Research on Improved YOLOv7 for Traffic Obstacle Detection
Object detection and recognition algorithms are widely used in applications such as real-time monitoring and autonomous driving. However, there is limited research on traffic obstacle detection in complex scenarios involving road construction and sudden accidents. This gap results in low accuracy an...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/16/1/1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587322835599360 |
|---|---|
| author | Yifan Yang Song Cui Xuan Xiang Yuxing Bai Liguo Zang Hongshan Ding |
| author_facet | Yifan Yang Song Cui Xuan Xiang Yuxing Bai Liguo Zang Hongshan Ding |
| author_sort | Yifan Yang |
| collection | DOAJ |
| description | Object detection and recognition algorithms are widely used in applications such as real-time monitoring and autonomous driving. However, there is limited research on traffic obstacle detection in complex scenarios involving road construction and sudden accidents. This gap results in low accuracy and difficulties in recognizing occluded targets, thereby hindering the further development and widespread adoption of intelligent transportation systems. To address these issues, this paper proposes an improved algorithm based on YOLOv7, incorporating a lightweight coordinate attention mechanism to focus on small objects at long distances and capture target location information. The use of a high receptive field enhances the feature hierarchy within the detection network. Additionally, we introduce the focal efficient intersection over union loss function to address sample imbalance, which accelerates the model’s convergence speed, reduces loss values, and improves overall model stability. Our model achieved a detection accuracy of 98.1%, reflecting a 1.4% increase, while also enhancing detection speed and minimizing missed detections. These advancements significantly bolster the model’s performance, demonstrating advantages for real-world applications. |
| format | Article |
| id | doaj-art-e6c92a79549d4c02aaa454850435b909 |
| institution | Kabale University |
| issn | 2032-6653 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj-art-e6c92a79549d4c02aaa454850435b9092025-01-24T13:52:43ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-12-01161110.3390/wevj16010001Research on Improved YOLOv7 for Traffic Obstacle DetectionYifan Yang0Song Cui1Xuan Xiang2Yuxing Bai3Liguo Zang4Hongshan Ding5School of Traffic Engineering, Nanjing Institute of Technology, Nanjing 211167, ChinaSchool of Traffic Engineering, Nanjing Institute of Technology, Nanjing 211167, ChinaSchool of Traffic Engineering, Nanjing Institute of Technology, Nanjing 211167, ChinaSchool of Traffic Engineering, Nanjing Institute of Technology, Nanjing 211167, ChinaSchool of Traffic Engineering, Nanjing Institute of Technology, Nanjing 211167, ChinaJiangsu Haopeng Machinery Co., Ltd., Taizhou 225711, ChinaObject detection and recognition algorithms are widely used in applications such as real-time monitoring and autonomous driving. However, there is limited research on traffic obstacle detection in complex scenarios involving road construction and sudden accidents. This gap results in low accuracy and difficulties in recognizing occluded targets, thereby hindering the further development and widespread adoption of intelligent transportation systems. To address these issues, this paper proposes an improved algorithm based on YOLOv7, incorporating a lightweight coordinate attention mechanism to focus on small objects at long distances and capture target location information. The use of a high receptive field enhances the feature hierarchy within the detection network. Additionally, we introduce the focal efficient intersection over union loss function to address sample imbalance, which accelerates the model’s convergence speed, reduces loss values, and improves overall model stability. Our model achieved a detection accuracy of 98.1%, reflecting a 1.4% increase, while also enhancing detection speed and minimizing missed detections. These advancements significantly bolster the model’s performance, demonstrating advantages for real-world applications.https://www.mdpi.com/2032-6653/16/1/1intelligent transportationobject detectionYOLOv7traffic obstaclesattention mechanismloss function |
| spellingShingle | Yifan Yang Song Cui Xuan Xiang Yuxing Bai Liguo Zang Hongshan Ding Research on Improved YOLOv7 for Traffic Obstacle Detection World Electric Vehicle Journal intelligent transportation object detection YOLOv7 traffic obstacles attention mechanism loss function |
| title | Research on Improved YOLOv7 for Traffic Obstacle Detection |
| title_full | Research on Improved YOLOv7 for Traffic Obstacle Detection |
| title_fullStr | Research on Improved YOLOv7 for Traffic Obstacle Detection |
| title_full_unstemmed | Research on Improved YOLOv7 for Traffic Obstacle Detection |
| title_short | Research on Improved YOLOv7 for Traffic Obstacle Detection |
| title_sort | research on improved yolov7 for traffic obstacle detection |
| topic | intelligent transportation object detection YOLOv7 traffic obstacles attention mechanism loss function |
| url | https://www.mdpi.com/2032-6653/16/1/1 |
| work_keys_str_mv | AT yifanyang researchonimprovedyolov7fortrafficobstacledetection AT songcui researchonimprovedyolov7fortrafficobstacledetection AT xuanxiang researchonimprovedyolov7fortrafficobstacledetection AT yuxingbai researchonimprovedyolov7fortrafficobstacledetection AT liguozang researchonimprovedyolov7fortrafficobstacledetection AT hongshanding researchonimprovedyolov7fortrafficobstacledetection |