Improved YOLOv4-Tiny Lightweight Target Detection Algorithm
Object detection is an important branch of deep learning. A large number of edge devices need lightweight object detection algorithms, but the existing lightweight universal object detection algorithms have problems of low detection accuracy and slow detection speed. To solve this problem, an improv...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2024-01-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2301034.pdf |
| _version_ | 1797362602911727616 |
|---|---|
| author | HE Xiangjie, SONG Xiaoning |
| author_facet | HE Xiangjie, SONG Xiaoning |
| author_sort | HE Xiangjie, SONG Xiaoning |
| collection | DOAJ |
| description | Object detection is an important branch of deep learning. A large number of edge devices need lightweight object detection algorithms, but the existing lightweight universal object detection algorithms have problems of low detection accuracy and slow detection speed. To solve this problem, an improved YOLOv4-Tiny algorithm based on attention mechanism is proposed. The structure of the original backbone network of YOLOv4-Tiny algorithm is adjusted, the ECA (efficient channel attention) attention mechanism is introduced, the traditional spatial pyramid pooling (SPP) structure is improved to DC-SPP structure by using void convolution, and the CSATT (channel spatial attention) attention mechanism is proposed. The neck network of CSATT-PAN (channel spatial attention path aggregation network) is formed with the feature fusion network PAN, which improves the feature fusion capability of the network. Compared with the original YOLOv4-Tiny algorithm, the proposed YOLOv4-CSATT algorithm is significantly more sensitive to information and accurate in classification when the detection speed is basically the same. The accuracy is increased by 12.3 percentage points on VOC dataset and 6.4 percentage points is increased on COCO dataset. Moreover, the accuracy is 3.3，5.5，6.3，17.4，10.3，0.9 and 0.6 percentage points higher than the Faster R-CNN, SSD, Efficientdet-d1, YOLOv3-Tiny, YOLOv4-MobileNetv1, YOLOv4-MobileNetv2 and PP-YOLO algorithms respectively on VOC dataset, and 2.8, 7.1, 4.2, 18.0, 12.2, 2.1 and 4.0 percentage points higher in recall rate, respectively, with an FPS of 94. In this paper, the CSATT attention mechanism is proposed to improve the model’s ability to capture spatial channel information, and the ECA attention mechanism is combined with the feature fusion pyramid algorithm to improve the model’s feature fusion ability and target detection accuracy. |
| first_indexed | 2024-03-08T16:10:17Z |
| format | Article |
| id | doaj.art-4064560bad8c4ab895d28bbb85f3507d |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-03-08T16:10:17Z |
| publishDate | 2024-01-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-4064560bad8c4ab895d28bbb85f3507d2024-01-08T01:41:14ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182024-01-0118113815010.3778/j.issn.1673-9418.2301034Improved YOLOv4-Tiny Lightweight Target Detection AlgorithmHE Xiangjie, SONG Xiaoning0Jiangsu Engineering Laboratory of Pattern Recognition and Computational Intelligence, School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, ChinaObject detection is an important branch of deep learning. A large number of edge devices need lightweight object detection algorithms, but the existing lightweight universal object detection algorithms have problems of low detection accuracy and slow detection speed. To solve this problem, an improved YOLOv4-Tiny algorithm based on attention mechanism is proposed. The structure of the original backbone network of YOLOv4-Tiny algorithm is adjusted, the ECA (efficient channel attention) attention mechanism is introduced, the traditional spatial pyramid pooling (SPP) structure is improved to DC-SPP structure by using void convolution, and the CSATT (channel spatial attention) attention mechanism is proposed. The neck network of CSATT-PAN (channel spatial attention path aggregation network) is formed with the feature fusion network PAN, which improves the feature fusion capability of the network. Compared with the original YOLOv4-Tiny algorithm, the proposed YOLOv4-CSATT algorithm is significantly more sensitive to information and accurate in classification when the detection speed is basically the same. The accuracy is increased by 12.3 percentage points on VOC dataset and 6.4 percentage points is increased on COCO dataset. Moreover, the accuracy is 3.3，5.5，6.3，17.4，10.3，0.9 and 0.6 percentage points higher than the Faster R-CNN, SSD, Efficientdet-d1, YOLOv3-Tiny, YOLOv4-MobileNetv1, YOLOv4-MobileNetv2 and PP-YOLO algorithms respectively on VOC dataset, and 2.8, 7.1, 4.2, 18.0, 12.2, 2.1 and 4.0 percentage points higher in recall rate, respectively, with an FPS of 94. In this paper, the CSATT attention mechanism is proposed to improve the model’s ability to capture spatial channel information, and the ECA attention mechanism is combined with the feature fusion pyramid algorithm to improve the model’s feature fusion ability and target detection accuracy.http://fcst.ceaj.org/fileup/1673-9418/PDF/2301034.pdfobject detection; yolov4-tiny algorithm; attention mechanism; lightweight neural network；feature fusion |
| spellingShingle | HE Xiangjie, SONG Xiaoning Improved YOLOv4-Tiny Lightweight Target Detection Algorithm Jisuanji kexue yu tansuo object detection; yolov4-tiny algorithm; attention mechanism; lightweight neural network；feature fusion |
| title | Improved YOLOv4-Tiny Lightweight Target Detection Algorithm |
| title_full | Improved YOLOv4-Tiny Lightweight Target Detection Algorithm |
| title_fullStr | Improved YOLOv4-Tiny Lightweight Target Detection Algorithm |
| title_full_unstemmed | Improved YOLOv4-Tiny Lightweight Target Detection Algorithm |
| title_short | Improved YOLOv4-Tiny Lightweight Target Detection Algorithm |
| title_sort | improved yolov4 tiny lightweight target detection algorithm |
| topic | object detection; yolov4-tiny algorithm; attention mechanism; lightweight neural network；feature fusion |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2301034.pdf |
| work_keys_str_mv | AT hexiangjiesongxiaoning improvedyolov4tinylightweighttargetdetectionalgorithm |