基于小目标遮挡感知的烟头检测算法

doi:10.3778/j.issn.1002-8331.2407-0111

摘要/Abstract

摘要： 在复杂的电力作业场景中，烟头通常为小目标，且容易受到其他物体的遮挡，现有的小目标检测方法在多尺度特征融合和遮挡感知方面仍存在不足，尚未充分考虑电力场景的特殊需求。为解决这一问题，提出了一种适用于电力场景下小目标遮挡感知的烟头检测算法CBD-STOA。针对电力场景下烟头小目标检测精度低的问题，在颈部网络中引入了多尺度序列特征融合模块SSFF，以增强网络的多尺度信息提取能力，从而提高检测精度。为了应对烟头密集场景中的高误报率问题，CBD-STOA设计了三重特征融合模块TFF，通过融合不同尺度的特征图来增加细节信息，减少误报率。为了解决烟头遮挡的问题，CBD-STOA设计了遮挡感知检测头OADHead，通过执行多尺度空间传播，充分利用上下文信息来增强模型对特征图的全局感知，从而提高模型在部分遮挡情况下的检测能力。在自制烟头数据集ElectricSmoke上的实验结果显示，CBD-STOA算法的mAP50和mAP50-95相较于原始的YOLOv8n算法分别提高了2.0个百分点和4.1个百分点，同时在TinyPerson数据集上也有着不错的表现。该研究为小目标遮挡检测提供了新的思路和方法。

关键词: 电力安全, 小目标检测, 遮挡感知, 序列特征融合

Abstract: In complex power operation scenarios, cigarette butts are typically small targets and are easily occluded by other objects. Existing small object detection methods face limitations in multi-scale feature fusion and occlusion awareness, and fail to fully address the specific needs of power scenarios. To address these challenges, the paper proposes the CBD-STOA algorithm for cigarette butt detection with occlusion awareness in power scenes. Firstly, a multi-scale sequence feature fusion module (SSFF) is introduced into the neck network to improve detection accuracy for small objects. Secondly, a triple feature fusion module (TFF) is designed to reduce false positive rates in dense scenes by enhancing feature details through multi-scale feature fusion. Finally, an occlusion-aware detection head (OADHead) is developed to improve detection under partial occlusion by leveraging multi-scale spatial propagation and contextual information. Experiments on the custom ElectricSmoke dataset show that CBD-STOA achieves a 2.0 and 4.1 percentage points improvement in mAP50 and mAP50-95, respectively, compared to the original YOLOv8n algorithm, with strong performance on the TinyPerson dataset as well.

Key words: power grid security, small target detection, occlusion-aware, sequence feature fusion

田艳萍, 金淼, 陈习文, 张军, 刘莉, 余锋, 姜明华. 基于小目标遮挡感知的烟头检测算法[J]. 计算机工程与应用, 2025, 61(20): 270-280.

TIAN Yanping, JIN Miao, CHEN Xiwen, ZHANG Jun, LIU Li, YU Feng, JIANG Minghua. Cigarette Butt Detection Algorithm Based on Small Target Occlusion-Aware[J]. Computer Engineering and Applications, 2025, 61(20): 270-280.

参考文献

[1] 李明山, 韩清鹏, 张天宇, 等. 改进SSD 的安全帽检测方法[J]. 计算机工程与应用, 2021, 57(8): 192-197.
LI M S, HAN Q P, ZHANG T Y, et al. Safety helmet detection method of improved SSD[J]. Computer Engineering and App-lications, 2021, 57(8): 192-197.
[2] WANG Z Y, LI Y L, CHEN X, et al. Detecting everything in the open world: towards universal object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 11433-11443.
[3] YU F, CHEN Z Y, JIANG M H, et al. Smart clothing system with multiple sensors based on digital twin technology[J]. IEEE Internet of Things Journal, 2023, 10(7): 6377-6387.
[4] QIAO L M, ZHAO Y X, LI Z Y, et al. DeFRCN: decoupled faster R-CNN for few-shot object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 8661-8670.
[5] HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2980-2988.
[6] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[7] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2016: 21-37.
[8] TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10778-10787.
[9] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7464-7475.
[10] REDMON J, FARHADI A. YOLOv3: an incremental impr-ovement[J]. arXiv:1804.02767, 2018.
[11] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004. 10934, 2020.
[12] GE Z. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107. 08430, 2021.
[13] LIM J S, ASTRID M, YOON H J, et al. Small object detection using context and attention[C]//Proceedings of the International Conference on Artificial Intelligence in Information and Communication. Piscataway: IEEE, 2021: 181-186.
[14] LIU Z M, GAO G Y, SUN L, et al. IPG-Net: image pyramid guidance network for small object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 4422-4430.
[15] YANG C, HUANG Z H, WANG N Y. QueryDet: cascaded sparse query for accelerating high-resolution small object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 13658-13667.
[16] ZHANG H Y, WANG Y, DAYOUB F, et al. VarifocalNet: an IoU-aware dense object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 8510-8519.
[17] YU F, HUA A L, DU C H, et al. VTON-MP: multi-pose virtual try-on via appearance flow and feature filtering[J]. IEEE Transactions on Consumer Electronics, 2023, 69(4): 1101-1113.
[18] 张阳婷, 黄德启, 王东伟, 等. 基于深度学习的目标检测算法研究与应用综述[J]. 计算机工程与应用, 2023, 59(18):1-13.
ZHANG Y T, HUANG D Q, WANG D W, et al. Review on research and application of deep learning-based target detection algorithms[J]. Computer Engineering and Applications, 2023, 59(18):1-13.
[19] ZOPH B, CUBUK E D, GHIASI G, et al. Learning data augmentation strategies for object detection[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 566-583.
[20] LIU Y, SUN P, WERGELES N, et al. A survey and performance evaluation of deep learning methods for small object detection[J]. Expert Systems with Applications, 2021, 172: 114602.
[21] TALEBI H, MILANFAR P. Learning to resize images for computer vision tasks[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 487-496.
[22] JIN Z C, YU D D, SONG L C, et al. You should look at all objects[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 332-349.
[23] YU F, YU C Y, TIAN Z Y, et al. Intelligent wearable system with motion and emotion recognition based on digital twin technology[J]. IEEE Internet of Things Journal, 2024, 11(15): 26314-26328.
[24] GONG Y Q, YU X H, DING Y, et al. Effective fusion factor in FPN for tiny object detection[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 1159-1167.
[25] WANG K X, LIEW J H, ZOU Y T, et al. PANet: few-shot image semantic segmentation with prototype alignment[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 9196-9205.
[26] ZHU L, WANG X J, KE Z H, et al. BiFormer: vision Transformer with bi-level routing attention[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 10323-10333.
[27] ZHAO G M, GE W F, YU Y Z. GraphFPN: graph feature pyramid network for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 2743-2752.
[28] DU C H, YU F, JIANG M H, et al. VTON-SCFA: a virtual try-on network based on the semantic constraints and flow alignment[J]. IEEE Transactions on Multimedia, 2023, 25: 777-791.
[29] GUPTA A, CHELLAPPA R. You can run but not hide: impr-oving gait recognition with intrinsic occlusion type awareness[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2024: 5881-5890.
[30] 宁欣,田伟娟,于丽娜,等.面向小目标和遮挡目标检测的脑启发CIRA-DETR全推理方法[J].计算机学报, 2022, 45(10): 2080-2092.
NING X, TIAN W J, YU L N, et al. Brain-inspired CIRA-DETR full inference method for small and occluded object detection[J]. Journal of Computer Science, 2022, 45(10): 2080-2092.
[31] HU Y Q, NIU A X, ZHU Y, et al. Multiple object tracking based on occlusion-aware embedding consistency learning[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2024: 9521-9525.
[32] PIET J, SHARMA A, PAXSON V, et al. Network detection of interactive SSH impostors using deep learning[C]//Proceedings of the 32nd USENIX Conference on Security Symposium, 2023: 4283-4300.
[33] LEI J R, HU X B, WANG Y, et al. PyramidFlow: high-resolution defect contrastive localization using pyramid normalizing flow[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 14143-14152.
[34] DENG J K, GUO J, VERVERAS E, et al. RetinaFace: single-shot multi-level face localisation in the wild[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 5202-5211.
[35] YU F, ZHANG Y, LI H Y, et al. Phase contour enhancement network for clothing parsing[J]. IEEE Transactions on Consumer Electronics, 2024, 70(1): 2784-2793.
[36] KANG M, TING C M, TING F F, et al. ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J]. Image and Vision Computing, 2024, 147: 105057.
[37] YU Z, HUANG H, CHEN W, et al. YOLO-facev2: a scale and occlusion aware face detector[J]. arXiv:2208.02019, 2022.
[38] YU X H, GONG Y Q, JIANG N, et al. Scale match for tiny person detection[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2020: 1246-1254.
[39] DUAN K W, BAI S, XIE L X, et al. CenterNet: keypoint triplets for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 6568-6577.
[40] WANG C C, HE W, NIE Y, et al. Gold-YOLO: efficient object detector via gather-and-distribute mechanism[J]. arXiv:2309. 1131,2023.
[41] WANG C Y, YEH I H, LIAO H Y M. YOLOv9: learning what you want to learn using programmable gradient information[J]. arXiv:2402.13616, 2024.
[42] WANG A, CHEN H, LIU L, et al. YOLOv10: real-time end-to-end object detection[J]. arXiv:2405.14458, 2024.