A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring
The recent advancements in artificial intelligence have brought about significant changes in education. In the context of intelligent campus development, target detection technology plays a pivotal role in applications such as campus environment monitoring and the facilitation of classroom behavior...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/23/12806 |
| _version_ | 1827592476619177984 |
|---|---|
| author | Jian Dong Zhange Zhang Siqi He Yu Liang Yuqing Ma Jiaqi Yu Ruiyan Zhang Binbin Li |
| author_facet | Jian Dong Zhange Zhang Siqi He Yu Liang Yuqing Ma Jiaqi Yu Ruiyan Zhang Binbin Li |
| author_sort | Jian Dong |
| collection | DOAJ |
| description | The recent advancements in artificial intelligence have brought about significant changes in education. In the context of intelligent campus development, target detection technology plays a pivotal role in applications such as campus environment monitoring and the facilitation of classroom behavior surveillance. However, traditional object detection methods face challenges in open and dynamic campus scenarios where unexpected objects and behaviors arise. Open-World Object Detection (OWOD) addresses this issue by enabling detectors to gradually learn and recognize unknown objects. Nevertheless, existing OWOD methods introduce two major uncertainties that limit the detection performance: the unknown discovery uncertainty from the manual generation of pseudo-labels for unknown objects and the known discrimination uncertainty from perturbations that unknown training introduces to the known class features. In this paper, we introduce a Parallel OWOD Framework with Uncertainty Mitigation to alleviate the unknown discovery uncertainty and the known discrimination uncertainty within the OWOD task. To address the unknown discovery uncertainty, we propose an objectness-driven discovery module to focus on capturing the generalized objectness shared among various known classes, driving the framework to discover more potential objects that are distinct from the background, including unknown objects. To mitigate the discrimination uncertainty, we decouple the learning processes for known and unknown classes through a parallel structure to reduce the mutual influence at the feature level and design a collaborative open-world classifier to achieve high-performance collaborative detection of both known and unknown classes. Our framework provides educators with a powerful tool for effective campus monitoring and classroom management. Experimental results on standard benchmarks demonstrate the framework’s superior performance compared to state-of-the-art methods, showcasing its transformative potential in intelligent educational environments. |
| first_indexed | 2024-03-09T01:55:07Z |
| format | Article |
| id | doaj.art-bdd8b7ce932f4f56af3739f92e989d4a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T01:55:07Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-bdd8b7ce932f4f56af3739f92e989d4a2023-12-08T15:11:47ZengMDPI AGApplied Sciences2076-34172023-11-0113231280610.3390/app132312806A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus MonitoringJian Dong0Zhange Zhang1Siqi He2Yu Liang3Yuqing Ma4Jiaqi Yu5Ruiyan Zhang6Binbin Li7State Key Lab of Software Development Environment, Beihang University, Beijing 100191, ChinaState Key Lab of Software Development Environment, Beihang University, Beijing 100191, ChinaSchool of Computer Science, Peking University, Beijing 100871, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaState Key Lab of Software Development Environment, Beihang University, Beijing 100191, ChinaBeijing Institute of Control and Electronic Technology, Beijing 100038, ChinaBeijing Institute of Control and Electronic Technology, Beijing 100038, ChinaChina Electronics Standardization Institute, Beijing 100007, ChinaThe recent advancements in artificial intelligence have brought about significant changes in education. In the context of intelligent campus development, target detection technology plays a pivotal role in applications such as campus environment monitoring and the facilitation of classroom behavior surveillance. However, traditional object detection methods face challenges in open and dynamic campus scenarios where unexpected objects and behaviors arise. Open-World Object Detection (OWOD) addresses this issue by enabling detectors to gradually learn and recognize unknown objects. Nevertheless, existing OWOD methods introduce two major uncertainties that limit the detection performance: the unknown discovery uncertainty from the manual generation of pseudo-labels for unknown objects and the known discrimination uncertainty from perturbations that unknown training introduces to the known class features. In this paper, we introduce a Parallel OWOD Framework with Uncertainty Mitigation to alleviate the unknown discovery uncertainty and the known discrimination uncertainty within the OWOD task. To address the unknown discovery uncertainty, we propose an objectness-driven discovery module to focus on capturing the generalized objectness shared among various known classes, driving the framework to discover more potential objects that are distinct from the background, including unknown objects. To mitigate the discrimination uncertainty, we decouple the learning processes for known and unknown classes through a parallel structure to reduce the mutual influence at the feature level and design a collaborative open-world classifier to achieve high-performance collaborative detection of both known and unknown classes. Our framework provides educators with a powerful tool for effective campus monitoring and classroom management. Experimental results on standard benchmarks demonstrate the framework’s superior performance compared to state-of-the-art methods, showcasing its transformative potential in intelligent educational environments.https://www.mdpi.com/2076-3417/13/23/12806intelligent campus monitoringuncertainty mitigationobjectness-driven object discoveryparallel networkopen-world object detectionartificial intelligence |
| spellingShingle | Jian Dong Zhange Zhang Siqi He Yu Liang Yuqing Ma Jiaqi Yu Ruiyan Zhang Binbin Li A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring Applied Sciences intelligent campus monitoring uncertainty mitigation objectness-driven object discovery parallel network open-world object detection artificial intelligence |
| title | A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring |
| title_full | A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring |
| title_fullStr | A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring |
| title_full_unstemmed | A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring |
| title_short | A Parallel Open-World Object Detection Framework with Uncertainty Mitigation for Campus Monitoring |
| title_sort | parallel open world object detection framework with uncertainty mitigation for campus monitoring |
| topic | intelligent campus monitoring uncertainty mitigation objectness-driven object discovery parallel network open-world object detection artificial intelligence |
| url | https://www.mdpi.com/2076-3417/13/23/12806 |
| work_keys_str_mv | AT jiandong aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT zhangezhang aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT siqihe aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT yuliang aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT yuqingma aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT jiaqiyu aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT ruiyanzhang aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT binbinli aparallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT jiandong parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT zhangezhang parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT siqihe parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT yuliang parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT yuqingma parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT jiaqiyu parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT ruiyanzhang parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring AT binbinli parallelopenworldobjectdetectionframeworkwithuncertaintymitigationforcampusmonitoring |