Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models

• URL: http://arxiv.org/abs/2608.07554v1
• Date: Sat, 01 Aug 2026 21:43:41 GMT
• Title: Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models
• Abstract summary: This paper investigates the impact of dataset composition on embedded real-time UAV wildfire detection using compact YOLO models.<n>Four training configurations were evaluated: real non-augmented, real augmented, hybrid non-augmented, and hybrid augmented.
• Score: 0.11744028458220425
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The development of vision-based wildfire detection systems for unmanned aerial vehicles is constrained by the limited availability of diverse real-world training images. This paper investigates the impact of dataset composition on embedded real-time UAV wildfire detection using compact YOLO models as a controlled validation family. Four training configurations were evaluated: real non-augmented, real augmented, hybrid non-augmented, and hybrid augmented, where the hybrid sets combine real wildfire images with AI-generated samples. The objective is to determine whether synthetic data mixing and image augmentation improve practical detection performance under resource-constrained deployment conditions. Experimental results show that the best overall operating point was obtained with the real non-augmented dataset, which achieved the strongest balance between recall and mean average precision for UAV-based wildfire detection. The results also show that neither hybridization with synthetic data nor augmentation produced a better final deployment choice. These findings suggest that, for embedded UAV wildfire detection, dataset realism and domain alignment are more valuable than increasing training set size through synthetic expansion.

Related papers

• Training with synthetic data for drone detection in thermal imagery [0.9236074230806578]
  Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging.<n>This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data.
  arXiv  Detail & Related papers  (2026-08-18T13:59:58Z)
• Boosting Robust AIGI Detection with LoRA-based Pairwise Training [55.076681464804636]
  Current AIGI detectors perform admirably on clean datasets, but their detection performance decreases when deployed "in the wild"<n>We propose a novel Lo-based Pairwise Training (RA) strategy designed specifically to achieve robust detection for AIGI under severe distortions.
  arXiv  Detail & Related papers  (2026-04-14T05:35:32Z)
• Sim-to-Real Fruit Detection Using Synthetic Data: Quantitative Evaluation and Embedded Deployment with Isaac Sim [0.0]
  This study investigates the effectiveness of synthetic data for sim-to-real transfer in object detection under constrained data conditions and embedded deployment requirements.<n>Results show that models trained exclusively on real data achieve the highest accuracy, while synthetic-only models exhibit reduced performance due to a domain gap.<n>The trained models were successfully deployed on a Jetson Orin NXRT, achieving real-time inference performance.
  arXiv  Detail & Related papers  (2026-03-30T16:52:29Z)
• Real-Time Monocular Scene Analysis for UAV in Outdoor Environments [0.0]
  We propose a joint deep-learning architecture, named Co-SemDepth, that can perform the two tasks accurately and rapidly.<n>Co-SemDepth is trained on a collected synthetic marine data, called MidSea, and tested on both synthetic and real data.
  arXiv  Detail & Related papers  (2026-03-09T14:08:50Z)
• Generative AI for Enhanced Wildfire Detection: Bridging the Synthetic-Real Domain Gap [0.0]
  Early detection of wildfires is a critical environmental challenge, with timely identification of smoke plumes being key to mitigating large-scale damage.<n>We leverage generative AI techniques to address this data limitation by synthesizing a comprehensive, annotated smoke dataset.<n>We then explore unsupervised domain adaptation methods for smoke plume segmentation, analyzing their effectiveness in closing the gap between synthetic and real-world data.
  arXiv  Detail & Related papers  (2025-09-02T00:40:55Z)
• More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV [58.89234732689013]
  CODrone is a comprehensive oriented object detection dataset for UAVs that accurately reflects real-world conditions.<n>It also serves as a new benchmark designed to align with downstream task requirements.<n>We conduct a series of experiments based on 22 classical or SOTA methods to rigorously evaluate CODrone.
  arXiv  Detail & Related papers  (2025-04-28T17:56:02Z)
• Diffusion-Based Particle-DETR for BEV Perception [94.88305708174796]
  Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV.
  arXiv  Detail & Related papers  (2023-12-18T09:52:14Z)
• UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perception [62.71374902455154]
  We leverage recent advancements in neural rendering to improve static and dynamic novelview UAV-based image rendering. We demonstrate a considerable performance boost when a state-of-the-art detection model is optimized primarily on hybrid sets of real and synthetic data.
  arXiv  Detail & Related papers  (2023-10-25T00:20:37Z)
• Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in Orchards [68.95806641664713]
  We explore the usability of Stable Diffusion 2.1-base for generating synthetic datasets of apple trees for object detection. We train a YOLOv5m object detection model to predict apples in a real-world apple detection dataset. Results demonstrate that the model trained on generated data is slightly underperforming compared to a baseline model trained on real-world images.
  arXiv  Detail & Related papers  (2023-06-20T09:46:01Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.