MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity
Despite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, signif...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/225 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548949774663680 |
|---|---|
| author | Peng Huang Yan Yin Kaifeng Hu Weidong Yang |
| author_facet | Peng Huang Yan Yin Kaifeng Hu Weidong Yang |
| author_sort | Peng Huang |
| collection | DOAJ |
| description | Despite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, significantly compromise detection accuracy. Moreover, the computational constraints of edge computing platforms pose a fundamental challenge in balancing real-time processing requirements with detection performance. Here, we present MonoSeg, a novel instance segmentation framework optimized for UAV perspective infrared vehicle detection. Our approach introduces three key innovations: (1) the Ghost Feature Bottle Cross module (GFBC), which enhances backbone feature extraction efficiency while significantly reducing computational over-head; (2) the Scale Feature Recombination module (SFR), which optimizes feature selection in the Neck stage through adaptive multi-scale fusion; and (3) Comprehensive Loss function that enforces precise instance boundary delineation. Extensive experimental evaluation on bench-mark datasets demonstrates that MonoSeg achieves state-of-the-art performance across standard metrics, including Box mAP and Mask mAP, while maintaining substantially lower computational requirements compared to existing methods. |
| format | Article |
| id | doaj-art-ce498fb980c74824bb6e3ce2126eaf1f |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-ce498fb980c74824bb6e3ce2126eaf1f2025-01-10T13:21:17ZengMDPI AGSensors1424-82202025-01-0125122510.3390/s25010225MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and IntegrityPeng Huang0Yan Yin1Kaifeng Hu2Weidong Yang3National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430000, ChinaNational Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430000, ChinaNational Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430000, ChinaNational Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430000, ChinaDespite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, significantly compromise detection accuracy. Moreover, the computational constraints of edge computing platforms pose a fundamental challenge in balancing real-time processing requirements with detection performance. Here, we present MonoSeg, a novel instance segmentation framework optimized for UAV perspective infrared vehicle detection. Our approach introduces three key innovations: (1) the Ghost Feature Bottle Cross module (GFBC), which enhances backbone feature extraction efficiency while significantly reducing computational over-head; (2) the Scale Feature Recombination module (SFR), which optimizes feature selection in the Neck stage through adaptive multi-scale fusion; and (3) Comprehensive Loss function that enforces precise instance boundary delineation. Extensive experimental evaluation on bench-mark datasets demonstrates that MonoSeg achieves state-of-the-art performance across standard metrics, including Box mAP and Mask mAP, while maintaining substantially lower computational requirements compared to existing methods.https://www.mdpi.com/1424-8220/25/1/225UAV perspectiveinfrared image target recognitioninstance segmentationlow computation |
| spellingShingle | Peng Huang Yan Yin Kaifeng Hu Weidong Yang MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity Sensors UAV perspective infrared image target recognition instance segmentation low computation |
| title | MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity |
| title_full | MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity |
| title_fullStr | MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity |
| title_full_unstemmed | MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity |
| title_short | MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity |
| title_sort | monoseg an infrared uav perspective vehicle instance segmentation model with strong adaptability and integrity |
| topic | UAV perspective infrared image target recognition instance segmentation low computation |
| url | https://www.mdpi.com/1424-8220/25/1/225 |
| work_keys_str_mv | AT penghuang monoseganinfrareduavperspectivevehicleinstancesegmentationmodelwithstrongadaptabilityandintegrity AT yanyin monoseganinfrareduavperspectivevehicleinstancesegmentationmodelwithstrongadaptabilityandintegrity AT kaifenghu monoseganinfrareduavperspectivevehicleinstancesegmentationmodelwithstrongadaptabilityandintegrity AT weidongyang monoseganinfrareduavperspectivevehicleinstancesegmentationmodelwithstrongadaptabilityandintegrity |