[1]翟正利,孙 霞,周 炜,等.基于全卷积神经网络的多目标显著性检测[J].计算机技术与发展,2020,30(08):34-39.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 006]
　ZHAI Zheng-li,SUN Xia,ZHOU Wei,et al.Multi-objective Saliency Detection Based on Full Convolution Neural Network[J].,2020,30(08):34-39.[doi:10. 3969 / j. issn. 1673-629X. 2020. 08. 006]
点击复制

基于全卷积神经网络的多目标显著性检测()

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

卷:
30
期数:
2020年08期
页码:
34-39
栏目:
智能、算法、系统工程
出版日期:
2020-08-10

文章信息/Info

Title:
Multi-objective Saliency Detection Based on Full Convolution Neural Network
文章编号:
1673-629X(2020)08-0034-06
作者:
翟正利; 孙 霞; 周 炜; 梁振明
青岛理工大学 信息与控制工程学院,山东 青岛 266520
Author(s):
ZHAI Zheng-li; SUN Xia; ZHOU Wei; LIANG Zhen-ming
School of Information and Control Engineering,Qingdao University of Technology,Qingdao 266520,China
关键词:
目标检测; 空洞卷积; 低级特征; 全卷积神经网络; 跳跃连接
Keywords:
object detection; void convolution; low-level feature; fully convolutional neural network; jump connection
分类号:
TP302.7
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 08. 006
摘要:
随着图像数据的爆炸性增长,图像处理变得越来越重要。 显著性目标检测是图像处理的重要研究方向之一,目前已采用多种研究方法进行显著性目标检测,但是传统的显著性检测方法所使用的低级特征对于复杂场景并不健壮。 全卷积神经网络在图像处理中表现出良好的性能,但存在目标显著性检测边界模糊等不足。为解决边界模糊等问题,该模型采用了一种具有跳跃连接的全卷积神经网络,以及 5 个不同膨胀率的空洞卷积按照一定规则组成的 ESP 模块,在全卷积神经网络的基础上采用 ESP 模块和不同的跳跃连接方式,以获取更多的低级特征来精确多目标显著对象的边界。实验中运用 MIT Scene Parsing 数据集训练和测试模型,通过与相关模型在精度和 MIOU 上的比较结果表明,在保证模型的处理时间未增加的同时,经过改进的全卷积神经网络的检测具有更高的准确度以及更精确的边界信息。
Abstract:
With the explosive growth of image data,image processing becomes more and more important. Saliency target detection is one of the important research directions in image processing. At present,many research methods have been used to detect saliency targets,but the low-level features used in traditional saliency detection methods are not robust for complex scenes. Fully convolutional network has excellent performance in image processing,but it has some shortcomings such as ambiguous edge of target saliency detection. In order to solve the problem of boundary fuzzy,a fully convolutional network with jump connection and ESP module composed of five hollow convolutions with different expansion rates according to certain rules are adopted in this model. On the basis of the fully convolutional network,the ESP module and different jump connection methods are used to obtain more low-level features to accurately define the boundary of multi-objective significant objects. In the experiment,we use the data set of MIT Scene Parsing to train and test the model. Compared with the related models in accuracy and MIOU,the results show that the improved fully convolutional network has higher accuracy and more accurate boundary information while ensuring that the processing time of the model does not increase.

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,(08):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,(08):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,(08):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,(08):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(08):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(08):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(08):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(08):18.
[9]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(08):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[10]张夏清,茅耀斌. 一种改进的ViBe背景提取算法[J].计算机技术与发展,2016,26(07):36.
　ZHANG Xia-qing,MAO Yao-bin. An Improved ViBe Background Generation Method[J].,2016,26(08):36.

更新日期/Last Update: 2020-08-10