Target detection of underground personnel based on deep convolutional neural network
In view of problems that human—centered video monitoring mode had limited duration, multiple scenes were difficult to monitor at the same time, and results of manual monitoring were not processed in time, target detection method of underground personnel based on deep convolutional neural network was...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Industry and Mine Automation
2018-11-01
|
| Series: | Gong-kuang zidonghua |
| Subjects: | |
| Online Access: | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671—251x.2018050068 |
| _version_ | 1797869002732601344 |
|---|---|
| author | TANG Shiyu ZHU Aichun ZHANG Sai CAO Qingfeng CUI Ran HUA Gang |
| author_facet | TANG Shiyu ZHU Aichun ZHANG Sai CAO Qingfeng CUI Ran HUA Gang |
| author_sort | TANG Shiyu |
| collection | DOAJ |
| description | In view of problems that human—centered video monitoring mode had limited duration, multiple scenes were difficult to monitor at the same time, and results of manual monitoring were not processed in time, target detection method of underground personnel based on deep convolutional neural network was proposed. Firstly, input image was scaled to a fixed size, and a feature map was formed after operation of deep convolutional neural network; then, a suggestion area was formed on the feature map through area suggestion network, the suggestion area was pooled into a unified size which was sent to full connection layer for operation; finally, the best suggestion area was selected according to probability score, and the required target detection box was automatically generated. The test results show that the method can successfully detect head of underground personnel with an accuracy rate of 87.6%. |
| first_indexed | 2024-04-10T00:04:42Z |
| format | Article |
| id | doaj.art-9e4083a50206455db33ebd475eeb25a9 |
| institution | Directory Open Access Journal |
| issn | 1671-251X |
| language | zho |
| last_indexed | 2024-04-10T00:04:42Z |
| publishDate | 2018-11-01 |
| publisher | Editorial Department of Industry and Mine Automation |
| record_format | Article |
| series | Gong-kuang zidonghua |
| spelling | doaj.art-9e4083a50206455db33ebd475eeb25a92023-03-17T01:18:56ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2018-11-014411323610.13272/j.issn.1671—251x.2018050068Target detection of underground personnel based on deep convolutional neural networkTANG Shiyu0ZHU Aichun1ZHANG Sai2CAO Qingfeng3CUI Ran4HUA Gang5School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, ChinaCollege of Computer Science and Technology, Nanjing University of Technology, Nanjing 211816, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, ChinaIn view of problems that human—centered video monitoring mode had limited duration, multiple scenes were difficult to monitor at the same time, and results of manual monitoring were not processed in time, target detection method of underground personnel based on deep convolutional neural network was proposed. Firstly, input image was scaled to a fixed size, and a feature map was formed after operation of deep convolutional neural network; then, a suggestion area was formed on the feature map through area suggestion network, the suggestion area was pooled into a unified size which was sent to full connection layer for operation; finally, the best suggestion area was selected according to probability score, and the required target detection box was automatically generated. The test results show that the method can successfully detect head of underground personnel with an accuracy rate of 87.6%.http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671—251x.2018050068coal mine safetytarget detection of underground personnelhead detectiondeep learningconvolutional neural networkfaster r—cn |
| spellingShingle | TANG Shiyu ZHU Aichun ZHANG Sai CAO Qingfeng CUI Ran HUA Gang Target detection of underground personnel based on deep convolutional neural network Gong-kuang zidonghua coal mine safety target detection of underground personnel head detection deep learning convolutional neural network faster r—cn |
| title | Target detection of underground personnel based on deep convolutional neural network |
| title_full | Target detection of underground personnel based on deep convolutional neural network |
| title_fullStr | Target detection of underground personnel based on deep convolutional neural network |
| title_full_unstemmed | Target detection of underground personnel based on deep convolutional neural network |
| title_short | Target detection of underground personnel based on deep convolutional neural network |
| title_sort | target detection of underground personnel based on deep convolutional neural network |
| topic | coal mine safety target detection of underground personnel head detection deep learning convolutional neural network faster r—cn |
| url | http://www.gkzdh.cn/article/doi/10.13272/j.issn.1671—251x.2018050068 |
| work_keys_str_mv | AT tangshiyu targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork AT zhuaichun targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork AT zhangsai targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork AT caoqingfeng targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork AT cuiran targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork AT huagang targetdetectionofundergroundpersonnelbasedondeepconvolutionalneuralnetwork |