Lightweight Object Detection Using Quantized YOLOv4-Tiny for Emergency Response in Aerial Imagery
Sindhu Boddu, Arindam Mukherjee

TL;DR
This paper develops a quantized YOLOv4-Tiny model optimized for emergency aerial imagery, achieving significant size and speed improvements while maintaining detection accuracy, suitable for real-time edge deployment.
Contribution
The creation of a new annotated aerial emergency dataset and the optimization of YOLOv4-Tiny through quantization for improved efficiency.
Findings
Model size reduced by 71%
Inference speed increased by 44%
Detection performance comparable to larger models
Abstract
This paper presents a lightweight and energy-efficient object detection solution for aerial imagery captured during emergency response situations. We focus on deploying the YOLOv4-Tiny model, a compact convolutional neural network, optimized through post-training quantization to INT8 precision. The model is trained on a custom-curated aerial emergency dataset, consisting of 10,820 annotated images covering critical emergency scenarios. Unlike prior works that rely on publicly available datasets, we created this dataset ourselves due to the lack of publicly available drone-view emergency imagery, making the dataset itself a key contribution of this work. The quantized model is evaluated against YOLOv5-small across multiple metrics, including mean Average Precision (mAP), F1 score, inference time, and model size. Experimental results demonstrate that the quantized YOLOv4-Tiny achieves…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · UAV Applications and Optimization · Advanced Image and Video Retrieval Techniques
