多尺度融合与FMB改进的YOLOv8异常行为检测方法

doi:10.3778/j.issn.1002-8331.2401-0240

摘要/Abstract

摘要： 针对异常行为检测目标面临多尺度变化、易漏检误检以及复杂背景干扰等问题，提出了一种多尺度特征融合与快速多交叉结构改进的行人异常行为检测方法。该方法以YOLOv8为基线网络，在模型主干部分设计了快速多交叉结构提升上下文信息感知能力并减少网络参数，提出空间递进卷积池化模块实现多尺度信息融合，降低尺度差异带来的易漏检误检问题，提高检测的准确度；在模型颈部中引入SimAM注意力机制抑制复杂背景干扰，提升目标检测性能；最后采用WIoU损失函数平衡检测锚框的惩戒力度增强模型泛化性能。所提方法在UCSD-Ped1、UCSD-Ped2数据集进行验证，并在OPIXray数据集进行了泛化性测试。结果表明，所提方法异常行为识别精度较诸多先进检测算法均有不同程度的提升，且参数量更小，是一种性能较为优异的行人异常行为检测方法。

关键词: 异常行为检测, YOLOv8, 空间递进卷积池化（S-PCP）, 快速多交叉结构（FMB）

Abstract: To resolve the problems of anomaly behavior detection including multi-scale variations, miss and false detection, and complex background interference, a method is proposed by incorporating the fusion of multi-scale features and fast multi-cross block (FMB) for anomaly behavior detection. Based on YOLOv8 as the baseline network, a FMB has been designed in the backbone to enhance context information awareness and reduce network parameters. Meanwhile, a spatial-progressive convolution pooling (S-PCP) module has been proposed to achieve multi-scale information fusion, thereby reducing the issues of miss and false detection caused by scale differences and improving detection accuracy. A SimAM attention mechanism has been introduced in the neck to suppress complex background interference and improve object detection performance. And WIoU has been used to balance the penalty force on anchor boxes, enhancing the model’s generalization performance. The proposed method has been extensively validated on the UCSD-Ped1 and UCSD-Ped2 datasets, and its generalization has been tested on the OPIXray dataset. The results indicate that the proposed method with fewer parameters achieves different improvements in anomaly behavior recognition accuracy compared to many advanced detection algorithms, demonstrating an excellent detection method for pedestrian anomaly behavior.

Key words: anomaly behavior detection, YOLOv8, spatial-progressive convolution pooling (S-PCP), fast multi-cross block (FMB)

石洋宇, 左景, 谢承杰, 郑棣文, 卢树华. 多尺度融合与FMB改进的YOLOv8异常行为检测方法[J]. 计算机工程与应用, 2024, 60(9): 101-110.

SHI Yangyu, ZUO Jing, XIE Chengjie, ZHENG Diwen, LU Shuhua. Improved YOLOv8 Method for Anomaly Behavior Detection with Multi-Scale Fusion and FMB[J]. Computer Engineering and Applications, 2024, 60(9): 101-110.

参考文献

[1] RISTEA N C, MADAN N, IONESCU R T, et al. Self-supervised predictive convolutional attentive block for anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 13576-13586.
[2] LIU W, CHANG H, MA B, et al. Diversity-measurable anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12147-12156.
[3] PANG G, SHEN C, CAO L, et al. Deep learning for anomaly detection: a review[J]. ACM Computing Surveys (CSUR), 2021, 54(2): 1-38.
[4] CHALAPATHY R, CHAWLA S. Deep learning for anomaly detection: a survey[J]. arXiv:1901.03407, 2019.
[5] 张晓平, 纪佳慧, 王力, 等. 基于视频的人体异常行为识别与检测方法综述[J]. 控制与决策, 2022, 37(1): 14-27.
ZHANG X P, JI J H, WANG L, et al. Overview of video based human abnormal behavior recognition and detection methods[J]. Control and Decision, 2022, 37(1): 14-27.
[6] REISS T, HOSHEN Y. Attribute-based representations for accurate and interpretable video anomaly detection[J]. arXiv:2212.00789, 2022.
[7] PARK H, NOH J, HAM B. Learning memory-guided normality for anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 14372-14381.
[8] RAVANBAKHSH M, NABI M, SANGINETO E, et al. Abnormal event detection in videos using generative adversarial nets[C]//2017 IEEE International Conference on Image Processing (ICIP), 2017: 1577-1581.
[9] LV H, CHEN C, CUI Z, et al. Learning normal dynamics in videos with meta prototype network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 15425-15434.
[10] HASAN M, CHOI J, NEUMANN J, et al. Learning temporal regularity in video sequences[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 733-742.
[11] LI Y J, DAI Z J. Abnormal behavior detection in crowd scene using YOLO and Conv-AE[C]//2021 33rd Chinese Control and Decision Conference (CCDC), 2021: 1720-1725.
[12] LIU W, LUO W, LIAN D, et al. Future frame prediction for anomaly detection—a new baseline[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 6536-6545.
[13] DONG F, ZHANG Y, NIE X. Dual discriminator generative adversarial network for video anomaly detection[J]. IEEE Access, 2020, 8: 88170-88176.
[14] ZAHEER M Z, MAHMOOD A, KHAN M H, et al. Generative cooperative learning for unsupervised video anomaly detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 14744-14754.
[15] LEE S, KIM H G, RO Y M. BMAN: bidirectional multi-scale aggregation networks for abnormal event detection[J]. IEEE Transactions on Image Processing, 2019, 29: 2395-2408.
[16] ULLAH W, HUSSAIN T, ULLAH F U M, et al. TransCNN: hybrid CNN and transformer mechanism for surveillance anomaly detection[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106173.
[17] GEORGESCU M I, BARBALAU A, IONESCU R T, et al. Anomaly detection in video via self-supervised and multi-task learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 12742-12752.
[18] JI H, ZENG X, LI H, et al. Human abnormal behavior detection method based on T-TINY-YOLO[C]//Proceedings of the 5th International Conference on Multimedia and Image Processing, 2020: 1-5.
[19] 徐守坤, 顾佳楠, 庄丽华, 等. 基于两阶段计算Transformer的小目标检测[J]. 计算机科学与探索, 2023, 17(12): 2967-2983.
XU S K, GU J N, ZHUANG L H, et al. Small object detection based on two-stage calculation transformer[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(12): 2967-2983.
[20] GLENN J, AYUSH C, LAUGHING, et al. ultralytics/ultralytics-main[EB/OL]. [2023-01-10]. https://github.com/ultralytics/ultralytics.
[21] YANG L, ZHANG R Y, LI L, et al. Simam: a simple, parameter-free attention module for convolutional neural networks[C]//International Conference on Machine Learning, 2021: 11863-11874.
[22] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[23] 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.
[24] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
[25] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 12021-12031.
[26] MAHADEVAN V, LI W, BHALODIA V, et al. Anomaly detection in crowded scenes[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA: IEEE, 2010: 1975-1981.
[27] TAO R, WEI Y, LI H, et al. Over-sampling de-occlusion attention network for prohibited items detection in noisy x-ray images[J]. arXiv:2103.00809, 2021.
[28] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, October 11-14, 2016. [S.l.]: Springer International Publishing, 2016: 21-37.
[29] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[30] ZHENG Z, YE R, WANG P, et al. Localization distillation for dense object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 9407-9416.
[31] YANG Z, LI Z, JIANG X, et al. Focal and global knowledge distillation for detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 4643-4652.
[32] CHEN F, ZHANG H, HU K, et al. Enhanced training of query-based object detection via selective query recollection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 23756-23765.
[33] GLENN J, AYUSH C, JIRKA B, et al. ultralytics/yolov5: v6.1-YOLOv5[EB/OL]. [2022-02-22]. https://github.com/ultralytics/yolov5.
[34] WANG C Y, BOCHKOVSKIY A, LIAO H Y 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, 2023: 7464-7475.
[35] TAO R, WEI Y, JIANG X, et al. Towards real-world X-ray security inspection: a high-quality benchmark and lateral inhibition module for prohibited items detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 10923-10932.
[36] WANG M, DU H, MEI W, et al. Material-aware cross-channel interaction attention (MCIA) for occluded prohibited item detection[J]. The Visual Computer, 2023, 39: 2865-2877.
[37] WEI Y, WANG Y, SONG H. CFPA-Net: cross-layer feature fusion and parallel attention network for detection and classification of prohibited items in x-ray baggage images[C]//2021 IEEE 7th International Conference on Cloud Computing and Intelligent Systems (CCIS), 2021: 203-207.
[38] 董乙杉, 郭靖圆, 李明泽, 等. 基于反向瓶颈和LCBAM设计的X光违禁品检测[J]. 计算机科学与探索, 2024, 18(5):1259-1270.
DONG Y S, GUO J Y, LI M Z, et al. X-ray prohibited items detection based on inverted bottleneck and light convolution block attention module[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(5): 1259-1270.
[39] 孙嘉傲, 董乙杉, 郭靖圆, 等. 自适应与多尺度特征融合的X光违禁品检测[J]. 计算机工程与应用, 2024, 60(2): 96-102.
SUN J A, DONG Y S, GUO J Y, et al. Detection of X-ray contraband by adaptive and multi-scale feature fusion[J]. Computer Engineering and Applications, 2024, 60(2): 96-102.
[40] 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, 2020: 12993-13000.
[41] ZHANG Y F, REN W, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146-157.
[42] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.