一种改进RetinaNet的室内人员检测算法

doi:10.19665/j.issn1001-2400.2019.05.010

摘要/Abstract

摘要：

由于现有的人员检测算法研究对象主要是室外直立行人,而室内人员姿态多变,且图像拍摄角度与室外行人差别较大,所以使用以往的检测方法得到的效果并不理想。基于此,笔者针对室内人员检测数据集提出了一种高精度检测模型。该模型以RetinaNet网络为基础,在残差网络中引入通道注意力模块,间接实现卷积层的随机失活,增强模型泛化能力;通过维度聚类算法找出锚点的最佳尺寸,并据此找到合适的特征图进行预测。实验表明,这种算法在室内人员检测数据集上检测精度可达99.84%,且在速度和内存占用方面也优于其他算法。

关键词: 机器视觉, 卷积神经网络, 室内人员检测

Abstract:

Human detection is of great significance in computer vision tasks such as security and human-machine interaction. In this paper, a high-precision detection model based on the indoor human detection dataset(IHDD) is proposed for indoor human detection. As the posture of the indoor staff is changeable and the image shooting angle is quite different from that of outdoor pedestrians, the model we propose makes significant improvement in the field of human detection. In this work, we integrate the Squeeze-and-Excitation module into the residual network to realize the dropout of the convolutional layer to enhance the generalization ability of the model. Meanwhile, dimension clustering is utilized to find the optimal size of anchors and the best feature map to be used in prediction. Experimental results on IHDD demonstrate that the proposed methods can reach a precision of 99.84% and outperform other algorithms in terms of speed and memory usage. It indicates that our method has a certain theoretical and practical value.

Key words: machine vision, convolutional neural nets, indoor human detection

中图分类号:

TP391

王璐璐,张为,孙琦龙. 一种改进RetinaNet的室内人员检测算法[J]. 西安电子科技大学学报, 2019, 46(5): 69-74.

WANG Lulu,ZHANG Wei,SUN Qilong. Indoor human detection algorithm based on the improved retinaNet[J]. Journal of Xidian University, 2019, 46(5): 69-74.

图/表 7

图1

图2

图3

图4

表1

图5

表2

参考文献 15

[1]	CAI Z, SABERIAN M, VASCONCELOS N. Learning Complexity-aware Cascades for Deep Pedestrian Detection[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 3361-3369.
[2]	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]// Proceedings of the 2014 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2014: 580-587.
[3]	GIRSHICK R.( 2015) Fast R-CNN[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448.
[4]	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.
[5]	ZHANG L L, LIN L, LIANG X D, et al. Is Faster R-CNN Doing Well for Pedestrian Detection?[C]// Lecture Notes in Computer Science: 9906. Cham: Springer, 2016: 443-457.
[6]	YANG D, ZHANG J, XU S , et al. Real-time Pedestrian Detection via Hierarchical Convolutional Feature[J]. Multimedia Tools and Applications, 2018,77(19):25841-25860.
[7]	LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot MultiBox Detector[C]// Lecture Notes in Computer Science: 9905. Heidelberg: Springer Verlag, 2016: 21-37.
[8]	王霞, 张为 . 基于联合学习的多视角室内人员检测网络[J]. 光学学报, 2019,39(2):78-88.
	WANG Xia, ZHANG Wei . Multi-view Indoor Human Detection Neural Network Based on Joint Learning[J]. Acta Optica Sinica, 2019,39(2):78-88.
[9]	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection[C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[10]	HU J, SHEN L, SUN G . Squeeze-and-excitation Networks[C]// Proceedings of the 2018 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2018: 7132-7141.
[11]	LIN T Y, DOLLÁR P, GIRSHICK R, . et al. Feature Pyramid Networks for Object Detection [C]//Proceedings of the 2017 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944.
[12]	HINTON G E, SRIVASTAVA N, KRIZHEVSKY A , et al. Improving Neural Networks by Preventing Co-adaptation of Feature Detectors[J]. Computer Science, 2012,3(4):212-223.
[13]	REDMON J, FARHADI A . YOLO9000: Better, Faster, Stronger[C]// Proceedings of the 2017 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525.
[14]	ARTHUR D, VASSILVITSKII S . K-means++: the Advantages of Careful Seeding[C]// Proceedings of the 2007 Annual ACM-SIAM Symposium on Discrete Algorithms. New York: ACM, 2007: 1027-1035.
[15]	OUYANG W, WANG X . Joint Deep Learning for Pedestrian Detection[C]// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2013: 2056-2063.

算法	精度	漏检率
文献[15]	75.52	28.840
文献[4]	84.82	17.290
文献[8]	87.34	14.660
文献[9]	98.61	0.050
文中	99.84	0.045

算法	速度/ (ms·image^-1)	内存/ (MB·image^-1)
文献[4]	221	3 279
文献[9]	144	1 081
文中	54	1 077