A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian
Accurate and efficient real-time pedestrian detection in hospitals is crucial for improving safety operations and effective management. However, this task poses significant challenges due to complex scenes, dense crowds, and pedestrian occlusions. This paper proposes a multi-branch anchor-free algor...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10781411/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533410987737088 |
|---|---|
| author | Keqiang Li Yifan Li Yiyi Wang Haining Yu Huan Zhang |
| author_facet | Keqiang Li Yifan Li Yiyi Wang Haining Yu Huan Zhang |
| author_sort | Keqiang Li |
| collection | DOAJ |
| description | Accurate and efficient real-time pedestrian detection in hospitals is crucial for improving safety operations and effective management. However, this task poses significant challenges due to complex scenes, dense crowds, and pedestrian occlusions. This paper proposes a multi-branch anchor-free algorithm for hospital pedestrian detection. Firstly, a multi-branch network structure is added after the backbone network of the model to adapt to multiple key local features of pedestrian targets. Subsequently, a distance loss function between key regions is designed to guide the branch networks in learning the differential detection positions of pedestrians locally. Furthermore, using ResNet34 as the baseline feature generation network, four upsampling blocks are appended at the end to form a hourglass structure, enhancing the branch network’s understanding of spatial information in pedestrian local features. Lastly, a local feature selection network is proposed to adaptively suppress non-optimal values from the multi-branch outputs, eliminating redundant feature boxes during prediction. Experimental results demonstrate that the method achieved an AP of 89.2% on the CrowdHuman dataset, indicating high detection accuracy. Additionally, on the HospitalPerson dataset for pedestrian detection in hospitals, the F1 score, Recall, and AP reached 0.9, 94.59%, and 85.42% respectively, showcasing the superior performance of the proposed method in hospital pedestrian detection, particularly in crowded and heavily occluded scenarios. |
| format | Article |
| id | doaj-art-63ba0e8b1318416eb8543e9f03277162 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-63ba0e8b1318416eb8543e9f032771622025-01-16T00:02:06ZengIEEEIEEE Access2169-35362024-01-011218482718484010.1109/ACCESS.2024.351266610781411A Multi-Branch Anchor-Free Detection Algorithm for Hospital PedestrianKeqiang Li0https://orcid.org/0009-0009-7896-7581Yifan Li1Yiyi Wang2Haining Yu3https://orcid.org/0009-0007-5890-479XHuan Zhang4https://orcid.org/0000-0002-0221-2766Shandong Cancer Hospital, Shandong First Medical University, Jinan, ChinaShandong Cancer Hospital, Shandong First Medical University, Jinan, ChinaSchool of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, ChinaShandong Cancer Hospital, Shandong First Medical University, Jinan, ChinaShandong Cancer Hospital, Shandong First Medical University, Jinan, ChinaAccurate and efficient real-time pedestrian detection in hospitals is crucial for improving safety operations and effective management. However, this task poses significant challenges due to complex scenes, dense crowds, and pedestrian occlusions. This paper proposes a multi-branch anchor-free algorithm for hospital pedestrian detection. Firstly, a multi-branch network structure is added after the backbone network of the model to adapt to multiple key local features of pedestrian targets. Subsequently, a distance loss function between key regions is designed to guide the branch networks in learning the differential detection positions of pedestrians locally. Furthermore, using ResNet34 as the baseline feature generation network, four upsampling blocks are appended at the end to form a hourglass structure, enhancing the branch network’s understanding of spatial information in pedestrian local features. Lastly, a local feature selection network is proposed to adaptively suppress non-optimal values from the multi-branch outputs, eliminating redundant feature boxes during prediction. Experimental results demonstrate that the method achieved an AP of 89.2% on the CrowdHuman dataset, indicating high detection accuracy. Additionally, on the HospitalPerson dataset for pedestrian detection in hospitals, the F1 score, Recall, and AP reached 0.9, 94.59%, and 85.42% respectively, showcasing the superior performance of the proposed method in hospital pedestrian detection, particularly in crowded and heavily occluded scenarios.https://ieeexplore.ieee.org/document/10781411/Hospitalpedestrian detectionanchor freemulti-branchcrowds detection |
| spellingShingle | Keqiang Li Yifan Li Yiyi Wang Haining Yu Huan Zhang A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian IEEE Access Hospital pedestrian detection anchor free multi-branch crowds detection |
| title | A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian |
| title_full | A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian |
| title_fullStr | A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian |
| title_full_unstemmed | A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian |
| title_short | A Multi-Branch Anchor-Free Detection Algorithm for Hospital Pedestrian |
| title_sort | multi branch anchor free detection algorithm for hospital pedestrian |
| topic | Hospital pedestrian detection anchor free multi-branch crowds detection |
| url | https://ieeexplore.ieee.org/document/10781411/ |
| work_keys_str_mv | AT keqiangli amultibranchanchorfreedetectionalgorithmforhospitalpedestrian AT yifanli amultibranchanchorfreedetectionalgorithmforhospitalpedestrian AT yiyiwang amultibranchanchorfreedetectionalgorithmforhospitalpedestrian AT hainingyu amultibranchanchorfreedetectionalgorithmforhospitalpedestrian AT huanzhang amultibranchanchorfreedetectionalgorithmforhospitalpedestrian AT keqiangli multibranchanchorfreedetectionalgorithmforhospitalpedestrian AT yifanli multibranchanchorfreedetectionalgorithmforhospitalpedestrian AT yiyiwang multibranchanchorfreedetectionalgorithmforhospitalpedestrian AT hainingyu multibranchanchorfreedetectionalgorithmforhospitalpedestrian AT huanzhang multibranchanchorfreedetectionalgorithmforhospitalpedestrian |