[1]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):55-58.[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(05):55-58.[doi:10.3969/j.issn.1673-629X.2018.05.013]
点击复制

基于全卷积网络的目标检测算法()
分享到:

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

卷:
28
期数:
2018年05期
页码:
55-58
栏目:
智能、算法、系统工程
出版日期:
2018-05-10

文章信息/Info

Title:
Object Detection Algorithm Based on Fully Convolutional Neural Network
文章编号:
1673-629X(2018)05-0055-04
作者:
施泽浩赵启军
四川大学 计算机学院 视觉合成图形图像技术国防重点实验室,四川 成都 610065
Author(s):
SHI Ze-haoZHAO Qi-jun
National Key Laboratory of Fundamental Science on Synthetic Vision,School of Computer Science,Sichuan University,Chengdu 610065,China
关键词:
目标检测深度学习全卷积神经网络回归计算机视觉
Keywords:
object detectiondeep learningconvolutional neural networkregressioncomputer vision
分类号:
TP301.6
DOI:
10.3969/j.issn.1673-629X.2018.05.013
文献标志码:
A
摘要:
目标检测是计算机视觉的一项重要任务,其主要内容是定位图像中出现的目标,并对其进行分类。主流算法普遍基于卷积加全连接的结构,存在模型参数巨大、检测效率低下等问题。而在现实应用中,比如自动驾驶车载系统、智能监控系统中对行人、车辆等目标的检测,往往对目标检测算法的实时性具有较高要求。为此,提出一种基于全卷积神经网络的目标检测算法。网络结构完全采用卷积层实现,不仅用卷积进行特征提取,而且用卷积层进行预测,采用多任务学习,大大提高了检测效率并降低了模型复杂度。相比主流深度学习目标检测算法,如 YOLO、Faster RCNN,该算法速度更快,模型参数更少,且保持相当的精度,在 PASCAL VOC2007 权威目标检测库上的平均准确率(mAP)达到 64.5。
Abstract:
 Object detection is a primary mission in computer vision that focuses on localization and classification of objects in an image.Almost all the mainstream algorithms use convolution structure followed by fully connected layer,which lead to huge number of model parameters and poor efficiency.In real application like automatic driving,intelligence CCTV and so on,high inference efficiency is required.For this,we propose a fully convolutional based object detection algorithm.The network structure is implemented by convolution layer,both feature extraction and prediction through convolution.Multi-task learning is utilized to improve detection efficiency greatly and reduce the complexity of model.Compared to YOLO and Faster RCNN,the proposed algorithm is faster,less in model parameters and maintain its precision.The average accuracy on PASCAL VOC2007 dataset reaches to 64.5.

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,(05):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,(05):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,(05):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,(05):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(05):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(05):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(05):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(05):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(05):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(05):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[11]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(05):82.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 017]
[12]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(05):72.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 013]
[13]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(05):87.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 016]
[14]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(05):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[15]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(05):23.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 005]
[16]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(05):88.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 016]
[17]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.[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(05):42.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 008]
[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(05):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(05):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(05):134.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 023]

更新日期/Last Update: 2018-06-28