Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports
With the development of automation in ports, the video surveillance systems with automated human detection begun to be applied in open-air handling operation areas for safety and security. The accuracy of traditional human detection based on the video camera is not high enough to meet the requiremen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2015-09-01
|
| Series: | Polish Maritime Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/pomr-2015-0049 |
| _version_ | 1818689376799948800 |
|---|---|
| author | Mi Chao Zhang Zhiwei He Xin Huang Youfang Mi Weijian |
| author_facet | Mi Chao Zhang Zhiwei He Xin Huang Youfang Mi Weijian |
| author_sort | Mi Chao |
| collection | DOAJ |
| description | With the development of automation in ports, the video surveillance systems with automated human detection begun to be applied in open-air handling operation areas for safety and security. The accuracy of traditional human detection based on the video camera is not high enough to meet the requirements of operation surveillance. One of the key reasons is that Histograms of Oriented Gradients (HOG) features of the human body will show great different between front & back standing (F&B) and side standing (Side) human body. Therefore, the final training for classifier will only gain a few useful specific features which have contribution to classification and are insufficient to support effective classification, while using the HOG features directly extracted by the samples from different human postures. This paper proposes a two-stage classification method to improve the accuracy of human detection. In the first stage, during preprocessing classification, images is mainly divided into possible F&B human body and not F&B human body, and then they were put into the second-stage classification among side human and non-human recognition. The experimental results in Tianjin port show that the two-stage classifier can improve the classification accuracy of human detection obviously. |
| first_indexed | 2024-12-17T12:09:08Z |
| format | Article |
| id | doaj.art-fbd94f40765d4bacbc449488935e887a |
| institution | Directory Open Access Journal |
| issn | 2083-7429 |
| language | English |
| last_indexed | 2024-12-17T12:09:08Z |
| publishDate | 2015-09-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Polish Maritime Research |
| spelling | doaj.art-fbd94f40765d4bacbc449488935e887a2022-12-21T21:49:29ZengSciendoPolish Maritime Research2083-74292015-09-0122s116317010.1515/pomr-2015-0049pomr-2015-0049Two-Stage Classification Approach for Human Detection in Camera Video in Bulk PortsMi Chao0Zhang Zhiwei1He Xin2Huang Youfang3Mi Weijian4Container Supply Chain Tech. Engineering Research Center, Shanghai Maritime University, No.1550 Haigang Ave, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, No.1550 Haigang Ave, Shanghai 201306, ChinaLogistics Engineering College, Shanghai Maritime University, No.1550 Haigang Ave, Shanghai 201306, ChinaContainer Supply Chain Tech. Engineering Research Center, Shanghai Maritime University, No.1550 Haigang Ave, Shanghai 201306, ChinaContainer Supply Chain Tech. Engineering Research Center, Shanghai Maritime University, No.1550 Haigang Ave, Shanghai 201306, ChinaWith the development of automation in ports, the video surveillance systems with automated human detection begun to be applied in open-air handling operation areas for safety and security. The accuracy of traditional human detection based on the video camera is not high enough to meet the requirements of operation surveillance. One of the key reasons is that Histograms of Oriented Gradients (HOG) features of the human body will show great different between front & back standing (F&B) and side standing (Side) human body. Therefore, the final training for classifier will only gain a few useful specific features which have contribution to classification and are insufficient to support effective classification, while using the HOG features directly extracted by the samples from different human postures. This paper proposes a two-stage classification method to improve the accuracy of human detection. In the first stage, during preprocessing classification, images is mainly divided into possible F&B human body and not F&B human body, and then they were put into the second-stage classification among side human and non-human recognition. The experimental results in Tianjin port show that the two-stage classifier can improve the classification accuracy of human detection obviously.https://doi.org/10.1515/pomr-2015-0049human detectionhistograms of oriented gradientssupport vector machineclassification |
| spellingShingle | Mi Chao Zhang Zhiwei He Xin Huang Youfang Mi Weijian Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports Polish Maritime Research human detection histograms of oriented gradients support vector machine classification |
| title | Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports |
| title_full | Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports |
| title_fullStr | Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports |
| title_full_unstemmed | Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports |
| title_short | Two-Stage Classification Approach for Human Detection in Camera Video in Bulk Ports |
| title_sort | two stage classification approach for human detection in camera video in bulk ports |
| topic | human detection histograms of oriented gradients support vector machine classification |
| url | https://doi.org/10.1515/pomr-2015-0049 |
| work_keys_str_mv | AT michao twostageclassificationapproachforhumandetectionincameravideoinbulkports AT zhangzhiwei twostageclassificationapproachforhumandetectionincameravideoinbulkports AT hexin twostageclassificationapproachforhumandetectionincameravideoinbulkports AT huangyoufang twostageclassificationapproachforhumandetectionincameravideoinbulkports AT miweijian twostageclassificationapproachforhumandetectionincameravideoinbulkports |