改进SSD特征融合的目标检测算法研究

doi:10.3778/j.issn.1002-8331.2212-0370

摘要/Abstract

摘要： 针对目标检测在复杂环境下存在漏检和误检问题，提出一种在SSD（single shot multibox detector）算法中引入RFB（receptive field block）模块的方法，采用将Conv4_3、FC7、Conv8_2三个浅特征层进行特征连接的融合策略来检测小物体。加入空洞卷积层提高感受并获取更多目标尺度信息，利用网络结构连接浅层特征。在后三个深特征层Conv9_2、Conv10_2、Conv11_2中使用反卷积模块进行特征融合，生成新的Conv9_2和新的Conv10_2，使用RFB模块减少参数计算来检测物体。经过NMS（non-maximum suppression）处理进行目标检测的分类与回归。在PASCAL VOC2007、CSV和COCO2017数据集上的实验结果表明，该算法的检测精度得到了提升，其mAP相比DSSD（deconvolutional SSD）提升6.6个百分点，比SSD提升12.1个百分点，检测速度为49.1?FPS，同时对复杂环境具有良好的鲁棒性以及实时检测能力。

关键词: 目标检测, SSD, 特征连接, 特征融合

Abstract: Aiming at the problems of missing detection and false detection in complex environment, a RFB（receptive field block） module is introduced into the algorithm of SSD（single shot multibox detector）. Small objects are detected by the fusion strategy of Conv4_3, FC7 and Conv8_2 with three shallow feature layers. Hollow convolution layer is added to improve perception and obtain more target scale information. Network structure is used to connect shallow features. In the last three deep feature layers, Conv9_2, Conv10_2 and Conv11_2, deconvolution module is used to form new Conv9_2 and Conv10_2 by feature fusion, and RFB module is used to reduce parameter calculation to detect objects. Finally, the classification and regression of target detection are carried out through NMS（non-maximum suppression）. The experimental results on PASCAL VOC2007, CSV and COCO2017 datasets show that the detection accuracy of this algorithm has been improved. mAP is improved by 6.6 percentage points compared with DSSD（deconvolutional SSD）, 12.1 percentage points compared with SSD, and the speed is 49.1 FPS. At the same time, it has good robustness and real-time detection ability for complex environment.

Key words: object detection, SSD, connection of features, feature fusion

葛海波, 李强, 周婷, 黄朝锋. 改进SSD特征融合的目标检测算法研究[J]. 计算机工程与应用, 2023, 59(22): 193-201.

GE Haibo, LI Qiang, ZHOU Ting, HUANG Chaofeng. Research on Target Detection Algorithm Based on Improved SSD Feature Fusion[J]. Computer Engineering and Applications, 2023, 59(22): 193-201.

参考文献

[1] LI B，JIANG W，GU J，et al.Research on target detection algorithm based on deep learning technology[C]//Proceedings of the 2021 IEEE International Conference on Power Electronics，Computer Applications，Shenyang，2021：137-142.
[2] REN S，HE K，GIRSHICK R，et al.Farter R-CNN：towards real-time object-detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39（6）：1137-1149.
[3] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision.Cham：Springrer，2016：21-37.
[4] WANG S，WU W.Optical fiber defect detection method based on DSSD network[C]//Proceedings of the 2019 IEEE International Conference on Smart Internet of Things，2019.
[5] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[6] CHEN Z，WU K，LI Y，et al.SSD-MSN：an improved multi-scale object detection network based on SSD[J].IEEE Access，2019，7：80622-80632.
[7] FAN D，LIU D，CHI W，et al.Improved SSD-based multi-scale pedestrian detection algorithm[C]//Advances in 3D Image and Graphics Representation，Analysis，Computing and Information Technology：Algorithms and Applications，Volume 2.Singapore：Springer，2020：109-118.
[8] FU C Y，LIU W，RANGA A，et al.DSSD：deconvolutional single shot detector[J].arXiv：1701.06659，2017.
[9] JISOO J，HYOJIN P，NOJUN K，et al.Enhancement of SSD by concatenating feature maps for object detection[C]//Proceedings of the 28th British Machine Vision Conference，2017：1286-1291.
[10] LI Z，ZHOU F.FSSD：feature fusion single shot multibox detector[J].arXiv：1712.00960，2017.
[11] LIU S，HUANG D.Receptive field block net for acurate and fast object detection[C]//Proceedings of the 15th European Conference on Computer Vision，Munich，2018：404-419.
[12] YANG J，HE W Y，ZHANG T，et al.Research on subway pedestrian detection algorithms based on SSD model[J].IET Intelligent Transport Systems，2020，14：7553.
[13] 张馨月，降爱莲.融合特征增强和自注意力的SSD小目标检测算法[J].计算机工程与应用，2022，58（5）：247-255.
JIANG A L，ZHANG X Y.SSD small target detection algorithm combining feature enhancement and self-attention[J].Computer Engineering and Applications，2022，58（5）：247-255.
[14] 王燕妮，余丽仙.注意力与多尺度有效融合的SSD目标检测算法[J].计算机科学与探索，2022，16（2）：438-447.
WANG Y N，YU L X.SSD object detection algorithm with effective fusion of attention and multi-scale[J].Journal of Frontiers of Computer Science and Technology，2022，16（2）：438-447.
[15] 陈家栋，雷斌.基于改进SSD轻量化的交通路口目标检测[J].传感器与微系统，2022，41（10）：117-121.
CHEN J D，LEI B.Traffic intersection target detection based on improved SSD lightweight[J].Transducer and Microsystem Technologies，2022，41（10）：117-121.
[16] 何丽，张红艳，房婉琳.融合多尺度边界特征的显著实例分割[J].计算机科学与探索，2022，16（8）：1865-1876.
HE L，ZHANG H Y，FANG W L.Salient instance segmentation via multiscale boundary characteristic network[J].Journal of Frontiers of Computer Science and Technology，2022，16（8）：1865-1876.
[17] LIU W，ANGUELOV D，ERHAN S，et al.SSD：single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision，Amsterdam，Oct 11-14，2016.Cham：Springer，2016：21-37.
[18] EVERINGHAM M，VAN G L，WILLIAMS C K I，et al.The pascal visual object classes （voc） challenge[J].International Journal of Computer Vision，2010，88：303-338.
[19] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[20] WANG C Y，BOCHKOVSKIY，LIAO H Y M.YOLOv7：trainable bag-of-freebies sets new state-of-the-art for realtime object detectors[J].arXiv：2207.02696，2022.
[21] 朱炳宇，刘朕，张景祥.融合Grad-CAM和卷积神经网络的COVID-19检测算法[J].计算机科学与探索，2022，16（9）：2108-2120.
ZHU B Y，LIU Z，ZHANG J X.COVID-19 detection algorithm combining Grad-CAM and convolutional neural network[J].Journal of Frontiers of Computer Science and Technology，2022，16（9）：2108-2120.
[22] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal net works[C]//Advances in Neural Information Processing Systems 28.Cambridge：MIT Press，2015：91-99.
[23] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition，Las Vegas，2016：779-788.