MBD-YOLO: An Improved Lightweight Multi-Scale Small-Object Detection Model for UAVs Based on YOLOv8
Source abstract
Abstract
To address the challenges of low detection accuracy and weak generalization in UAV aerial imagery caused by complex ground environments, significant scale variations among targets, dense small objects, and background interference, this paper proposes an improved lightweight multi-scale small-object detection model, MBD-YOLO (MBFF module, BiMS-FPN, and Dual-Stream Head). Specifically, to enhance multi-scale feature extraction capabilities, we introduce the Multi-Branch Feature Fusion (MBFF) module, which dynamically adjusts receptive fields through parallel branches and adaptive depthwise convolutions, expanding the receptive field while preserving detail perception. We further design a lightweight Bidirectional Multi-Scale Feature Aggregation Pyramid Network (BiMS-FPN), integrating bidirectional propagation paths and a Multi-Scale Feature Aggregation (MSFA) module to mitigate feature spatial misalignment and improve small-target detection. Additionally, the Dual-Stream Head with NMS-free architecture leverages a task-aligned architecture and dynamic matching strategies to boost inference speed without compromising accuracy. Experiments on the VisDrone2019 dataset demonstrate that MBD-YOLO-n surpasses YOLOv8n by 6.3% in mAP50 and 8.2% in mAP50–95, with accuracy gains of 17.96–55.56% for several small-target categories, while increasing parameters by merely 3.1%. Moreover, MBD-YOLO-s achieves superior detection accuracy, efficiency, and generalization with only 12.1 million parameters, outperforming state-of-the-art models and proving suitable for resource-constrained embedded deployment scenarios. The superior performance of MBD-YOLO, which harmonizes high precision with low computational demand, fulfills the critical requirements for real-time deployment on resource-limited UAVs, showing great promise for applications in traffic monitoring, urban security, and agricultural surveying.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Robotics and Sensor-Based Localization · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Langfang Integrated Natural Resources Survey Center, China Geological Survey, Langfang 065099, China
Innovation Base for Natural Resources Monitoring Technology of Yongding River Downstream Areas, Geological Society of China, Langfang 065099, China
North China Institute of Aerospace Engineering, Langfang 065000, China
School of Emergency Management and Safety Engineering, North China University of Science and Technology, Tangshan 063210, China
Funding
the Geological Survey Project of the China Geological Survey
References (59)
Show source-provided references
1. Osmani, K., and Schulz, D. (2024). Comprehensive Investigation of Unmanned Aerial Vehicles (UAVs): An In-Depth Analysis of Avionics Systems. Sensors, 24.10.3390/s24103064 ↗
2. Marine environmental monitoring with unmanned vehicle platforms: Present applications and future prospects10.1016/j.scitotenv.2022.159741 ↗
3. UAV remote sensing applications in marine monitoring: Knowledge visualization and review10.1016/j.scitotenv.2022.155939 ↗
4. Seidaliyeva, U., Ilipbayeva, L., Taissariyeva, K., Smailov, N., and Matson, E.T. (2024). Advances and Challenges in Drone Detection and Classification Techniques: A State-of-the-Art Review. Sensors, 24.10.3390/s24010125 ↗
5. Multiple Vehicle Detection and Tracking in Highway Traffic Surveillance Video Based on SIFT Feature Matching
6. Robust Traffic Sign Recognition Based on Color Global and Local Oriented Edge Magnitude Patterns10.1109/TITS.2014.2298912 ↗
7. Automatic Building Extraction via Adaptive Iterative Segmentation With LiDAR Data and High Spatial Resolution Imagery Fusion10.1109/JSTARS.2020.2992298 ↗
8. Vehicle Detection From UAV Imagery With Deep Learning: A Review10.1109/TNNLS.2021.3080276 ↗
9. Zhao, Y., Ma, Q., Lei, G., Wang, L., and Guo, C. (2025). Research on Lightweight Tracking of Small-Sized UAVs Based on the Improved YOLOv8N-Drone Architecture. Drones, 9.10.3390/drones9080551 ↗
10. Das, A.K., Nayak, J., Naik, B., Pati, S.K., and Pelusi, D. (2020). Deep Learning Techniques—R-CNN to Mask R-CNN: A Survey. Computational Intelligence in Pattern Recognition, Springer.10.1007/978-981-15-2449-3_35 ↗
11. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
12. Girshick, R., and Ieee (2015, January 7–13). Fast R-CNN. Proceedings of the IEEE International Conferenceon Computer Vision, Santiago, Chile.10.1109/ICCV.2015.169 ↗
13. Faster R-CNN: Towards Real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
14. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 17). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision—ECCV 2016, Cham, Switzerland.10.1007/978-3-319-46448-0_2 ↗
15. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16–22). DETRs Beat YOLOs on Real-time Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01605 ↗
16. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS10.3390/make5040083 ↗
17. Comparative study of some deep learning object detection algorithms: R-CNN, fast R-CNN, faster R-CNN, SSD, and YOLO
18. Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
19. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
20. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
21. Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering10.1016/j.ijmedinf.2019.01.005 ↗
22. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
23. Hua, W., Chen, Q., and Chen, W. (2024). A new lightweight network for efficient UAV object detection. Sci. Rep., 14.10.1038/s41598-024-64232-z ↗
24. Xue, Z., Lin, H., and Wang, F. (2022). A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement. Forests, 13.10.3390/f13081332 ↗
25. Improved Mosaic: Algorithms for more Complex Images10.1088/1742-6596/1684/1/012094 ↗
26. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path Aggregation Network for Instance Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
27. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H., and Ieee Comp, S.O.C. (2020, January 14–19). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
28. Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014, January 6–12). Microsoft COCO: Common Objects in Context. Proceedings of the Computer Vision—ECCV 2014, Zurich, Switzerland.10.1007/978-3-319-10599-4 ↗
29. Khanam, R., and Hussain, M. (2024). What is YOLOv5: A deep look into the internal features of the popular object detector. arXiv.
30. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv.
31. Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., and Sun, J. (2021, January 20–25). RepVGG: Making VGG-Style ConvNets Great Again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
32. Wang, C., Bochkovskiy, A., and Liao, H. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
33. Varghese, R., and Sambath, M. (2024, January 18–19). Yolov8: A novel object detection algorithm with enhanced performance and robustness. Proceedings of the 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), Chennai, India.10.1109/ADICS58448.2024.10533619 ↗
34. Zhao, X., Zhang, H., Zhang, W., Ma, J., Li, C., Ding, Y., and Zhang, Z. (2025). MSUD-YOLO: A Novel Multiscale Small Object Detection Model for UAV Aerial Images. Drones, 9.10.3390/drones9060429 ↗
35. Chen, C., Zheng, Z., Xu, T., Guo, S., Feng, S., Yao, W., and Lan, Y. (2023). YOLO-Based UAV Technology: A Review of the Research and Its Applications. Drones, 7.10.3390/drones7030190 ↗
36. Yang, F., Ouyang, T., and Liu, C. (2024, January 22–24). Deformer-FPN: FPN network based on deformable convolution and lightweight upsampling operator for ship detection in SAR image. Proceedings of the 2024 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Zhuhai, China.10.1109/ICSIDP62679.2024.10868184 ↗
37. PA-YOLO: Small Target Detection Algorithm with Enhanced Information Representation for UAV Aerial Photography
38. Xu, S., Ji, Y., Wang, G., Jin, L., and Wang, H. (2023, January 17–20). GFSPP-YOLO: A Light YOLO Model Based on Group Fast Spatial Pyramid Pooling. Proceedings of the 2023 IEEE 11th International Conference on Information, Communication and Networks (ICICN), Xi’an, China.10.1109/ICICN59530.2023.10393445 ↗
39. Kim, M., Jeong, J., and Kim, S. (2021). ECAP-YOLO: Efficient Channel Attention Pyramid YOLO for Small Object Detection in Aerial Image. Remote Sens., 13.10.3390/rs13234851 ↗
40. Vehicle detection in aerial imagery: A small target detection benchmark10.1016/j.jvcir.2015.11.002 ↗
41. Gold-yolo: Efficient object detector via gather-and-distribute mechanism
42. Zhang, Z. (2023). Drone-YOLO: An Efficient Neural Network Method for Target Detection in Drone Images. Drones, 7.10.3390/drones7080526 ↗
43. Simplify-YOLOv5m: A Simplified High-Speed Insulator Detection Algorithm for UAV Images10.1109/TIM.2025.3614801 ↗
44. Liu, H., Sun, F., Gu, J., and Deng, L. (2022). SF-YOLOv5: A Lightweight Small Object Detection Algorithm Based on Improved Feature Fusion Mode. Sensors, 22.10.3390/s22155817 ↗
45. LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle10.1016/j.ins.2024.121366 ↗
46. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., and Liu, Z. (2020, January 14–19). Dynamic convolution: Attention over convolution kernels. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ELECTR NETWORK, Seattle, WA, USA.10.1109/CVPR42600.2020.01104 ↗
47. Wang, S., Zhao, Z., Chen, Y., Mao, Y., and Cheung, J. (2025). Enhancing Thyroid Nodule Detection in Ultrasound Images: A Novel YOLOv8 Architecture with a C2fA Module and Optimized Loss Functions. Technologies, 13.10.3390/technologies13010028 ↗
48. Dang-Nguyen, D.T., Gurrin, C., Larson, M., Smeaton, A.F., Rudinac, S., Dao, M.S., Trattner, C., and Chen, P. (2023). SPEM: Self-adaptive Pooling Enhanced Attention Module for Image Recognition. MultiMedia Modeling, Springer.10.1007/978-3-031-27077-2 ↗
49. Yolov10: Real-time end-to-end object detection
50. Dong, Y., Xie, X., An, Z., Qu, Z., Miao, L., and Zhou, Z. (2023). NMS-Free Oriented Object Detection Based on Channel Expansion and Dynamic Label Assignment in UAV Aerial Images. Remote Sens., 15.10.3390/rs15215079 ↗
51. PANet: A Point-Attention Based Multi-Scale Feature Fusion Network for Point Cloud Registration
52. Tan, M., Pang, R., and Le, Q.V. (2019). EfficientDet: Scalable and Efficient Object Detection. arXiv.10.1109/CVPR42600.2020.01079 ↗
53. Feng, J., and Yi, C. (2022). Lightweight Detection Network for Arbitrary-Oriented Vehicles in UAV Imagery via Global Attentive Relation and Multi-Path Fusion. Drones, 6.10.3390/drones6050108 ↗
54. Yang, J., Chen, F., Das, R.K., Zhu, Z., and Zhang, S. (2024, January 14–19). Adaptive-Avg-Pooling Based Attention Vision Transformer for Face Anti-Spoofing. Proceedings of the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Republic of Korea.10.1109/ICASSP48485.2024.10446940 ↗
55. AlignSeg: Feature-Aligned Segmentation Networks
56. Chen, Y., Chen, Q., Hu, Q., and Cheng, J. (2022). DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection. arXiv.
57. Zong, Z., Song, G., and Liu, Y. (2022). DETRs with Collaborative Hybrid Assignments Training. arXiv.10.1109/ICCV51070.2023.00621 ↗
58. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, January 7–12). Distance-IoU loss: Faster and better learning for bounding box regression. Proceedings of the AAAI conference on artificial intelligence, New York, NY, USA.10.1609/aaai.v34i07.6999 ↗
59. Powers, D.M.W. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.