Detecting infrared UAVs on edge devices through lightweight instance segmentation.
<h4>Motivation</h4>Infrared unmanned aerial vehicle (UAV) detection for surveillance applications faces three conflicting requirements: accurate detection of pixel-level thermal signatures, real-time processing capabilities, and deployment feasibility on resource-constrained edge devices...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0330074 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849228079259451392 |
|---|---|
| author | YuZhi Chen HaoYue Sun Liang Tian Ye Yang ShenYang Wang TianYou Wang |
| author_facet | YuZhi Chen HaoYue Sun Liang Tian Ye Yang ShenYang Wang TianYou Wang |
| author_sort | YuZhi Chen |
| collection | DOAJ |
| description | <h4>Motivation</h4>Infrared unmanned aerial vehicle (UAV) detection for surveillance applications faces three conflicting requirements: accurate detection of pixel-level thermal signatures, real-time processing capabilities, and deployment feasibility on resource-constrained edge devices. Current deep learning approaches typically optimize for one or two of these objectives while compromising the third.<h4>Method</h4>This paper presents YOLO11-AU-IR, a lightweight instance segmentation framework that addresses these challenges through three architectural innovations. First, Efficient Adaptive Downsampling (EADown) employs dual-branch processing with grouped convolutions to preserve small-target spatial features during multi-scale fusion. Second, HeteroScale Attention Network (HSAN) implements grouped multi-scale convolutions with joint channel-spatial attention mechanisms for enhanced cross-scale feature representation. These architectural optimizations collectively reduce computational requirements while maintaining detection accuracy. Third, Adaptive Threshold Focal Loss (ATFL) introduces epoch-adaptive parameter tuning to address the extreme foreground-background imbalance inherent in infrared UAV imagery.<h4>Results</h4>YOLO11-AU-IR is evaluated on the AUVD-Seg300 dataset, achieving 97.7% mAP@0.50 and 75.2% mAP@0.50:0.95, surpassing the YOLO11n-seg baseline by 1.7% and 4.4%, respectively. The model reduces parameters by 24.5% and GFLOPs by 11.8% compared to YOLO11n-seg, while maintaining real-time inference at 59.8 FPS on an NVIDIA RTX 3090 with low variance. On the NVIDIA Jetson TX2, under INT8 CPU-only deployment, YOLO11-AU-IR retains 95% mAP@0.50 with minimal memory footprint and stable performance, demonstrating its practical edge compatibility. Ablation studies further confirm the complementary contributions of EADown, HSAN, and ATFL in enhancing accuracy, robustness, and efficiency. Code and dataset are publicly available at https://github.com/chen-yuzhi/YOLO11-AU-IR. |
| format | Article |
| id | doaj-art-5603bf5bb94b4ab4bb175c307c0f7de1 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-5603bf5bb94b4ab4bb175c307c0f7de12025-08-23T05:32:31ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01208e033007410.1371/journal.pone.0330074Detecting infrared UAVs on edge devices through lightweight instance segmentation.YuZhi ChenHaoYue SunLiang TianYe YangShenYang WangTianYou Wang<h4>Motivation</h4>Infrared unmanned aerial vehicle (UAV) detection for surveillance applications faces three conflicting requirements: accurate detection of pixel-level thermal signatures, real-time processing capabilities, and deployment feasibility on resource-constrained edge devices. Current deep learning approaches typically optimize for one or two of these objectives while compromising the third.<h4>Method</h4>This paper presents YOLO11-AU-IR, a lightweight instance segmentation framework that addresses these challenges through three architectural innovations. First, Efficient Adaptive Downsampling (EADown) employs dual-branch processing with grouped convolutions to preserve small-target spatial features during multi-scale fusion. Second, HeteroScale Attention Network (HSAN) implements grouped multi-scale convolutions with joint channel-spatial attention mechanisms for enhanced cross-scale feature representation. These architectural optimizations collectively reduce computational requirements while maintaining detection accuracy. Third, Adaptive Threshold Focal Loss (ATFL) introduces epoch-adaptive parameter tuning to address the extreme foreground-background imbalance inherent in infrared UAV imagery.<h4>Results</h4>YOLO11-AU-IR is evaluated on the AUVD-Seg300 dataset, achieving 97.7% mAP@0.50 and 75.2% mAP@0.50:0.95, surpassing the YOLO11n-seg baseline by 1.7% and 4.4%, respectively. The model reduces parameters by 24.5% and GFLOPs by 11.8% compared to YOLO11n-seg, while maintaining real-time inference at 59.8 FPS on an NVIDIA RTX 3090 with low variance. On the NVIDIA Jetson TX2, under INT8 CPU-only deployment, YOLO11-AU-IR retains 95% mAP@0.50 with minimal memory footprint and stable performance, demonstrating its practical edge compatibility. Ablation studies further confirm the complementary contributions of EADown, HSAN, and ATFL in enhancing accuracy, robustness, and efficiency. Code and dataset are publicly available at https://github.com/chen-yuzhi/YOLO11-AU-IR.https://doi.org/10.1371/journal.pone.0330074 |
| spellingShingle | YuZhi Chen HaoYue Sun Liang Tian Ye Yang ShenYang Wang TianYou Wang Detecting infrared UAVs on edge devices through lightweight instance segmentation. PLoS ONE |
| title | Detecting infrared UAVs on edge devices through lightweight instance segmentation. |
| title_full | Detecting infrared UAVs on edge devices through lightweight instance segmentation. |
| title_fullStr | Detecting infrared UAVs on edge devices through lightweight instance segmentation. |
| title_full_unstemmed | Detecting infrared UAVs on edge devices through lightweight instance segmentation. |
| title_short | Detecting infrared UAVs on edge devices through lightweight instance segmentation. |
| title_sort | detecting infrared uavs on edge devices through lightweight instance segmentation |
| url | https://doi.org/10.1371/journal.pone.0330074 |
| work_keys_str_mv | AT yuzhichen detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation AT haoyuesun detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation AT liangtian detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation AT yeyang detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation AT shenyangwang detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation AT tianyouwang detectinginfrareduavsonedgedevicesthroughlightweightinstancesegmentation |