Article Details

Title · Authors · Abstract · Keywords · DOI · References

Remote Sensing Small Target Detection Based on YOLO-AGDA Multi-feature Gather-and-Distribute Mechanism

ZUO Hangxu1, YUAN Shichang2

(1.College of Digital Economy, Sichuan Vocational College of Chemical Technology, Luzhou 646005, China; 2.Institute of Digital Economy, Kaifeng University, Kaifeng 475004, China)

Section：Artificial Intelligence · Vol. 2026, Issue 9 · Pages：31-39 · 2096-4706（2026）09-0031-09 · CLC number：TP391.4 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.09.007

Abstract

To address the challenges of small-object omission, low feature fusion efficiency, and the difficulty in balancing model complexity and detection accuracy in multi-scale remote sensing Object Detection, this paper proposes a lightweight remote sensing detection model, termed YOLO-AGDA, based on the YOLOv8n framework. The model embeds an Atrous Spatial Pyramid Pooling (ASPP) module in the shallow layers to enhance multi-scale contextual feature representation, introduces a Gather-and-Distribute (GD) adaptive fusion mechanism to strengthen cross-layer semantic interaction, and adopts the Distance Intersection over Union (DIoU) loss function to improve localization accuracy. In addition, the ASDdet detection head is employed for object prediction. Experimental results on the RSOD dataset demonstrate that YOLO-AGDA achieves the mAP@0.5 of 94.5%, representing a 6.1 percentage-point improvement over the baseline model, while maintaining a compact parameter size of only 22.3 MB. These results indicate that the proposed model effectively balances detection accuracy and real-time inference performance, making it well suited for efficient Object Detection in complex remote sensing scenarios.

Keywords

remote sensing small Object Detection; YOLO-AGDA; Gather-and-Distribute mechanism; multi-scale feature fusion; DIoU loss function

References

  1. [1] WANG S Y，QU Z，LI C J，et al. BANet: Small and Multi-Object Detection With a Bidirectional Attention Network for Traffic Scenes [J/OL].Engineering Applications of Artificial Intelligence，2023，117：105504（2022-10-22）.https://doi.org/10.1016/j.engappai.2022.105504.
  2. [2] ZHANG Y，YE M，ZHU G，et al. FFCA-YOLO for Small Object Detection in Remote Sensing Images [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-14.
  3. [3] CUI Y，GUO D，YUAN H，et al. Enhanced YOLO Network for Improving the Efficiency of Traffic Sign Detection [J/OL].Applied Sciences，2024，14（2）：555（2024-01-08）.https://doi.org/10.3390/app14020555.
  4. [4] ZHANG M，WANG Z，SONG W，et al. Efficient Small-Object Detection in Underwater Images Using the Enhanced YOLOv8 Network [J/OL].Applied Sciences，2024，14（3）：1095（2024-01-27）.https://doi.org/10.3390/app14031095.
  5. [5] LV C，ZHOU H，CHEN Y，et al. A Lightweight Fire Detection Algorithm for Small Targets Based on YOLOv5s [J].Scientific Reports，2024，14（1）：14104（2024-01-19）.https://doi.org/10.1038/s41598-024-64934-4.
  6. [6] ZHAO H，JING J，LIU Y，et al. FSDF: A High-Performance Fire Detection Framework [J/OL].Expert Systems with Applications，2024，238：121665（2024-03-15）.https://doi.org/10.1016/j.eswa.2023.121665.
  7. [7] LI C，ZHOU S，YU H，et al. An Efficient Method for Detecting Dense and Small Objects in UAV Images [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2024，17：1082-1094.
  8. [8] LIU H，YU Y，LIU S，et al. A Military Object Detection Model of UAV Reconnaissance Image and Feature Visualization [J/OL].Applied Sciences，2022，12（23）：12236.（2022-11-29）.https://doi.org/10.3390/app122312236.
  9. [9] JANAKIRAMAIAH B，KALYANI G，KARUNA A，et al. Military Object Detection in Defense Using Multi-Level Capsule Networks [J].Soft Computing，2023，27（2）：1045-1059.
  10. [10] GAO L，LI C，WEI Z，et al. Military Unmanned Equipment Image Target Recognition Method Based on Improved Deep Learning [C]// The 2nd International Conference on Algorithms，Network and Computer Technology.Wuhan：IOP Publishing，2024，2732（1）：012004[2025-10-09].https://iopscience.iop.org/article/10.1088/1742-6596/2732/1/012004.
  11. [11] WANG H，LIU C，CAI Y，et al. YOLOv8-QSD: An Improved Small Object Detection Algorithm for Autonomous Vehicles Based on YOLOv8 [J].IEEE Transactions on Instrumentation and Measurement，2024，73：1-12.
  12. [12] ZHANG Y，YE M，ZHU G，et al. FFCA-YOLO for Small Object Detection in Remote Sensing Images [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-14.
  13. [13] ZHAO Z，DU J，LI C，et al. Dense Tiny Object Detection: A Scene Context Guided Approach and a Unified Benchmark [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-15.
  14. [14] WANG Z，BAI L，SONG G，et al. Optimized Faster R-CNN for Oil Wells Detection From High-Resolution Remote Sensing Images [J].International Journal of Remote Sensing，2023，44（22）：6897-6928.
  15. [15] SHI J，WANG J. Multi-Scale Semantic Information Refinement and Hybrid Dual Attention Module Based Object Detection in Remote Sensing Images [C]//Proceedings of the International Conference on Computer Vision and Deep Learning.New York：ACM，2024：1-7.
  16. [16] MA T J. Remote Sensing Detection Enhancement [J/OL].Journal of Big Data，2021，8（1）：127（2021-10-02）.https://doi.org/10.1186/s40537-021-00517-8.
  17. [17] ZHOU L，LI Y，RAO X，et al. Feature Enhancement-Based Ship Target Detection Method in Optical Remote Sensing Images [J/OL].Electronics，2022，11（4）：634（2022-02-18）.https://doi.org/10.3390/electronics11040634.
  18. [18] QING Y，LIU W，FENG L，et al. Improved YOLO Network for Free-Angle Remote Sensing Target Detection [J].Remote Sensing，2021，13（11）：2171（2021-06-01）.https://doi.org/10.3390/rs13112171.
  19. [19] LIU X，GONG W，SHANG L，et al. Remote Sensing Image Target Detection and Recognition Based on YOLOv5 [J/OL].Remote Sensing，2023，15（18）：4459（2023-09-10）.https://doi.org/10.3390/rs15184459.
  20. [20] YUE M，ZHANG L，ZHANG Y，et al. An Improved YOLOv8 Detector for Multi-Scale Target Detection in Remote Sensing Images [J].IEEE Access，2024，12：1586-1600.
  21. [21] SAGAR A S，CHEN Y，XIE Y K，et al. MSA R-CNN: A Comprehensive Approach to Remote Sensing Object Detection and Scene Understanding [J/OL].Expert Systems with Applications，2024，241：122788（2023-12-01）.https://doi.org/10.1016/j.eswa.2023.122788.
  22. [22] WEN G，CAO P，WANG H，et al. MS-SSD：Multi-Scale Single Shot Detector for Ship Detection in Remote Sensing Images [J].Applied Intelligence，2023，53（2）：1586-1604.
  23. [23] HUO B，LI C，ZHANG J，et al. SAFF-SSD: Self-Attention Combined Feature Fusion-Based SSD for Small Object Detection in Remote Sensing [J/OL].Remote Sensing，2023，15（12）：3027（2023-06-09）.https://doi.org/10.3390/rs15123027.
  24. [24] HAO Z，WANG C，CHEN P，et al. A Detection Method for Small Target in Remote Sensing Image Based on Improved SSD [C]//International Conference on Electronic Information Engineering and Computer Science （EIECS 2022）.Bellingham：SPIE，2023，12602：378-383.
  25. [25] WU T，DONG Y. YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition [J/OL].Applied Sciences，2023，13（24）：12977（2023-12-05）.https://doi.org/10.3390/app132412977.
  26. [26] SHEN L，LANG B，SONG Z. CA-YOLO：Model Optimization for Remote Sensing Image Object Detection [J].IEEE Access，2023，11：67890-67903.
  27. [27] YI H，LIU B，ZHAO B，et al. Small Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2023，16：11200-11212.
  28. [28] ZHANG Y，YE M，ZHU G，et al. FFCA-YOLO for Small Object Detection in Remote Sensing Images [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-14.
  29. [29] SONG Q，HOU M，XUE Y，et al. MA-YOLO: A Multi-Attention Object Detection Network for Remote Sensing Images [J/OL].Journal of Electronic Imaging，2024，33（1）：013006（2024-01-05）.https://doi.org/10.1117/1.JEI.33.1.013006.
  30. [30] REDMON J，DIVVALA S，GIRSHICK R，et al. You Only Look Once: Unified, Real-Time Object Detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas：IEEE，2016：779-788.
  31. [31] AFFES N，KTARI J，BEN AMOR N，et al. Comparison of YOLOv5, YOLOv6, YOLOv7 and YOLOv8 for Intelligent Video Surveillance [J].Journal of Information Assurance & Security，2023，18（5）：1-12.
  32. [32] HE K，ZHANG X，REN S，et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
  33. [33] WANG C，HE W，NIE Y，et al. Gold-YOLO：Efficient Object Detector via Gather-and-Distribute Mechanism [J].Advances in Neural Information Processing Systems，2024，36：1-12.
  34. [34] ZHENG Z，WANG P，LIU W，et al. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression [C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York：AAAI，2020，34（7）：12993-13000.
  35. [35] CHEN L C，PAPANDREOU G，KOKKINOS I，et al. DeepLab: Semantic Image Segmentation With Deep Convolutional Nets，Atrous Convolution，and Fully Connected CRFs [J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40（4）：834-848.
  36. [36] LONG Y，GONG Y，XIAO Z，et al. Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks [J].IEEE Transactions on Geoscience and Remote Sensing，2017，55（5）：2486-2498.

Funding

Project of Sichuan Vocational and Technical College of Chemical Technology (SCHYB-2025-18)

About the authors

Zuo Hangxu (1998-), male, Han ethnicity, from Luzhou, Sichuan, holds a master's degree. His research interests include machine learning, deep learning, and their applications in healthcare and object detection; Yuan Shichang (1996-), male, Han ethnicity, from Xuchang, Henan Province, holds a master's degree. His research interests include data mining, network security, and intelligent information processing technology, with a focus on feature modeling and security analysis methods in complex data environments.