[1]余 进,史燕中,王春华,等.一种轻量化目标检测算法研究[J].计算机技术与发展,2020,30(11):42-47.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
　YU Jin,SHI Yan-zhong,WANG Chun-hua,et al.Research of a Lightweight Object Detection Algorithm[J].,2020,30(11):42-47.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
点击复制

一种轻量化目标检测算法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年11期
页码:
42-47
栏目:
智能、算法、系统工程
出版日期:
2020-11-10

文章信息/Info

Title:
Research of a Lightweight Object Detection Algorithm
文章编号:
1673-629X(2020)11-0042-06
作者:
余 进1; 2; 史燕中3; 王春华2; 赵 倩2; 吴 蔚2
1. 中国航天科工集团第二研究院,北京 100039; 2. 北京航天长峰科技工业集团有限公司,北京 100039; 3. 北京航天长峰股份有限公司,北京 100039
Author(s):
YU Jin1; 2; SHI Yan-zhong3; WANG Chun-hua2; ZHAO Qian2; WU Wei2
1. 2nd Institute of China Aerospace Science & Industry Corp,Beijing 100039,China; 2. Changfeng Science Technology Industry Group Corp,Beijing 100039,China; 3. Beijing Aerospace Changfeng Co. ,Ltd. ,Beijing 100039,China
关键词:
深度学习; 目标检测; 轻量化; 深度可分离卷积; YOLOv3
Keywords:
deep learning; object detection; lightweight; depthwise separable convolutions; YOLOv3
分类号:
TP301. 6
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 11. 008
摘要:
基于深度卷积神经网络的目标检测算法对硬件的计算性能要求很高, 难以部署在一些嵌入式设备和移动终端中, 而当前的一些轻量化分类算法没有针对目标检测任务的特点进行网络结构设计。针对这一问题,借鉴深度可分离卷积的思路,通过引入多尺度的特征融合模块,设计了一个针对目标检测任务的轻量化特征提取网络 TinyNet,进而提高了轻量化特征提取网络对不同尺度目标的适应性。 结合当前性能较好的 YOLOv3 目标检测框架,用 TinyNet 取代 YOLOv3 的特征提取网络,并利用轻量化模块进一步优化 YOLOv3 的检测子网络,得到一个轻量化的目标检测模型 Tiny-YOLOv3+。实验结果表明,相比于使用其他轻量化特征提取网络设计的 YOLOv3,Tiny-YOLOv3+在检测精度有所提升的基础上,大大地降低了原模型的参数量,明显提升了检测速度,有效提高了轻量化检测模型的性能和效率。
Abstract:
Detectors based on deep convolutional neural networks which demand hardware of high performance computing capability are difficult to operate on embedded devices and mobile terminals. In addition,recent networks structure design of lightweight models for classification have no consideration of the feature of object detectors. To address this issue,a lightweight feature extraction network TinyNet for target detection task is designed by using the idea of deep separable convolution as reference and introducing the multi-scale feature fusion module, so as to improve the adaptability of the lightweight feature extraction network to targets of different scales. Combining with the current YOLOv3 target detection framework with better performance,the feature extraction network of YOLOv3 is replaced by TinyNet and the detection sub-network of YOLOv3 is further optimized by the lightweight module to obtain a lightweight target detection model Tiny-YOLOv3+. The experiment shows that compared with YOLOv3,which uses other lightweight features to extract network design,Tiny-YOLOv3+,on the basis of improved detection accuracy, greatly reduces the number of parameters of the original model,significantly improves the detection speed and effectively improves the performance and efficiency of the lightweight detection model.

相似文献/References:

[1]刘晓明 李毓蕙 高燕 郑华强.基于目标区域清晰显示的H.264编码策略[J].计算机技术与发展,2010,(06):29.
　LIU Xiao-ming,LI Yu-hui,GAO Yan,et al.A Coding Strategy of H.264 Based on High-definition Display of Target Region[J].,2010,(11):29.
[2]刘翔 吴谨 祝愿博 康晓晶.基于视频序列的目标检测与跟踪技术研究[J].计算机技术与发展,2009,(11):179.
　LIU Xiang,WU Jin,ZHU Yuan-bo,et al.A Study of Object Detecting and Tracking Based on Video Sequences[J].,2009,(11):179.
[3]曙光 张超 蔡则苏.基于改进的混合高斯模型的目标检测方法[J].计算机技术与发展,2012,(07):60.
　SHU Guang,ZHANG Chao,CAI Ze-su.Target Detection Method Based on Improved Gaussian Mixture Model[J].,2012,(11):60.
[4]刘洁,李目,周少武.一种混沌混合粒子群优化RBF神经网络算法[J].计算机技术与发展,2013,(08):181.
　LIU Jie[],LI Mu[],ZHOU Shao-wu[].An Algorithm of Chaotic Hybrid Particle Swarm Optimization Based on RBF Neural Network[J].,2013,(11):181.
[5]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
　JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(11):37.
[6]卢官明,衣美佳. 步态识别关键技术研究[J].计算机技术与发展,2015,25(07):100.
　LU Guan-ming,YI Mei-jia. Research on Critical Techniques in Gait Recognition[J].,2015,25(11):100.
[7]高翔,朱婷婷,刘洋. 多摄像头系统的目标检测与跟踪方法研究[J].计算机技术与发展,2015,25(07):221.
　GAO Xiang,ZHU Ting-ting,LIU Yang. Research of Target Detection and Tracking Method for Multi-camera System[J].,2015,25(11):221.
[8]章文洁[][],黄旻[],张桂峰[]. 滤光片多光谱成像中运动目标场景误配准修正[J].计算机技术与发展,2016,26(01):18.
　ZHANG Wen-jie[][],HUANG Min[],ZHANG Gui-feng[]. Misregistration Correction for Moving Object Scene in Filter-type Multispectral Imaging[J].,2016,26(11):18.
[9]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(11):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[10]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(11):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[11]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(11):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[12]丁洪金,宫法明.基于时序分析的人体活动状态识别与定位[J].计算机技术与发展,2019,29(04):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
　DING Hong-jin,GONG Fa-ming.Human Activities Recognition and Location Based on Temporal Analysis[J].,2019,29(11):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
[13]陈莉君,李 卓.基于深度神经压缩的 YOLO 优化[J].计算机技术与发展,2019,29(12):72.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 013]
　CHEN Li-jun,LI Zhuo.YOLO Optimization Based on Deep Neural Compression[J].,2019,29(11):72.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 013]
[14]许必宵,宫 婧,孙知信.基于卷积神经网络的目标检测模型综述[J].计算机技术与发展,2019,29(12):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
　XU Bi-xiao,GONG Jing,SUN Zhi-xin.A Survey of Object Detection Models Based on Convolutional Neural Networks[J].,2019,29(11):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
[15]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(11):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[16]宫法明,马玉辉.基于时空双分支网络的人体动作识别研究[J].计算机技术与发展,2020,30(09):23.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 005]
　GONG Fa-ming,MA Yu-hui.Research on Human Action Recognition Based on Space-time Double-branch Network[J].,2020,30(11):23.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 005]
[17]何 松,孙 静,郭乐江,等.基于激光 SLAM 和深度学习的语义地图构建[J].计算机技术与发展,2020,30(09):88.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 016]
　HE Song,SUN Jing,GUO Le-jiang,et al.Semantic Mapping Based on Laser SLAM and Deep Learning[J].,2020,30(11):88.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 016]
[18]樊海玮,史 双,蔺 琪,等.复杂背景下 SAR 图像船舶目标检测算法研究[J].计算机技术与发展,2021,31(10):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 009]
　FAN Hai-wei,SHI Shuang,LIN Qi,et al.Research on Ship Target Detection Algorithm in Complex Background SAR Image[J].,2021,31(11):49.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 009]
[19]李 威,李 楠,于清玲.基于 Faster RCNN 的可回收物自动分类算法研究[J].计算机技术与发展,2021,31(增刊):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]
　LI Wei,LI Nan,YU Qing-ling.Research on Automatic Classification Algorithm of Recyclables Based on Faster RCNN[J].,2021,31(11):100.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 020]
[20]周巧瑜,曹 扬,詹瑾瑜,等.基于 Yolo 和 GOTURN 的景区游客翻越行为识别[J].计算机技术与发展,2022,32(01):134.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 023]
　ZHOU Qiao-yu,CAO Yang,ZHAN Jin-yu,et al.A Fence Climbing Behavior Recognition of Scenic AreaTourist Based on Yolo and GOTURN[J].,2022,32(11):134.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 023]

更新日期/Last Update: 2020-11-10