基于多级特征和混合注意力机制的室内人群检测网络

doi:10.11772/j.issn.1001-9081.2019061075

计算机应用 ›› 2019, Vol. 39 ›› Issue (12): 3496-3502.DOI: 10.11772/j.issn.1001-9081.2019061075

基于多级特征和混合注意力机制的室内人群检测网络

沈文祥, 秦品乐, 曾建潮

中北大学大数据学院, 太原 030051

收稿日期:2019-06-24 修回日期:2019-09-19 出版日期:2019-12-10 发布日期:2019-10-15
作者简介:沈文祥(1995-),男,安徽淮南人,硕士研究生,主要研究方向:深度学习、计算机视觉;秦品乐(1978-),男,山西长治人,副教授,博士,CCF会员,主要研究方向:机器视觉、大数据、医学影像;曾建潮(1963-)男,陕西大荔县人,教授,博士,CCF会员,主要研究方向:演化计算、机器学习。
基金资助:
山西省重点研发计划项目（201803D31212-1）。

Indoor crowd detection network based on multi-level features and hybrid attention mechanism

SHEN Wenxiang, QIN Pinle, ZENG Jianchao

College of Big Data, North University of China, Taiyuan Shanxi 030051, China

Received:2019-06-24 Revised:2019-09-19 Online:2019-12-10 Published:2019-10-15
Contact: 曾建潮
Supported by:
This work is partially supported by the Shanxi Provincial Key Research and Development Plan (201803D31212-1).

摘要/Abstract

摘要： 针对室内人群目标尺度和姿态多样性、人头目标易与周围物体特征混淆的问题，提出了一种基于多级特征和混合注意力机制的室内人群检测网络（MFANet）。该网络结构包括三部分，即特征融合模块、多尺度空洞卷积金字塔特征分解模块以及混合注意力模块。首先，通过将浅层特征和中间层特征信息融合，形成包含上下文信息的融合特征，用于解决浅层特征图中小目标语义信息不丰富、分类能力弱的问题；然后，利用空洞卷积增大感受野而不增加参数的特性，对融合特征进行多尺度分解，形成新的小目标检测分支，实现网络对多尺度目标的定位和检测；最后，用局部混合注意力模块来融合全局像素关联空间注意力和通道注意力，增强对关键信息贡献大的特征，来增强网络对目标和背景的区分能力。实验结果表明，所提方法在室内监控场景数据集SCUT-HEAD上达到了0.94的准确率、0.91的召回率和0.92的F1分数，在召回率、准确率和F1指标上均明显优于当前用于室内人群检测的其他算法。

关键词: 室内人群检测, 特征融合, 注意力机制, 空洞卷积, 特征金字塔

Abstract: In order to solve the problem of indoor crowd target scale and attitude diversity and confusion of head targets with surrounding objects, a new Network based on Multi-level Features and hybrid Attention mechanism for indoor crowd detection (MFANet) was proposed. It is composed of three parts:feature fusion module, multi-scale dilated convolution pyramid feature decomposition module, and hybrid attention module. Firstly, by combining the information of shallow features and intermediate layer features, a fusion feature containing context information was formed to solve the problem of the lack of semantic information and the weakness of classification ability of the small targets in the shallow feature map. Then, with the characteristics of increasing the receptive field without increasing the parameters, the dilated convolution was used to perform the multi-scale decomposition on the fusion features to form a new small target detection branch, realizing the positioning and detection of the multi-scale targets by the network. Finally, the local fusion attention module was used to integrate the global pixel correlation space attention and channel attention to enhance the features with large contribution on the key information in order to improve the ability of distinguishing target from background. The experimental results show that the proposed method achieves an accuracy of 0.94, a recall rate of 0.91 and an F1 score of 0.92 on the indoor monitoring scene dataset SCUT-HEAD. All of these three are significantly better than those of other algorithms currently used for indoor crowd detection.

Key words: indoor crowd detection, feature fusion, attention mechanism, dilate convolution, feature pyramid

中图分类号:

沈文祥, 秦品乐, 曾建潮. 基于多级特征和混合注意力机制的室内人群检测网络[J]. 计算机应用, 2019, 39(12): 3496-3502.

SHEN Wenxiang, QIN Pinle, ZENG Jianchao. Indoor crowd detection network based on multi-level features and hybrid attention mechanism[J]. Journal of Computer Applications, 2019, 39(12): 3496-3502.

参考文献

[1] WANG Q, FAN H, SUN G, et al. Laplacian pyramid adversarial network for face completion[J]. Pattern Recognition, 2019, 88:493-505.
[2] YIN X, LIU X. Multi-task convolutional neural network for pose-invariant face recognition[J]. IEEE Transactions on Image Processing, 2018, 27(2):964-975.
[3] LU J, YUAN X, YAHAGI T. A method of face recognition based on fuzzy clustering and parallel neural networks[J]. Signal Processing, 2006, 86(8):2026-2039.
[4] ZHANG K, ZHANG Z, LI Z, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal Processing Letters, 2016, 23(10):1499-1503.
[5] CAO Y, GUAN D, HUANG W, et al. Pedestrian detection with unsupervised multispectral feature learning using deep neural networks[J]. Information Fusion, 2019, 46:206-217.
[6] JUNG S I, HONG K S. Deep network aided by guiding network for pedestrian detection[J]. Pattern Recognition Letters, 2017, 90:43-49
[7] NEUBECK A, VAN GOOL L. Efficient non-maximum suppression[C]//Proceedings of the 18th International Conference on Pattern Recognition. Piscataway:IEEE, 2006:850-855
[8] SINGH B, DAVIS L S. An analysis of scale invariance in object detection-SNIP[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:3578-3587
[9] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, LNCS 9905. Cham:Springer, 2016:21-37.
[10] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:936-944.
[11] ZHOU P, NI B, GENG C, et al. Scale-transferrable object detection[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:528-537.
[12] JADERBERG M, SIMONYAN K, ZISSERMAN A, et al. Spatial transformer networks[C]//Proceedings of the 2015 International Conference on Neural Information Processing Systems. New York:Curran Associates Inc., 2015:2017-2025.
[13] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:7132-7141.
[14] ZHANG H, GOODFELLOW I, METAXAS D, et al. Self-attention generative adversarial networks[C]//Proceedings of the 36th International Conference on Machine Learning. New York:PMLR, 2019:7354-7363.
[15] 李晓光,付陈平,李晓莉,等.面向多尺度目标检测的改进Faster R-CNN算法[J].计算机辅助设计与图形学学报,2019,31(7):1095-1101.(LI X G, FU C P, LI X L, et al. Improved faster R-CNN for multi-scale object detection[J]. Journal of Computer-Aided Design and Computer Graphics, 2019, 31(7):1095-1101.)
[16] 李静,降爱莲.复杂场景下基于R-FCN的小人脸检测研究[J/OL].计算机工程与应用:1-12[2019-04-22].http://kns.cnki.net/kcms/detail/Detail.aspx?dbname=CAPJLAST&filename=JSGG20190123006&v=. (LI J, JIANG A L. Face detection based on R-FCN in complex scenes[J/OL]. Journal of Computer Engineering and Applications:1-12[2019-04-22]. http://kns.cnki.net/kcms/detail/Detail.aspx?dbname=CAPJLAST&filename=JSGG20190123006&v=.)
[17] REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:6517-6525.
[18] LI J, LIANG X, SHEN S, et al. Scale-aware fast R-CNN for pedestrian detection[J]. IEEE Transactions on Multimedia, 2018, 20(4):985-996.
[19] SERMANET P, EIGEN D, ZHANG X, et al. OverFeat:integrated recognition, localization and detection using convolutional networks[EB/OL].[2019-04-11]. https://arxiv.org/pdf/1312.6229v4.pdf.
[20] CAI Z, FAN Q, FERIS R S, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//Proceedings of the 14th European Conference on Computer Vision, LNCS 9908. Cham:Springer, 2016:354-370.
[21] FU C, LIU W, RANGA A, TYAGI A, et al. DSSD:deconvolutional single shot detector[EB/OL].[2019-04-11]. https://arxiv.org/pdf/1701.06659.pdf.
[22] 杨康,宋慧慧,张开华.基于双重注意力孪生网络的实时视觉跟踪[J].计算机应用,2019,39(6):1652-1656.(YANG K, SONG H H, ZHANG K H. Real-time visual tracking based on dual attention Siamese network[J]. Journal of Computer Applications, 2019, 39(6):1652-1656.)
[23] QUAN Y, LI Z, ZHANG C. Object detection by combining deep dilated convolutions network and light-weight network[C]//Proceedings of the 12th International Conference on Knowledge Science, Engineering and Management, LNCS 11775. Cham:Springer, 2019:452-463.
[24] WANG P, CHEN P, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE, 2018:1451-1460.
[25] PENG D, SUN Z, CHEN Z, et al. Detecting heads using feature refine net and cascaded multi-scale architecture[C]//Proceedings of the 24th International Conference on Pattern Recognition. Piscataway:IEEE, 2018:2528-2533.

基于多级特征和混合注意力机制的室内人群检测网络

Indoor crowd detection network based on multi-level features and hybrid attention mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[2]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[3]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[6]	王伟, 赵尔平, 崔志远, 孙浩. 基于HowNet义原和Word2vec词向量表示的多特征融合消歧方法[J]. 计算机应用, 2021, 41(8): 2193-2198.
[7]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[8]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
[9]	张洋, 江铭虎. 基于注意力机制的文本作者识别[J]. 计算机应用, 2021, 41(7): 1897-1901.
[10]	武维, 李泽平, 杨华蔚, 林川, 王忠德. 融合内容特征和时序信息的深度注意力视频流行度预测模型[J]. 计算机应用, 2021, 41(7): 1878-1884.
[11]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[12]	冯兴杰, 张天泽. 基于分组卷积进行特征融合的全景分割算法[J]. 计算机应用, 2021, 41(7): 2054-2061.
[13]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[14]	吴丽丹, 薛雨阳, 童同, 杜民, 高钦泉. 基于前景语义信息的图像着色算法[J]. 计算机应用, 2021, 41(7): 2048-2053.
[15]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.