ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios
Abnormal behavior of crew members is an important cause of frequent ship safety accidents. The existing abnormal crew recognition algorithms are affected by complex ship environments and have low performance in real and open shipborne environments. This paper proposes an abnormal crew detection netw...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/22/7288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850147104214745088 |
|---|---|
| author | Zhengbao Li Heng Zhang Ding Gao Zewei Wu Zheng Zhang Libin Du |
| author_facet | Zhengbao Li Heng Zhang Ding Gao Zewei Wu Zheng Zhang Libin Du |
| author_sort | Zhengbao Li |
| collection | DOAJ |
| description | Abnormal behavior of crew members is an important cause of frequent ship safety accidents. The existing abnormal crew recognition algorithms are affected by complex ship environments and have low performance in real and open shipborne environments. This paper proposes an abnormal crew detection network for complex ship scenarios (ACD-Net), which uses a two-stage algorithm to detect and identify abnormal crew members in real-time. An improved YOLOv5s model based on a transformer and CBAM mechanism (YOLO-TRCA) is proposed with a C3-TransformerBlock module to enhance the feature extraction ability of crew members in complex scenes. The CBAM attention mechanism is introduced to reduce the interference of background features and improve the accuracy of real-time detection of crew abnormal behavior. The crew identification algorithm (CFA) tracks and detects abnormal crew members’ faces in real-time in an open environment (CenterFace), continuously conducts face quality assessment (Filter), and selects high-quality facial images for identity recognition (ArcFace). The CFA effectively reduces system computational overhead and improves the success rate of identity recognition. Experimental results indicate that ACD-Net achieves 92.3% accuracy in detecting abnormal behavior and a 69.6% matching rate for identity recognition, with a processing time of under 39.5 ms per frame at a 1080P resolution. |
| format | Article |
| id | doaj-art-9396d2370f3e41af930453da6a24b0ea |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-9396d2370f3e41af930453da6a24b0ea2025-08-20T02:27:39ZengMDPI AGSensors1424-82202024-11-012422728810.3390/s24227288ACD-Net: An Abnormal Crew Detection Network for Complex Ship ScenariosZhengbao Li0Heng Zhang1Ding Gao2Zewei Wu3Zheng Zhang4Libin Du5College of Ocean Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwan Port Road, Huangdao District, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwan Port Road, Huangdao District, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwan Port Road, Huangdao District, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwan Port Road, Huangdao District, Qingdao 266590, ChinaYellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, 106 Nanjing Road, Qingdao 266071, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, No. 579 Qianwan Port Road, Huangdao District, Qingdao 266590, ChinaAbnormal behavior of crew members is an important cause of frequent ship safety accidents. The existing abnormal crew recognition algorithms are affected by complex ship environments and have low performance in real and open shipborne environments. This paper proposes an abnormal crew detection network for complex ship scenarios (ACD-Net), which uses a two-stage algorithm to detect and identify abnormal crew members in real-time. An improved YOLOv5s model based on a transformer and CBAM mechanism (YOLO-TRCA) is proposed with a C3-TransformerBlock module to enhance the feature extraction ability of crew members in complex scenes. The CBAM attention mechanism is introduced to reduce the interference of background features and improve the accuracy of real-time detection of crew abnormal behavior. The crew identification algorithm (CFA) tracks and detects abnormal crew members’ faces in real-time in an open environment (CenterFace), continuously conducts face quality assessment (Filter), and selects high-quality facial images for identity recognition (ArcFace). The CFA effectively reduces system computational overhead and improves the success rate of identity recognition. Experimental results indicate that ACD-Net achieves 92.3% accuracy in detecting abnormal behavior and a 69.6% matching rate for identity recognition, with a processing time of under 39.5 ms per frame at a 1080P resolution.https://www.mdpi.com/1424-8220/24/22/7288abnormal behavior detectionidentity recognitionYOLOv5sfacial imagesface quality assessment |
| spellingShingle | Zhengbao Li Heng Zhang Ding Gao Zewei Wu Zheng Zhang Libin Du ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios Sensors abnormal behavior detection identity recognition YOLOv5s facial images face quality assessment |
| title | ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios |
| title_full | ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios |
| title_fullStr | ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios |
| title_full_unstemmed | ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios |
| title_short | ACD-Net: An Abnormal Crew Detection Network for Complex Ship Scenarios |
| title_sort | acd net an abnormal crew detection network for complex ship scenarios |
| topic | abnormal behavior detection identity recognition YOLOv5s facial images face quality assessment |
| url | https://www.mdpi.com/1424-8220/24/22/7288 |
| work_keys_str_mv | AT zhengbaoli acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios AT hengzhang acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios AT dinggao acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios AT zeweiwu acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios AT zhengzhang acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios AT libindu acdnetanabnormalcrewdetectionnetworkforcomplexshipscenarios |