A deep learning based detection algorithm for anomalous behavior and anomalous item on buses
Abstract This paper proposes a new strategy for analysing and detecting abnormal passenger behavior and abnormal objects on buses. First, a library of abnormal passenger behaviors and objects on buses is established. Then, a new mask detection and abnormal object detection and analysis (MD-AODA) alg...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85962-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594764434767872 |
|---|---|
| author | Shida Liu Yu Bi Qingyi Li Ye Ren Honghai Ji Li Wang |
| author_facet | Shida Liu Yu Bi Qingyi Li Ye Ren Honghai Ji Li Wang |
| author_sort | Shida Liu |
| collection | DOAJ |
| description | Abstract This paper proposes a new strategy for analysing and detecting abnormal passenger behavior and abnormal objects on buses. First, a library of abnormal passenger behaviors and objects on buses is established. Then, a new mask detection and abnormal object detection and analysis (MD-AODA) algorithm is proposed. The algorithm is based on the deep learning YOLOv5 (You Only Look Once) algorithm with improvements. For onboard face mask detection, a strategy based on the combination of onboard face detection and target tracking is used. To detect abnormal objects in the vehicle, a geometric scale conversion-based approach for recognizing large-size ab-normal objects is adopted. To apply the algorithm effectively to real bus data, an embedded video analysis system is designed. The system incorporates the proposed method, which results in improved accuracy and timeliness in detecting anomalies compared to existing approaches. The algorithm’s effectiveness and applicability is verified through comprehensive experiments using actual video bus data. The experimental results affirm the validity and practicality of the pro-posed algorithm. |
| format | Article |
| id | doaj-art-619e68eb77454330918ce24953206516 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-619e68eb77454330918ce249532065162025-01-19T12:21:28ZengNature PortfolioScientific Reports2045-23222025-01-0115111610.1038/s41598-025-85962-8A deep learning based detection algorithm for anomalous behavior and anomalous item on busesShida Liu0Yu Bi1Qingyi Li2Ye Ren3Honghai Ji4Li Wang5School of Electrical and Control Engineering, North China University of TechnologySchool of Electrical and Control Engineering, North China University of TechnologySchool of Electrical and Control Engineering, North China University of TechnologySchool of Electrical and Control Engineering, North China University of TechnologySchool of Electrical and Control Engineering, North China University of TechnologySchool of Electrical and Control Engineering, North China University of TechnologyAbstract This paper proposes a new strategy for analysing and detecting abnormal passenger behavior and abnormal objects on buses. First, a library of abnormal passenger behaviors and objects on buses is established. Then, a new mask detection and abnormal object detection and analysis (MD-AODA) algorithm is proposed. The algorithm is based on the deep learning YOLOv5 (You Only Look Once) algorithm with improvements. For onboard face mask detection, a strategy based on the combination of onboard face detection and target tracking is used. To detect abnormal objects in the vehicle, a geometric scale conversion-based approach for recognizing large-size ab-normal objects is adopted. To apply the algorithm effectively to real bus data, an embedded video analysis system is designed. The system incorporates the proposed method, which results in improved accuracy and timeliness in detecting anomalies compared to existing approaches. The algorithm’s effectiveness and applicability is verified through comprehensive experiments using actual video bus data. The experimental results affirm the validity and practicality of the pro-posed algorithm.https://doi.org/10.1038/s41598-025-85962-8Abnormal behavior analysisAbnormal object recognitionTarget detection |
| spellingShingle | Shida Liu Yu Bi Qingyi Li Ye Ren Honghai Ji Li Wang A deep learning based detection algorithm for anomalous behavior and anomalous item on buses Scientific Reports Abnormal behavior analysis Abnormal object recognition Target detection |
| title | A deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| title_full | A deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| title_fullStr | A deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| title_full_unstemmed | A deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| title_short | A deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| title_sort | deep learning based detection algorithm for anomalous behavior and anomalous item on buses |
| topic | Abnormal behavior analysis Abnormal object recognition Target detection |
| url | https://doi.org/10.1038/s41598-025-85962-8 |
| work_keys_str_mv | AT shidaliu adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT yubi adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT qingyili adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT yeren adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT honghaiji adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT liwang adeeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT shidaliu deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT yubi deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT qingyili deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT yeren deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT honghaiji deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses AT liwang deeplearningbaseddetectionalgorithmforanomalousbehaviorandanomalousitemonbuses |