[1]凌永标,毛 峰,杨岚岚,等.基于混合注意力网络的安全工器具检测[J].计算机技术与发展,2022,32(06):209-214.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 035]
　LING Yong-biao,MAO Feng,YANG Lan-lan*,et al.Safety Tools Detection Based on Hybrid Attention Network[J].,2022,32(06):209-214.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 035]
点击复制

基于混合注意力网络的安全工器具检测()
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:
209-214
栏目:
应用前沿与综合
出版日期:
2022-06-10

文章信息/Info

Title:
Safety Tools Detection Based on Hybrid Attention Network
文章编号:
1673-629X(2022)06-0209-06
作者:
凌永标; 毛 峰; 杨岚岚; 邱兴卫; 张志锐; 张 杰
1. 国网黄山供电公司,安徽 黄山 245000;
2. 安徽大学 计算机科学与技术学院,安徽 合肥 230601
Author(s):
LING Yong-biao1; 2 ; MAO Feng1; 2 ; YANG Lan-lan2* ; QIU Xing-wei1 ; ZHANG Zhi-rui1 ; ZHANG Jie1
1. Huangshan Power Supply Company of State Grid,Huangshan 245000,China;
2. School of Computer Science and Technology,Anhui University,Hefei 230601,China
关键词:
目标检测; 安全工器具; 注意力网络; 数据增强; 特征金字塔
Keywords:
object detection; safety tools; attention network; data enhancement; feature pyramid
分类号:
TP389. 1
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 035
摘要:
在电网施工和安全检查过程中,电力工作人员的安全问题至关重要。 施工现场的安全工器具是否有破损直接关系到电力工作人员的安全,因此提出一种基于混合注意力网络的安全工器具神经网络自动检测方法,用于施工现场的安全工器具检测问题。 所提出的混合注意力网络以经典的 Faster R-CNN 为主干网络,混合注意力模块包含全局通道注意力和局部空间注意力两个子模块。 其中全局通道注意力关注的是通道的重要性,而局部空间注意力关注的是空间位置信息,主要是帮助网络定位目标。 还引入了多种混叠的数据增强方法,以及采用了基于多尺度特征金字塔的多层预测方法。此外,为了验证该方法的有效性,还从电网施工现场采集了一批真实图片,整理并标注对应的安全工器具,构建了一个安全工器具数据集。 经实验对比,该方法对于安全工器具的自动检测有较好的效果。
Abstract:
In the process of power grid construction and safety inspection,electric power staff safety is crucial. Construction site safety instruments to see if there is any breakage directly relates to the safety of staff in the electric power. Therefore,we propose an automatic detection method of safety tools based on hybrid attention network, which is used for safety tools detection in construction site. Theproposed hybrid attention network takes the classical Faster R-CNN as the main stem network,and the hybrid attention module consists oftwo sub-modules:global channel attention and local spatial attention. Global channel attention is concerned with the importance of thechannel,while local spatial attention is concerned with spatial location information,mainly to help the network locate the target. We alsointroduce a variety of aliasing data enhancement method and use the multilayer prediction method based on multi-scale feature pyramids.In addition,in order to validate the effectiveness of the proposed method,we also collect a batch of real images from the grid constructionsite,obtain the corresponding safety instruments and construct a set of security and instrument data. According to comparison, theproposed method is effective for the automatic detection of safety and instrument.

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,(06):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,(06):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,(06):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,(06):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(06):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(06):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(06):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(06):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(06):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(06):36.

更新日期/Last Update: 2022-06-10