[1]杨朝晨,陈佳悦,邢 可,等.基于改进的 DSSD 的小目标检测算法研究[J].计算机技术与发展,2022,32(06):63-67.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 011]
　YANG Zhao-chen,CHEN Jia-yue,XING Ke,et al.Small Target Detection Algorithm Based on Improved DSSD[J].,2022,32(06):63-67.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 011]
点击复制

基于改进的 DSSD 的小目标检测算法研究()
分享到：

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

卷:
32
期数:
2022年06期
页码:
63-67
栏目:
图形与图像
出版日期:
2022-06-10

文章信息/Info

Title:
Small Target Detection Algorithm Based on Improved DSSD
文章编号:
1673-629X(2022)06-0063-05
作者:
杨朝晨; 陈佳悦; 邢 可; 刘梦尼; 高 涛
1. 长安大学 信息工程学院,陕西 西安 710064;
2. 西北大学 信息科学与技术学院,陕西 西安 710127
Author(s):
YANG Zhao-chen1 ; CHEN Jia-yue2 ; XING Ke1 ; LIU Meng-ni1 ; GAO Tao1
1. School of Information Engineering,Chang’an University,Xi’an 710064,China;
2. School of Information Science and Technology,Northwest University,Xi’an 710127,China
关键词:
深度学习; DSSD; 残差网络; 小目标检测; 图像处理
Keywords:
deep learning; DSSD; residual network; small target detection; image processing
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 011
摘要:
随着深度学习的迅速发展,图像识别技术也随之日益提高,其中目标检测在辅助驾驶系统、医学领域和车流监测系统等占有重要地位。 大多目标检测算法对大目标较为敏感,且并未考虑特征与特征之间的相互关系及重要程度,然而小目标在图像中覆盖区域小,分辨率低,携带信息较少,导致小目标的误检或漏检率较高。 针对以上问题,对小目标检测的难点进行研究,提出了一种基于改进的 DSSD( deconvolutional single shot detector) 的小目标检测算法。 该算法引入混合注意力机制,在通道维度上增加权重分量进行加权求和表示信息相关度,并将图片中的空间域信息做对应空间变换,提取关键信息,突出局部重点区域,有利于前景小目标的特征学习。 实验结果表明,该算法在 VOC2007 测试集上的精确度达到81. 02% ,比原 DSSD 算法高出 1. 3% ,且均优于其他对比算法,证明了算法的有效性。
Abstract:
With the rapid development of deep learning,image recognition technology is also improving,and target detection has becomean important and highly relevant topic in assistant driving system,medical field and traffic flow monitoring system. Most of the target detection algorithms are sensitive to large targets and unable to take into account the relationship and importance between features.However,small targets have small coverage area, low resolution and less information, which leads to high false detection or misseddetection rate of small targets. In view of the above problems,the difficulties of small target detection are studied,and a small targetdetection algorithm based on DSSD is proposed. In this algorithm, the hybrid attention mechanism is introduced, and the weightedcomponent is added to the channel dimension to represent the information correlation,and the spatial domain information in the image istransformed in corresponding space to extract key information and highlight local key areas,which is conducive to feature learning ofsmall foreground targets. The experimental results demonstrate that the proposed algorithm achieves 81. 02% accuracy on the VOC2007test set,which is 1. 3% higher than that of the original DSSD algorithm,and is also superior to other comparison algorithms,which provesthe effectiveness of the algorithm.

相似文献/References:

[1]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(06):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]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(06):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]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(06):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(06):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(06):1.
[7]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(06):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(06):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(06):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(06):7.

更新日期/Last Update: 2022-06-10