Long-Distance Person Detection Based on YOLOv7
In the research field of small object detection, most object detectors have been successfully used for pedestrian detection, face recognition, lost and found, and automatic driving, among other applications, and have achieved good results. However, when general object detectors encounter challenging...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/6/1502 |
| _version_ | 1797612197121097728 |
|---|---|
| author | Fan Tang Fang Yang Xianqing Tian |
| author_facet | Fan Tang Fang Yang Xianqing Tian |
| author_sort | Fan Tang |
| collection | DOAJ |
| description | In the research field of small object detection, most object detectors have been successfully used for pedestrian detection, face recognition, lost and found, and automatic driving, among other applications, and have achieved good results. However, when general object detectors encounter challenging low-resolution images from the TinyPerson dataset, they will produce undesirable detection results because of the dense occlusion between people and different body poses. In order to solve these problems, this paper proposes a tiny object detection method TOD-YOLOv7 based on YOLOv7.First, this paper presents a reconstruction of the YOLOv7 network by adding a tiny object detection layer to enhance its detection ability. Then, we use the recursive gated convolution module to realize the interaction with the higher-order space to accelerate the model initialization process and reduce the reasoning time. Secondly, this paper proposes the integration of a coordinate attention mechanism into the YOLOv7 feature extraction network to strengthen the pedestrian object information and weaken the background information.Additionally, we leverage data augmentation techniques to improve the representation learning of the algorithm. The results show that compared with the baseline model YOLOv7, the detection accuracy of this model on the TinyPerson dataset is improved from 7.1% to 9.5%, and the detection speed reaches 208 frames per second (FPS). The algorithm of this paper is shown to achieve better detection results for tiny object detection. |
| first_indexed | 2024-03-11T06:37:52Z |
| format | Article |
| id | doaj.art-798acb7747914d2dabf7f52ae2d3625d |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T06:37:52Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-798acb7747914d2dabf7f52ae2d3625d2023-11-17T10:46:25ZengMDPI AGElectronics2079-92922023-03-01126150210.3390/electronics12061502Long-Distance Person Detection Based on YOLOv7Fan Tang0Fang Yang1Xianqing Tian2School of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaSchool of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaSchool of Cyberspace Security and Computer, Hebei University, Baoding 071000, ChinaIn the research field of small object detection, most object detectors have been successfully used for pedestrian detection, face recognition, lost and found, and automatic driving, among other applications, and have achieved good results. However, when general object detectors encounter challenging low-resolution images from the TinyPerson dataset, they will produce undesirable detection results because of the dense occlusion between people and different body poses. In order to solve these problems, this paper proposes a tiny object detection method TOD-YOLOv7 based on YOLOv7.First, this paper presents a reconstruction of the YOLOv7 network by adding a tiny object detection layer to enhance its detection ability. Then, we use the recursive gated convolution module to realize the interaction with the higher-order space to accelerate the model initialization process and reduce the reasoning time. Secondly, this paper proposes the integration of a coordinate attention mechanism into the YOLOv7 feature extraction network to strengthen the pedestrian object information and weaken the background information.Additionally, we leverage data augmentation techniques to improve the representation learning of the algorithm. The results show that compared with the baseline model YOLOv7, the detection accuracy of this model on the TinyPerson dataset is improved from 7.1% to 9.5%, and the detection speed reaches 208 frames per second (FPS). The algorithm of this paper is shown to achieve better detection results for tiny object detection.https://www.mdpi.com/2079-9292/12/6/1502object detectionYOLOv7recursive gated convolutiontiny object detection layercoordinate attention mechanism |
| spellingShingle | Fan Tang Fang Yang Xianqing Tian Long-Distance Person Detection Based on YOLOv7 Electronics object detection YOLOv7 recursive gated convolution tiny object detection layer coordinate attention mechanism |
| title | Long-Distance Person Detection Based on YOLOv7 |
| title_full | Long-Distance Person Detection Based on YOLOv7 |
| title_fullStr | Long-Distance Person Detection Based on YOLOv7 |
| title_full_unstemmed | Long-Distance Person Detection Based on YOLOv7 |
| title_short | Long-Distance Person Detection Based on YOLOv7 |
| title_sort | long distance person detection based on yolov7 |
| topic | object detection YOLOv7 recursive gated convolution tiny object detection layer coordinate attention mechanism |
| url | https://www.mdpi.com/2079-9292/12/6/1502 |
| work_keys_str_mv | AT fantang longdistancepersondetectionbasedonyolov7 AT fangyang longdistancepersondetectionbasedonyolov7 AT xianqingtian longdistancepersondetectionbasedonyolov7 |