Summary of Object Detection in Thermal Images Using Deep Learning For Unmanned Aerial Vehicles, by Minh Dang Tu et al.
Object Detection in Thermal Images Using Deep Learning for Unmanned Aerial Vehicles
by Minh Dang Tu, Kieu Trang Le, Manh Duong Phung
First submitted to arxiv on: 13 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a neural network model capable of detecting small and tiny objects in thermal images taken by drones. The architecture consists of three parts: the backbone, neck, and prediction head. The backbone combines YOLOv5’s structure with a transformer encoder, while the neck incorporates a BI-FPN block, sliding window, and transformer to enhance information flow into the prediction head. The prediction head performs detection using the Sigmoid function on feature maps. The use of transformers and sliding windows improves accuracy while keeping the model feasible for embedded systems. Experiments on public datasets VEDAI and private collections demonstrate higher accuracy compared to state-of-the-art methods like ResNet, Faster RCNN, ComNet, ViT, YOLOv5, SMPNet, and DPNetV3. The model achieves real-time computation speed with a stability rate of over 90% on the Jetson AGX embedded computer. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it possible for drones to recognize small objects in thermal images using artificial intelligence. The AI model has three parts that work together to detect things. It uses special structures called transformers and sliding windows to help it recognize objects better. The model is tested on different datasets and performs well compared to other state-of-the-art models. It also works quickly enough to be used in real-time applications. |
Keywords
* Artificial intelligence * Encoder * Faster rcnn * Neural network * Resnet * Sigmoid * Transformer * Vit
