Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm
Target detection plays a key role in the safe driving of autonomous vehicles. At present, most studies use single sensor to collect obstacle information, but single sensor cannot deal with the complex urban road environment, and the rate of missed detection is high. Therefore, this paper presents a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2227-7390/6/10/213 |
| _version_ | 1818266847314706432 |
|---|---|
| author | Jian Han Yaping Liao Junyou Zhang Shufeng Wang Sixian Li |
| author_facet | Jian Han Yaping Liao Junyou Zhang Shufeng Wang Sixian Li |
| author_sort | Jian Han |
| collection | DOAJ |
| description | Target detection plays a key role in the safe driving of autonomous vehicles. At present, most studies use single sensor to collect obstacle information, but single sensor cannot deal with the complex urban road environment, and the rate of missed detection is high. Therefore, this paper presents a detection fusion system with integrating LiDAR and color camera. Based on the original You Only Look Once (YOLO) algorithm, the second detection scheme is proposed to improve the YOLO algorithm for dim targets such as non-motorized vehicles and pedestrians. Many image samples are used to train the YOLO algorithm to obtain the relevant parameters and establish the target detection model. Then, the decision level fusion of sensors is introduced to fuse the color image and the depth image to improve the accuracy of the target detection. Finally, the test samples are used to verify the decision level fusion. The results show that the improved YOLO algorithm and decision level fusion have high accuracy of target detection, can meet the need of real-time, and can reduce the rate of missed detection of dim targets such as non-motor vehicles and pedestrians. Thus, the method in this paper, under the premise of considering accuracy and real-time, has better performance and larger application prospect. |
| first_indexed | 2024-12-12T20:13:12Z |
| format | Article |
| id | doaj.art-a05377caf7a34fdba6c5d266cca46d45 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-12-12T20:13:12Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-a05377caf7a34fdba6c5d266cca46d452022-12-22T00:13:28ZengMDPI AGMathematics2227-73902018-10-0161021310.3390/math6100213math6100213Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO AlgorithmJian Han0Yaping Liao1Junyou Zhang2Shufeng Wang3Sixian Li4College of Transportation, Shandong University of Science and Technology, Huangdao District, Qingdao 266590, ChinaCollege of Transportation, Shandong University of Science and Technology, Huangdao District, Qingdao 266590, ChinaCollege of Transportation, Shandong University of Science and Technology, Huangdao District, Qingdao 266590, ChinaCollege of Transportation, Shandong University of Science and Technology, Huangdao District, Qingdao 266590, ChinaCollege of Transportation, Shandong University of Science and Technology, Huangdao District, Qingdao 266590, ChinaTarget detection plays a key role in the safe driving of autonomous vehicles. At present, most studies use single sensor to collect obstacle information, but single sensor cannot deal with the complex urban road environment, and the rate of missed detection is high. Therefore, this paper presents a detection fusion system with integrating LiDAR and color camera. Based on the original You Only Look Once (YOLO) algorithm, the second detection scheme is proposed to improve the YOLO algorithm for dim targets such as non-motorized vehicles and pedestrians. Many image samples are used to train the YOLO algorithm to obtain the relevant parameters and establish the target detection model. Then, the decision level fusion of sensors is introduced to fuse the color image and the depth image to improve the accuracy of the target detection. Finally, the test samples are used to verify the decision level fusion. The results show that the improved YOLO algorithm and decision level fusion have high accuracy of target detection, can meet the need of real-time, and can reduce the rate of missed detection of dim targets such as non-motor vehicles and pedestrians. Thus, the method in this paper, under the premise of considering accuracy and real-time, has better performance and larger application prospect.http://www.mdpi.com/2227-7390/6/10/213autonomous vehicletarget detectionmulti-sensorsfusionYOLO |
| spellingShingle | Jian Han Yaping Liao Junyou Zhang Shufeng Wang Sixian Li Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm Mathematics autonomous vehicle target detection multi-sensors fusion YOLO |
| title | Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm |
| title_full | Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm |
| title_fullStr | Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm |
| title_full_unstemmed | Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm |
| title_short | Target Fusion Detection of LiDAR and Camera Based on the Improved YOLO Algorithm |
| title_sort | target fusion detection of lidar and camera based on the improved yolo algorithm |
| topic | autonomous vehicle target detection multi-sensors fusion YOLO |
| url | http://www.mdpi.com/2227-7390/6/10/213 |
| work_keys_str_mv | AT jianhan targetfusiondetectionoflidarandcamerabasedontheimprovedyoloalgorithm AT yapingliao targetfusiondetectionoflidarandcamerabasedontheimprovedyoloalgorithm AT junyouzhang targetfusiondetectionoflidarandcamerabasedontheimprovedyoloalgorithm AT shufengwang targetfusiondetectionoflidarandcamerabasedontheimprovedyoloalgorithm AT sixianli targetfusiondetectionoflidarandcamerabasedontheimprovedyoloalgorithm |