A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments
Target detection in resource-constrained environments faces multiple challenges such as the use of camouflage, diverse target sizes, and harsh environmental conditions. Moreover, the need for solutions suitable for edge computing environments, which have limited computational resources, adds complex...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/12/3800 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850164454478577664 |
|---|---|
| author | Kaipeng Wang Guanglin He Xinmin Li |
| author_facet | Kaipeng Wang Guanglin He Xinmin Li |
| author_sort | Kaipeng Wang |
| collection | DOAJ |
| description | Target detection in resource-constrained environments faces multiple challenges such as the use of camouflage, diverse target sizes, and harsh environmental conditions. Moreover, the need for solutions suitable for edge computing environments, which have limited computational resources, adds complexity to the task. To meet these challenges, we propose MSCDNet (Multi-Scale Context Detail Network), an innovative and lightweight architecture designed specifically for efficient target detection in such environments. MSCDNet integrates three key components: the Multi-Scale Fusion Module, which improves the representation of features at various target scales; the Context Merge Module, which enables adaptive feature integration across scales to handle a wide range of target conditions; and the Detail Enhance Module, which emphasizes preserving crucial edge and texture details for detecting camouflaged targets. Extensive evaluations highlight the effectiveness of MSCDNet, which achieves 40.1% mAP50-95, 86.1% precision, and 68.1% recall while maintaining a low computational load with only 2.22 M parameters and 6.0 G FLOPs. When compared to other models, MSCDNet outperforms YOLO-family variants by 1.9% in mAP50-95 and uses 14% fewer parameters. Additional generalization tests on VisDrone2019 and BDD100K further validate its robustness, with improvements of 1.1% in mAP50 on VisDrone and 1.2% in mAP50-95 on BDD100K over baseline models. These results affirm that MSCDNet is well suited for tactical deployment in scenarios with limited computational resources, where reliable target detection is paramount. |
| format | Article |
| id | doaj-art-ebd756dafdbd495aab5b383dc66ebbba |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-ebd756dafdbd495aab5b383dc66ebbba2025-08-20T02:21:58ZengMDPI AGSensors1424-82202025-06-012512380010.3390/s25123800A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained EnvironmentsKaipeng Wang0Guanglin He1Xinmin Li2Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, ChinaScience and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, ChinaScience and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, ChinaTarget detection in resource-constrained environments faces multiple challenges such as the use of camouflage, diverse target sizes, and harsh environmental conditions. Moreover, the need for solutions suitable for edge computing environments, which have limited computational resources, adds complexity to the task. To meet these challenges, we propose MSCDNet (Multi-Scale Context Detail Network), an innovative and lightweight architecture designed specifically for efficient target detection in such environments. MSCDNet integrates three key components: the Multi-Scale Fusion Module, which improves the representation of features at various target scales; the Context Merge Module, which enables adaptive feature integration across scales to handle a wide range of target conditions; and the Detail Enhance Module, which emphasizes preserving crucial edge and texture details for detecting camouflaged targets. Extensive evaluations highlight the effectiveness of MSCDNet, which achieves 40.1% mAP50-95, 86.1% precision, and 68.1% recall while maintaining a low computational load with only 2.22 M parameters and 6.0 G FLOPs. When compared to other models, MSCDNet outperforms YOLO-family variants by 1.9% in mAP50-95 and uses 14% fewer parameters. Additional generalization tests on VisDrone2019 and BDD100K further validate its robustness, with improvements of 1.1% in mAP50 on VisDrone and 1.2% in mAP50-95 on BDD100K over baseline models. These results affirm that MSCDNet is well suited for tactical deployment in scenarios with limited computational resources, where reliable target detection is paramount.https://www.mdpi.com/1424-8220/25/12/3800target detectionlightweight neural networkmulti-scale feature fusioncontext-aware modulationedge computing |
| spellingShingle | Kaipeng Wang Guanglin He Xinmin Li A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments Sensors target detection lightweight neural network multi-scale feature fusion context-aware modulation edge computing |
| title | A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments |
| title_full | A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments |
| title_fullStr | A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments |
| title_full_unstemmed | A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments |
| title_short | A Lightweight Multi-Scale Context Detail Network for Efficient Target Detection in Resource-Constrained Environments |
| title_sort | lightweight multi scale context detail network for efficient target detection in resource constrained environments |
| topic | target detection lightweight neural network multi-scale feature fusion context-aware modulation edge computing |
| url | https://www.mdpi.com/1424-8220/25/12/3800 |
| work_keys_str_mv | AT kaipengwang alightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments AT guanglinhe alightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments AT xinminli alightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments AT kaipengwang lightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments AT guanglinhe lightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments AT xinminli lightweightmultiscalecontextdetailnetworkforefficienttargetdetectioninresourceconstrainedenvironments |