Namat Bachir, Qurban Ali Memon. Benchmarking YOLOv5 models for improved human detection in search and rescue missions[J]. Journal of Electronic Science and Technology, 2024, 22(1): 100243
- Journal of Electronic Science and Technology
- Vol. 22, Issue 1, 100243 (2024)
Fig. 1. Proposed approach using YOLOv5.
Fig. 2. Sample dataset images.
Fig. 3. Input and network image resolution: (a) input image resolution and (b) network image resolution.
Fig. 4. Classifier at different IOU thresholds: (a) precision and (b) recall.
Fig. 5. Average precision: (a) precision–to-recall and (b) F 1score.
Fig. 6. Two samples of positive detections with high confidence.
Fig. 7. False detections of YOLOv5L model (shadows, dark areas).
|
Table 1. Network resolution (%) YOLOv5 detection performance.
|
Table 2. Hardware machine specification of Google Collaboratory.
|
Table 3. Comparative results on the SAR dataset.
|
Table 4. Precision-to-recall ratios for different models.
|
Table 5. Performance comparison of YOLOv5 models on the SAR dataset.
|
Table 6. Performance comparison of YOLOv5 models on the HERIDAL dataset.
|
Table 7. Comparison of YOLOv3, YOLOv4, YOLOv5L and faster R-CNN models on the HERIDAL dataset.
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20