Abstract
The prevailing applications of Unmanned Aerial Vehicles (UAVs) in transportation systems promote the development of object detection methods to collect real-time traffic information through UAVs. However, due to the small size and high density of objects from the aerial perspective, most existing algorithms are difficult to accurately process and extract informative features from the traffic images collected by UAVs. To address the challenges, this paper proposes a new real-time small object detection (RSOD) algorithm based on YOLOv3, which improves the small object detection accuracy by (i) using feature maps of a shallower layer containing more fine-grained information for location prediction; (ii) fusing local and global features of shallow and deep feature maps in Feature Pyramid Network(FPN) to enhance the ability to extract more representative features; (iii)assigning weights to output features of FPN and fusing them adaptively; and(iv) improving the excitation layer in Squeeze-and-Excitation attention mechanism to adjust the feature responses of each channel more precisely. Experimental results show that, when the input size is 608 × 608 × 3, the precision of the proposed RSOD algorithm measured by mAP@0.5 is 43.3% and 52.7% on the Visdrone-DET2018 and UAVDT datasets, which is 3.4% and 5.1% higher than those of YOLOv3, respectively.
Similar content being viewed by others
References
Zhao P, Hu H (2019) Geographical patterns of traffic congestion in growing megacities: Big data analytics from Beijing [J]. Cities 92:164–174
El-Sayed H, Chaqfa M, Zeadally S et al (2019) A traffic-aware approach for enabling unmanned aerial vehicles (UAVs) in smart city scenarios [J]. IEEE Access 7:86297–86305
Kong Z, Zhang N, Guan X et al (2021) Detecting slender objects with uncertainty based on keypoint-displacement representation [J]. Neural Networks 139:246–254
Ren J, Guo Y, Zhang D et al (2018) Distributed and efficient object detection in edge computing: challenges and solutions [J]. IEEE Network 32(6):137–143
Sun W, Zhang X, He X (2020) A Two-stage vehicle type recognition method combining the most effective gabor features [J]. Cmc-Computers Materials And Continua 65(3):2489–2510
Fan H, Wen L, Du D et al (2020) VisDrone-SOT2020: The Vision Meets Drone Single Object Tracking Challenge Results [C]. In: 2020 European conference on computer vision (ECCV), pp 728–749
Du D, Qi Y, Yu H et al (2018) The unmanned aerial vehicle benchmark: Object detection and tracking [C]. In: 2018 European conference on computer vision (ECCV), pp 370–386
Zhu P, Wen L, Du D et al (2018) Visdrone-det2018: The vision meets drone object detection in image challenge results [C]. In: 2018 European conference on computer vision workshops
Liu L, Ouyang W, Wang X et al (2020) Deep learning for generic object detection: A survey [J]. International Journal of Computer Vision 128(2):261–318
Haas T, Schubert C, Eickhoff M et al (2020) BubCNN: Bubble detection using Faster RCNN and shape regression network [J]. Chemical Engineering Science 216:115467
Li Z, Li Y, Yang Y et al (2021) A high-precision detection method of hydroponic lettuce seedlings status based on improved Faster RCNN [J]. Computers and Electronics in Agriculture 182:106054
Zhang Q, Chang X, Bian S B (2020) Vehicle-damage-detection segmentation algorithm based on improved mask RCNN [J]. IEEE Access 8:6997–7004
Sun X, Wu P, Hoi S C H (2018) Face detection using deep learning: An improved faster RCNN approach [J]. Neurocomputing 299:42–50
Zhai S, Shang D, Wang S et al (2020) DF-SSD: an improved ssd object detection algorithm based on DenseNet and feature fusion [J]. IEEE Access 8:24344–24357
Fu K, Zhang T, Zhang Y et al (2019) Meta-SSD: Towards fast adaptation for few-shot object detection with meta-learning [J]. IEEE Access 7:77597–77606
Huang Z, Wang J, Fu X et al (2020) DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection [J]. Information Sciences 522:241–258
Liu Y, Sun P, Wergeles N et al (2021) A survey and performance evaluation of deep learning methods for small object detection [J]. Expert Systems with Applications 2021:114602
Tong K, Wu Y, Zhou F (2020) Recent advances in small object detection based on deep learning: A review [J]. Image and Vision Computing 97:103910
Pérez-Hernández F, Tabik S, Lamas A et al (2020) Object detection binary classifiers methodology based on deep learning to identify small objects handled similarly: application in video surveillance [J]. Knowledge-Based Systems 194:105590
Singh B, Davis L S (2018) An analysis of scale invariance in object detection snip [C]. In: 2018 IEEE conference on computer vision and pattern recognition (CVPR), pp 3578–3587
Lin T Y, Girshick R (2017) Feature pyramid networks for object detection. In: 2017 IEEE conference on computer vision and pattern recognition(CVPR), pp 2117–2125
Liu Y, Yang F, Hu P (2020) Small-object detection in UAV-captured images via multi-branch parallel feature pyramid networks [J]. IEEE Access 8:145740–145750
Zhang X, Izquierdo E, Chandramouli K (2019) Dense and small object detection in uav vision based on cascade network [C]. In: 2019 the IEEE/CVF international conference on computer vision workshops
Bai Y, Zhang Y, Ding M et al (2018) Sod-mtgan: Small object detection via multi-task generative adversarial network [C]. In: The European conference on computer vision (ECCV), pp 206–221
Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767
Sun W, Zhang X, Shi S et al (2019) Vehicle classification approach based on the combined texture and shape features with a compressive DL [J]. IET Intell Transp Syst 13(7):1069– 1077
Tian F, Gao Y, Fang Z et al (2021) Depth estimation using a self-supervised network based on cross-layer feature fusion and the quadtree constraint [J]. In: IEEE transactions on circuits and systems for video technology
Liu S, Qi L, Qin H et al (2018) Path aggregation network for instance segmentation [C]. In: IEEE conference on computer vision and pattern recognition(CVPR), vol 2018, pp 8759–8768
Ghiasi G, Lin T Y, Le Q V (2019) Nas-fpn: Learning scalable feature pyramid architecture for object detection [C]. In: The IEEE/ CVF conference on computer vision and pattern recognition (CVPR), pp 7036–7045
Xu H, Yao L, Zhang W et al (2019) Auto-fpn: Automatic network architecture adaptation for object detection beyond classification [C]. In: The IEEE/CVF international conference on computer vision (ICCV), vol 2019, pp 6649–6658
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks [C]. In: The IEEE conference on computer vision and pattern recognition (CVPR), vol 2018, pp 7132–7141
Woo S, Park J, Lee J Y et al (2018) Cbam: convolutional block attention module [C]. In: The European conference on computer vision (ECCV), vol 2018, pp 3–19
Gao P, Yuan R, Wang F et al (2020) Siamese attentional keypoint network for high performance visual tracking [J]. Knowledge-based systems 193:105448
Gao P, Zhang Q, Wang F et al (2020) Learning reinforced attentional representation for end-to-end visual tracking [J]. Information Sciences 517:52–67
Gómez-Ríos A, Tabik S, Luengo J et al (2019) Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation [J]. Expert Systems with Applications 118:315–328
Li C, Yang T, Zhu S et al (2020) Density map guided object detection in aerial images [C]. In: The IEEE/CVF conference on computer vision and pattern recognition workshops, vol 2020, pp 190–191
Yang F, Fan H, Chu P et al (2019) Clustered object detection in aerial images [C]. In: The IEEE/CVF international conference on computer vision (ICCV), vol 2019, pp 8311–8320
Liu Y, Gu Y C, Zhang XY et al (2020) Lightweight salient object detection via hierarchical visual perception learning [J]. IEEE Transactions on Cybernetics 2020:1–11
Sun W, Zhang X, He X. (2019) Lightweight image classifier using dilated and depthwise separable convolutions [J]. Journal of Cloud Computing 2020 9(1):1–12
Choudhary T, Mishra V, Goswami A et al (2020) A comprehensive survey on model compression and acceleration [J]. Artif Intell Rev 2020 53(7):5113–5155
Gou J, Yu B, Maybank SJ et al (2021) Knowledge distillation: a survey [J]. Int J Comput Vis 2021 129(6):1789–1819
Acknowledgements
This study was supported in part by National Natural Science Foundation of China (No.61304205, 61502240), the Natural Science Foundation of Jiangsu Province (BK20191401, BK20201136) and the Innovation and Entrepreneurship Training Project of College Students(202010300290, 202010300211, 202010300116E).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sun, W., Dai, L., Zhang, X. et al. RSOD: Real-time small object detection algorithm in UAV-based traffic monitoring. Appl Intell 52, 8448–8463 (2022). https://doi.org/10.1007/s10489-021-02893-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02893-3