面向拥挤行人检测的改进YOLOv7算法

doi:10.19678/j.issn.1000-3428.0067741

摘要/Abstract

摘要：

针对拥挤行人检测场景下检测算法容易产生漏检与误检的问题，提出一种改进的YOLOv7拥挤行人检测算法。在骨干网络中引入BiFormer视觉变换器和改进的高效层聚合网络(RC-ELAN)模块，通过自注意力机制与注意力模块使骨干网络更多聚焦于被遮挡行人的重要特征，有效缓解了目标特征缺失对检测造成的负面影响。采用基于双向特征金字塔网络思想的改进颈部网络，通过转置卷积和改进的Rep-ELAN-W模块使模型可以高效利用中低维特征图中的小目标特征信息，有效提升了模型的小目标行人检测性能。引入高效的完全交并比损失函数，使模型可以进一步收敛至更高精度。在含有大量小目标遮挡行人的WiderPerson数据集上的实验结果表明，与YOLOv7、YOLOv5、YOLOX算法相比，改进的YOLOv7算法的交并比阈值分别取0.5和0.5~0.95时的平均精准度提升了2.5和2.8、9.9和7.1、12.3和10.7个百分点，可较好地应用于拥挤行人检测场景。

关键词: 机器视觉, 拥挤行人检测, 注意力机制, YOLO系列算法, 双向特征金字塔网络

Abstract:

Aiming at the problem that the detection algorithm is prone to omission and false detection in crowded pedestrian detection scenarios, this study proposes an improved YOLOv7 crowded pedestrian detection algorithm. Introducing a BiFormer visual transformer and an improved RepConv and Channel Space Attention Module (CSAM)-based Efficient Layer Aggregation Network (RC-ELAN) module in the backbone network, the self-attention mechanism and the attention module enable the backbone network to focus more on the important features of the occluded pedestrians, effectively mitigating the adverse effects of the missing target features on the detection. The improved neck network based on the idea of a Bidirectional Feature Pyramid Network (BiFPN) is used, and the transposed convolution and improved Rep-ELAN-W module enable the model to efficiently utilize the small-target feature information in the middle and low-dimensional feature maps, effectively improving the small-target pedestrian detection performance of the model. The introduction of an Efficient Complete Intersection-over-Union (E-CIoU) loss function allows the model to further converge to a higher accuracy. Experimental results on the WiderPerson dataset containing a large number of small target-obscuring pedestrians demonstrate that the average accuracies of the improved YOLOv7 algorithm when the IoU thresholds are set to 0.5 and 0.5-0.95 are improved by 2.5 and 2.8, 9.9 and 7.1, and 12.3 and 10.7 percentage points compared with the YOLOv7, YOLOv5, and YOLOX algorithms, respectively, which can be better applied to crowded pedestrian detection scenarios.

Key words: machine vision, crowded pedestrian detection, attention mechanism, YOLO series algorithms, Bi-directional Feature Pyramid Network(BiFPN)

徐芳芯, 樊嵘, 马小陆. 面向拥挤行人检测的改进YOLOv7算法[J]. 计算机工程, 2024, 50(3): 250-258.

Fangxin XU, Rong FAN, Xiaolu MA. Improved YOLOv7 Algorithm for Crowded Pedestrian Detection[J]. Computer Engineering, 2024, 50(3): 250-258.

http://www.ecice06.com/CN/Y2024/V50/I3/250

图/表 14

图1 YOLOv7网络结构

Fig.1 YOLOv7 network structure

图2 BiFormer模块结构

Fig.2 BiFormer module structure

图3 通道空间注意力模块结构

Fig.3 Channel space attention module structure

图4 RC-ELAN模块结构

Fig.4 RC-ELAN module structure

图5 Rep-ELAN-W模块结构

Fig.5 Rep-ELAN-W module structure

图6 改进的骨干网络结构

Fig.6 Improved backbone network structure

图7 BiFPN结构

Fig.7 BiFPN structure

图8 转置卷积原理

Fig.8 Transposed convolution principle

图9 改进的颈部网络结构

Fig.9 Improved neck network structure

图10 改进的YOLOv7网络结构

Fig.10 Improved YOLOv7 network structure

图11 检测效果对比

Fig.11 Comparison of detection effects

参考文献 32

1	XU M M, BAI Y C, QU S S, et al. Semantic part RCNN for real-world pedestrian detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington D. C., USA: IEEE Press, 2019: 45-54.
2	HOU Y, ZHENG L, GOULD S. Multiview detection with feature perspective transformation[C]//Proceedings of the 16th European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 1-18.
3	李颀, 王娇, 邓耀辉. 基于遮挡感知的行人检测与跟踪算法. 传感器与微系统, 2023, 42(4): 126- 130. URL
	LI Q, WANG J, DENG Y H. Pedestrian detection and tracking algorithm based on occlusion-aware. Transducer and Microsystem Technologies, 2023, 42(4): 126- 130. URL
4	ZHANG S F, WEN L Y, BIAN X, et al. Occlusion-aware R-CNN: detecting pedestrians in a crowd[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 657-674.
5	刘毅, 于畅洋, 李国燕, 等. UAST-RCNN: 遮挡行人的目标检测算法. 电子测量与仪器学报, 2022, 36(12): 168- 175. URL
	LIU Y, YU C Y, LI G Y, et al. UAST-RCNN: object detection algorithm for blocking pedestrians. Journal of Electronic Measurement and Instrumentation, 2022, 36(12): 168- 175. URL
6	XU C, WANG J W, YANG W, et al. RFLA: Gaussian receptive field based label assignment for tiny object detection[C]//Proceedings of the 17th European Conference Computer Vision. Berlin, Germany: Springer, 2022: 526-543.
7	ZHAO Q J, SHENG T, WANG Y T, et al. M2Det: a single-shot object detector based on multi-level feature pyramid network[C]//Proceedings of AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 9259-9266.
8	黄凤琪, 陈明, 冯国富. 基于可变形卷积的改进YOLO目标检测算法. 计算机工程, 2021, 47(10): 269-275, 282. doi: 10.19678/j.issn.1000-3428.0059096
	HUANG F Q, CHEN M, FENG G F. Improved YOLO object detection algorithm based on deformable convolution. Computer Engineering, 2021, 47(10): 269-275, 282. doi: 10.19678/j.issn.1000-3428.0059096
9	樊嵘, 马小陆. 面向拥挤行人检测的改进DETR算法. 计算机工程与应用, 2023, 59(19): 159- 165. URL
	FAN R, MA X L. Improved DETR for crowded pedestrian detection. Computer Engineering and Applications, 2023, 59(19): 159- 165. URL
10	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[EB/OL]. [2023-04-11]. https://arxiv.org/abs/2207.02696.
11	ZHU L, WANG X J, KE Z H, et al. BiFormer: vision transformer with bi-level routing attention[EB/OL]. [2023-04-11]. https://arxiv.org/abs/2303.08810.
12	TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2020: 10781-10790.
13	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 3-19.
14	CHEN X L, LIAN Q W, CHEN X L, et al. Surface crack detection method for coal rock based on improved YOLOv5. Applied Sciences, 2022, 12(19): 9695. doi: 10.3390/app12199695
15	ZHANG S F, XIE Y L, WAN J, et al. WiderPerson: a diverse dataset for dense pedestrian detection in the wild. IEEE Transactions on Multimedia, 2020, 22(2): 380- 393. doi: 10.1109/TMM.2019.2929005
16	BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2023-04-11]. https://arxiv.org/abs/2004.10934.
17	王金鹏, 周佳良, 张跃跃, 等. 基于优选YOLOv7模型的采摘机器人多姿态火龙果检测系统. 农业工程学报, 2023,(8): 276- 283. URL
	WANG J P, ZHOU J L, ZHANG Y Y, et al. A multi-pose dragon fruit detection system for picking robot based on the optimal YOLOv7 model. Transactions of the Chinese Society of Agricultural Engineering, 2023,(8): 276- 283. URL
18	GLENN J, AYUSH E, ALEX S, et al. ultralytics/yolov5[EB/OL]. [2023-04-11]. https://github.com/ultralytics/yolov5.
19	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 8759-8768.
20	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL]. [2023-04-11]. https://arxiv.org/abs/2010.11929.
21	DING X H, ZHANG X Y, MA N N, et al. RepVGG: making VGG-style ConvNets great again[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2021: 13733-13742.
22	ZOPH B, LE Q V. Neural architecture search with reinforcement learning[EB/OL]. [2023-04-11]. https://arxiv.org/abs/1611.01578.
23	ZHENG Z H, WANG P, REN D W, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Transactions on Cybernetics, 2022, 52(8): 8574- 8586. doi: 10.1109/TCYB.2021.3095305
24	ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IoU loss for accurate bounding box regression. Neurocomputing, 2022, 506, 146- 157. doi: 10.1016/j.neucom.2022.07.042
25	CHEN K, WANG J, PANG J, et al. MMDetection: open MMLab detection toolbox and benchmark[EB/OL]. [2023-04-11]. https://arxiv.org/abs/1906.07155.
26	KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. [2023-04-11]. https://arxiv.org/abs/1412.6980.
27	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of ECCV'16. Berlin, Germany: Springer, 2016: 21-37.
28	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2980-2988.
29	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
30	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-04-11]. https://arxiv.org/abs/1804.02767.
31	GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. [2023-04-11]. https://arxiv.org/abs/2107.08430.
32	NEUBECK A, VAN GOOL L. Efficient non-maximum suppression[C]//Proceedings of the 18th International Conference on Pattern Recognition. Washington D. C., USA: IEEE Press, 2006: 850-855.

[1]	赵佳圆, 张玉茹, 苏晓东, 徐红岩, 李世洲, 张玉荣. 基于注意力机制的人体关键点隐式建模网络[J]. 计算机工程, 2024, 50(3): 317-325.
[2]	谢新林, 尹东旭, 张涛源, 谢刚. 基于注意力机制的多尺度融合人群计数算法[J]. 计算机工程, 2024, 50(3): 290-297.
[3]	袁文涛, 卫文韬, 高德民. 融合注意力机制的多视图卷积手势识别研究[J]. 计算机工程, 2024, 50(3): 208-215.
[4]	赵博超, 马嘉骏, 崔磊, 栾文鹏, 朱静. 基于改进VMD-XGBoost-BiLSTM组合模型的光伏发电异常检测[J]. 计算机工程, 2024, 50(3): 306-316.
[5]	徐浩宸, 刘满华. 基于多层次自注意力网络的人脸特征点检测[J]. 计算机工程, 2024, 50(2): 239-246.
[6]	刘帅威, 李智, 王国美, 张丽. 基于Transformer和GAN的对抗样本生成算法[J]. 计算机工程, 2024, 50(2): 180-187.
[7]	王正家, 胡飞飞, 张成娟, 雷卓, 何涛. 引入轻量级Transformer的自适应窗口立体匹配算法[J]. 计算机工程, 2024, 50(2): 256-265.
[8]	郭祥振, 李思潼, 卢锐, 郭森, 崔学荣, 杨钢. 基于多任务联合注意力的结肠息肉分割网络[J]. 计算机工程, 2024, 50(2): 327-336.
[9]	丁国辉, 刘宇琪, 王言开, 耿施展, 姜天昊. 基于翻转网络的低相关性序列数据预测研究[J]. 计算机工程, 2024, 50(2): 78-90.
[10]	圣文顺, 余熊峰, 林佳燕, 陈欣. 融合注意力与特征金字塔的小尺度目标检测算法[J]. 计算机工程, 2024, 50(1): 242-250.
[11]	吴志强, 解庆, 李琳, 刘永坚. 基于多模态融合的图神经网络推荐算法[J]. 计算机工程, 2024, 50(1): 91-100.
[12]	申秀雨, 姬伟峰, 李映岐, 吴玄. 面向边缘计算的TCA1C DDoS检测模型[J]. 计算机工程, 2024, 50(1): 198-205.
[13]	杨瑞君, 秦晋京, 程燕. 基于生成对抗网络的自然场景低照度增强模型[J]. 计算机工程, 2024, 50(1): 279-288.
[14]	徐晓峰, 黄韫栀, 徐军. 基于各向异性注意力的双分支血管分割模型[J]. 计算机工程, 2024, 50(1): 348-356.
[15]	杨静, 陆铭华, 马洁琼, 吴金平, 刘星璇. 基于交替循环神经网络的水下防御态势预测方法[J]. 计算机工程, 2023, 49(9): 69-78.

选择文件类型/文献管理软件名称

选择包含的内容