Visual Ranging Based on Object Detection Bounding Box Optimization
Faster and more accurate ranging can be achieved by combining the object detection technique based on deep learning with conventional visual ranging. However, changes in scene, uneven lighting, fuzzy object boundaries and other factors may result in a non-fit phenomenon between the detection boundin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/19/10578 |
| _version_ | 1827722903222747136 |
|---|---|
| author | Zhou Shi Zhongguo Li Sai Che Miaowei Gao Hongchuan Tang |
| author_facet | Zhou Shi Zhongguo Li Sai Che Miaowei Gao Hongchuan Tang |
| author_sort | Zhou Shi |
| collection | DOAJ |
| description | Faster and more accurate ranging can be achieved by combining the object detection technique based on deep learning with conventional visual ranging. However, changes in scene, uneven lighting, fuzzy object boundaries and other factors may result in a non-fit phenomenon between the detection bounding box and the object. The pixel spacing between the detection bounding box and the object can cause ranging errors. To reduce pixel spacing, increase the degree of fit between the object detection bounding box and the object, and improve ranging accuracy, an object detection bounding box optimization method is proposed. Two evaluation indicators, WOV and HOV, are also proposed to evaluate the results of bounding box optimization. The experimental results show that the pixel width of the bounding box is optimized by 1.19~19.24% and the pixel height is optimized by 0~12.14%. At the same time, the ranging experiments demonstrate that the optimization of the bounding box improves the ranging accuracy. In addition, few practical monocular range measurement techniques can also determine the distance to an object whose size is unknown. Therefore, a similar triangle ranging technique based on height difference is suggested to measure the distance to items of unknown size. A ranging experiment is carried out based on the optimization of the detecting bounding box, and the experimental results reveal that the ranging relative error within 6 m is between 0.7% and 2.47%, allowing for precise distance measurement. |
| first_indexed | 2024-03-10T21:49:49Z |
| format | Article |
| id | doaj.art-ace8c56c8ddf49f3bacfc015fc01feb3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:49:49Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ace8c56c8ddf49f3bacfc015fc01feb32023-11-19T14:01:19ZengMDPI AGApplied Sciences2076-34172023-09-0113191057810.3390/app131910578Visual Ranging Based on Object Detection Bounding Box OptimizationZhou Shi0Zhongguo Li1Sai Che2Miaowei Gao3Hongchuan Tang4School of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaFaster and more accurate ranging can be achieved by combining the object detection technique based on deep learning with conventional visual ranging. However, changes in scene, uneven lighting, fuzzy object boundaries and other factors may result in a non-fit phenomenon between the detection bounding box and the object. The pixel spacing between the detection bounding box and the object can cause ranging errors. To reduce pixel spacing, increase the degree of fit between the object detection bounding box and the object, and improve ranging accuracy, an object detection bounding box optimization method is proposed. Two evaluation indicators, WOV and HOV, are also proposed to evaluate the results of bounding box optimization. The experimental results show that the pixel width of the bounding box is optimized by 1.19~19.24% and the pixel height is optimized by 0~12.14%. At the same time, the ranging experiments demonstrate that the optimization of the bounding box improves the ranging accuracy. In addition, few practical monocular range measurement techniques can also determine the distance to an object whose size is unknown. Therefore, a similar triangle ranging technique based on height difference is suggested to measure the distance to items of unknown size. A ranging experiment is carried out based on the optimization of the detecting bounding box, and the experimental results reveal that the ranging relative error within 6 m is between 0.7% and 2.47%, allowing for precise distance measurement.https://www.mdpi.com/2076-3417/13/19/10578visual rangingmonocular rangingobject detectiondata augmentationGrabCut segmentation |
| spellingShingle | Zhou Shi Zhongguo Li Sai Che Miaowei Gao Hongchuan Tang Visual Ranging Based on Object Detection Bounding Box Optimization Applied Sciences visual ranging monocular ranging object detection data augmentation GrabCut segmentation |
| title | Visual Ranging Based on Object Detection Bounding Box Optimization |
| title_full | Visual Ranging Based on Object Detection Bounding Box Optimization |
| title_fullStr | Visual Ranging Based on Object Detection Bounding Box Optimization |
| title_full_unstemmed | Visual Ranging Based on Object Detection Bounding Box Optimization |
| title_short | Visual Ranging Based on Object Detection Bounding Box Optimization |
| title_sort | visual ranging based on object detection bounding box optimization |
| topic | visual ranging monocular ranging object detection data augmentation GrabCut segmentation |
| url | https://www.mdpi.com/2076-3417/13/19/10578 |
| work_keys_str_mv | AT zhoushi visualrangingbasedonobjectdetectionboundingboxoptimization AT zhongguoli visualrangingbasedonobjectdetectionboundingboxoptimization AT saiche visualrangingbasedonobjectdetectionboundingboxoptimization AT miaoweigao visualrangingbasedonobjectdetectionboundingboxoptimization AT hongchuantang visualrangingbasedonobjectdetectionboundingboxoptimization |