA_Loss is merged with Focal Loss to obtain IoU_MDA_Focal Loss, simultaneously enhancing the detection performance of fuzzy samples and difficult-to-distinguish samples. The experimental results on the WiderPerson and VOC2007 datasets show that the mAP of IoU_MDA_Loss has increased by 2.04%, 2.36%, and IoU_MDA_Focal Loss has increased by 1.82%, 2.65%, respectively, compared to the baseline model. The detection performance surpasses current mainstream algorithms. |
| first_indexed | 2024-04-24T12:00:41Z |
| format | Article |
| id | doaj.art-41b7bf74f91d43c5bf792a4beeba94c7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T12:00:41Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-41b7bf74f91d43c5bf792a4beeba94c72024-04-08T23:00:45ZengIEEEIEEE Access2169-35362024-01-0112476304764510.1109/ACCESS.2024.337510910463038IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation AwareYuling Chen0https://orcid.org/0000-0003-0628-1651Xiaoxia Li1Zhenxiang He2https://orcid.org/0009-0007-6458-6820Hang Chen3Jinwei Chen4Bin Wu5School of Information Engineering, Southwest University of Science and Technology, Mianyang, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang, ChinaMianyang Teachers’ College, Mianyang, ChinaSchool of Information Engineering, Southwest University of Science and Technology, Mianyang, ChinaTo at the low robustness of the existing model for occluded object detection, an occluded object detection algorithm based on fuzzy sample anchor box IoU Matching degree Deviation Aware(IoU_MDA)is proposed. Firstly, fuzzy samples are defined based on Anchor-based, which reflects the degree of object occlusion. Secondly, IoU_MDA is proposed to quantify the degree of interference experienced by fuzzy samples. Then, IoU_MDA_Loss is constructed based on IoU_MDA, combined with IoU and the balance parameter <inline-formula> <tex-math notation="LaTeX">$\Phi$ </tex-math></inline-formula>. To address class imbalance issues and enhance model generality, intra-class and inter-class fuzzy weights, and fuzzy sample focusing parameters are designed on the basis of the initial IoU_MDA_Loss. An occluded object training scheme is designed based on IoU perception, and non-fuzzy sample weight balancing parameters are constructed. Finally, IoU_MDA_Loss is merged with Focal Loss to obtain IoU_MDA_Focal Loss, simultaneously enhancing the detection performance of fuzzy samples and difficult-to-distinguish samples. The experimental results on the WiderPerson and VOC2007 datasets show that the mAP of IoU_MDA_Loss has increased by 2.04%, 2.36%, and IoU_MDA_Focal Loss has increased by 1.82%, 2.65%, respectively, compared to the baseline model. The detection performance surpasses current mainstream algorithms.https://ieeexplore.ieee.org/document/10463038/Object detectionIoU matching degree deviation aware (IoU_MDA)fuzzy sampleoccluded objects |
| spellingShingle | Yuling Chen Xiaoxia Li Zhenxiang He Hang Chen Jinwei Chen Bin Wu IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware IEEE Access Object detection IoU matching degree deviation aware (IoU_MDA) fuzzy sample occluded objects |
| title | IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware |
| title_full | IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware |
| title_fullStr | IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware |
| title_full_unstemmed | IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware |
| title_short | IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy Sample Anchor Box IoU Matching Degree Deviation Aware |
| title_sort | iou mda an occluded object detection algorithm based on fuzzy sample anchor box iou matching degree deviation aware |
| topic | Object detection IoU matching degree deviation aware (IoU_MDA) fuzzy sample occluded objects |
| url | https://ieeexplore.ieee.org/document/10463038/ |
| work_keys_str_mv | AT yulingchen ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware AT xiaoxiali ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware AT zhenxianghe ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware AT hangchen ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware AT jinweichen ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware AT binwu ioumdaanoccludedobjectdetectionalgorithmbasedonfuzzysampleanchorboxioumatchingdegreedeviationaware |