Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.09300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909645843464192 |
|---|---|
| author | Boddu, Sindhu Mukherjee, Arindam |
| author_facet | Boddu, Sindhu Mukherjee, Arindam |
| contents | This paper presents the deployment and performance evaluation of a quantized YOLOv4-Tiny model for real-time object detection in aerial emergency imagery on a resource-constrained edge device the Raspberry Pi 5. The YOLOv4-Tiny model was quantized to INT8 precision using TensorFlow Lite post-training quantization techniques and evaluated for detection speed, power consumption, and thermal feasibility under embedded deployment conditions. The quantized model achieved an inference time of 28.2 ms per image with an average power consumption of 13.85 W, demonstrating a significant reduction in power usage compared to its FP32 counterpart. Detection accuracy remained robust across key emergency classes such as Ambulance, Police, Fire Engine, and Car Crash. These results highlight the potential of low-power embedded AI systems for real-time deployment in safety-critical emergency response applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09300 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Edge Deployment of Quantized YOLOv4-Tiny for Aerial Emergency Object Detection on Raspberry Pi 5 Boddu, Sindhu Mukherjee, Arindam Computer Vision and Pattern Recognition This paper presents the deployment and performance evaluation of a quantized YOLOv4-Tiny model for real-time object detection in aerial emergency imagery on a resource-constrained edge device the Raspberry Pi 5. The YOLOv4-Tiny model was quantized to INT8 precision using TensorFlow Lite post-training quantization techniques and evaluated for detection speed, power consumption, and thermal feasibility under embedded deployment conditions. The quantized model achieved an inference time of 28.2 ms per image with an average power consumption of 13.85 W, demonstrating a significant reduction in power usage compared to its FP32 counterpart. Detection accuracy remained robust across key emergency classes such as Ambulance, Police, Fire Engine, and Car Crash. These results highlight the potential of low-power embedded AI systems for real-time deployment in safety-critical emergency response applications. |
| title | Efficient Edge Deployment of Quantized YOLOv4-Tiny for Aerial Emergency Object Detection on Raspberry Pi 5 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.09300 |