Efficient Pedestrian Detection at Nighttime Using a Thermal Camera
Most of the commercial nighttime pedestrian detection (PD) methods reported previously utilized the histogram of oriented gradient (HOG) or the local binary pattern (LBP) as the feature and the support vector machine (SVM) as the classifier using thermal camera images. In this paper, we propose a ne...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/17/8/1850 |
| _version_ | 1828359301433917440 |
|---|---|
| author | Jeonghyun Baek Sungjun Hong Jisu Kim Euntai Kim |
| author_facet | Jeonghyun Baek Sungjun Hong Jisu Kim Euntai Kim |
| author_sort | Jeonghyun Baek |
| collection | DOAJ |
| description | Most of the commercial nighttime pedestrian detection (PD) methods reported previously utilized the histogram of oriented gradient (HOG) or the local binary pattern (LBP) as the feature and the support vector machine (SVM) as the classifier using thermal camera images. In this paper, we propose a new feature called the thermal-position-intensity-histogram of oriented gradient (TPIHOG or T π HOG) and developed a new combination of the T π HOG and the additive kernel SVM (AKSVM) for efficient nighttime pedestrian detection. The proposed T π HOG includes detailed information on gradient location; therefore, it has more distinctive power than the HOG. The AKSVM performs better than the linear SVM in terms of detection performance, while it is much faster than other kernel SVMs. The combined T π HOG-AKSVM showed effective nighttime PD performance with fast computational time. The proposed method was experimentally tested with the KAIST pedestrian dataset and showed better performance compared with other conventional methods. |
| first_indexed | 2024-04-14T03:39:53Z |
| format | Article |
| id | doaj.art-c24d9f5f1f1347659e82dd4a4304b907 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T03:39:53Z |
| publishDate | 2017-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c24d9f5f1f1347659e82dd4a4304b9072022-12-22T02:14:34ZengMDPI AGSensors1424-82202017-08-01178185010.3390/s17081850s17081850Efficient Pedestrian Detection at Nighttime Using a Thermal CameraJeonghyun Baek0Sungjun Hong1Jisu Kim2Euntai Kim3The School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, KoreaThe School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, KoreaThe School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, KoreaThe School of Electrical and Electronic Engineering, Yonsei University, Seoul 120-749, KoreaMost of the commercial nighttime pedestrian detection (PD) methods reported previously utilized the histogram of oriented gradient (HOG) or the local binary pattern (LBP) as the feature and the support vector machine (SVM) as the classifier using thermal camera images. In this paper, we propose a new feature called the thermal-position-intensity-histogram of oriented gradient (TPIHOG or T π HOG) and developed a new combination of the T π HOG and the additive kernel SVM (AKSVM) for efficient nighttime pedestrian detection. The proposed T π HOG includes detailed information on gradient location; therefore, it has more distinctive power than the HOG. The AKSVM performs better than the linear SVM in terms of detection performance, while it is much faster than other kernel SVMs. The combined T π HOG-AKSVM showed effective nighttime PD performance with fast computational time. The proposed method was experimentally tested with the KAIST pedestrian dataset and showed better performance compared with other conventional methods.https://www.mdpi.com/1424-8220/17/8/1850pedestrian detectionfar-infrared sensorthermal-position-intensity-histogram of oriented gradient |
| spellingShingle | Jeonghyun Baek Sungjun Hong Jisu Kim Euntai Kim Efficient Pedestrian Detection at Nighttime Using a Thermal Camera Sensors pedestrian detection far-infrared sensor thermal-position-intensity-histogram of oriented gradient |
| title | Efficient Pedestrian Detection at Nighttime Using a Thermal Camera |
| title_full | Efficient Pedestrian Detection at Nighttime Using a Thermal Camera |
| title_fullStr | Efficient Pedestrian Detection at Nighttime Using a Thermal Camera |
| title_full_unstemmed | Efficient Pedestrian Detection at Nighttime Using a Thermal Camera |
| title_short | Efficient Pedestrian Detection at Nighttime Using a Thermal Camera |
| title_sort | efficient pedestrian detection at nighttime using a thermal camera |
| topic | pedestrian detection far-infrared sensor thermal-position-intensity-histogram of oriented gradient |
| url | https://www.mdpi.com/1424-8220/17/8/1850 |
| work_keys_str_mv | AT jeonghyunbaek efficientpedestriandetectionatnighttimeusingathermalcamera AT sungjunhong efficientpedestriandetectionatnighttimeusingathermalcamera AT jisukim efficientpedestriandetectionatnighttimeusingathermalcamera AT euntaikim efficientpedestriandetectionatnighttimeusingathermalcamera |