Opto-Electronic Engineering, Volume. 49, Issue 3, 210372-1(2022)
Real-time object detection for UAV images based on improved YOLOv5s
Figures & Tables(17)
Fig. 6. (a) Total number of category instances on the VisDrone dataset; (b) Classes confusion matrix of YOLOv5m algorithm
Fig. 7. The detection examples of different algorithms in the VisDrone UAV scene. (a) YOLOv5m model; (b) YOLOv5sm+ model; (c) YOLOv5s model
Fig. 8. Comparison of the detection effects of three algorithms in dense vehicle scenes. (a) YOLOv5m; (b) YOLOv5s; (c) YOLOv5sm+
Fig. 9. Detection comparison of improved algorithm in DIOR dataset. (a) YOLOv5s; (b) YOLOv5sm+
Table 1. Receptive field analysis table
View tableView in ArticleTable 1. Receptive field analysis table
YOLOv5s 感受野 通道 YOLOv5sm 感受野 通道 Focus 6 32 Conv 3*3 (stride:2) 3 24 Conv3*3 (dilation:2) 15 48 下采样 10 64 Conv3*3 (stride:2) 19 96 Res-Block 27 96 C3_x1 18 64 Res-Dconv 51 96 下采样 26 128 Conv 3*3 (stride:2) 59 192 C3_x3 74 128 C3_x3 107 192 下采样 90 256 Conv3*3 (stride:2) 123 384 C3_x3 186 256 C3_x3 219 384 下采样 218 512 Conv3*3 (stride:2) 251 768 Spp 218~634 512 Spp 251~667 768 C3_x1 282~698 512 C3_x1 315~731 768
Table 2. Pre-setting anchors in response to the receptive field and down-sampling
View tableView in ArticleTable 2. Pre-setting anchors in response to the receptive field and down-sampling
下采样因子 3 4 5 最大感受野/pixel 111 255 731 先验框范围 8*8~37*37 32*32~85*85 96*96~365*365
Table 3. Statistics of different types of objects
View tableView in ArticleTable 3. Statistics of different types of objects
目标种类 Small (0×0~32×32) Mid (32×32~96×96) Large (96×96~) 数量 44.44 18.63 1.704
Table 4. Performance comparison experiment results of depth and width models
View tableView in ArticleTable 4. Performance comparison experiment results of depth and width models
深度 宽度 mAP50 mAP BFLOPs 0.33 0.5 0.502 0.288 16.5 0.33 0.75 0.540 0.319 36.3 1.33 0.5 0.525 0.311 35.4
Table 5. Verification experiment results on Res-Dconv module
View tableView in ArticleTable 5. Verification experiment results on Res-Dconv module
Baseline Res-Dconv mAP50 mAP BFLOPs √ 0.502 0.288 16.5 √ √ 0.516 0.299 19.8
Table 6. The ablation experiment results of our algorithm modules on the VisDrone dataset
View tableView in ArticleTable 6. The ablation experiment results of our algorithm modules on the VisDrone dataset
Baseline SM SCAM SDCM mAP mAP50 BFLOPs Infer AP-small AP-medium AP-large 注：加粗字体为该列最优值。 YOLOv5s 0.319 0.548 16.5 4.8 0.220 0.437 0.495 √ 0.358 0.589 30.1 8.3 0.280 0.476 0.495 √ √ 0.324 0.555 14.7 3.8 0.225 0.446 0.511 √ √ 0.333 0.555 19.5 4.9 0.250 0.448 0.482 √ √ 0.356 0.593 38.0 9.0 0.278 0.475 0.512 √ √ √ 0.360 0.596 30.8 7.7 0.281 0.479 0.505
Table 7. Detection performance of different algorithms on VisDrone dataset
View tableView in ArticleTable 7. Detection performance of different algorithms on VisDrone dataset
算法 mAP50 mAP mAP75 AP-small AP-mid AP-large BFLOPs Infer/ms 注：+为添加改进模块的模型，*为多尺度测试结果，包含引用文献实验结果。 YOLOv3 0.609 0.389 0.417 0.297 0.496 0.545 154.9 27.8 Scaled-YOLOv4 0.620 0.400 0.428 0.305 0.514 0.626 119.4 27.1 ClusDet[ 1 ]0.562 0.324 0.316 - - - - - HRDNet[ 1 ]0.620 0.3551 0.351 - - - - - YOLOv5s 0.548 0.319 0.317 0.220 0.437 0.495 16.5 4.8 YOLOv5m 0.595 0.365 0.372 0.285 0.482 0.525 50.4 9.8 YOLOX-s 0.535 0.314 0.317 0.225 0.415 0.485 41.65 5.1 MobileNetv3 0.554 0.329 0.329 0.245 0.443 0.495 23.8 8.0 MobileViT 0.555 0.333 0.337 0.249 0.442 0.418 - 13.7 YOLOv5sm+ 0.596 0.360 0.369 0.281 0.479 0.505 30.8 7.7 YOLOv5sm+* 0.606 0.367 0.378 0.295 0.478 0.439 - -
Table 8. Detection performance of different algorithms on DIOR dataset
View tableView in ArticleTable 8. Detection performance of different algorithms on DIOR dataset
模型 BackBone mAP50 注：加粗字体为该列最优值，包含其他文献对比结果。 Faster R-CNN[ 33 ]VGG16 0.541 PANet[ 20 ]ResNet50 0.638 Retina-Net[ 24 ]ResNet50 0.685 文献[ 32 ]ResNet50 0.732 CAT-Net[ 34 ]ResNet50 0.763 YOLOv5sm+(ours) - 0.667
Tools
Get Citation
Copy Citation Text
Xu Chen, Dongliang Peng, Yu Gu. Real-time object detection for UAV images based on improved YOLOv5s[J]. Opto-Electronic Engineering, 2022, 49(3): 210372-1
Paper Information
Category:
Received: Nov. 22, 2021
Accepted: --
Published Online: Apr. 24, 2022
The Author Email: Yu Gu (guyu@hdu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20