目录
1.1 MIVIA Fire Detection Dataset
1.2 FireNet-LightWeight-Network-for-Fire-Detection
1.3 Fire Flame Dataset(Deep Quest AI)
2.1 FIRESENSE Database
2.2 furg-fire-dataset-master (Hüttner et al.)
2.3 CVPR Lab ——KMU Fire and Smoke database
2.4 BoWFireDataset (Chino et al.)
2.5 Sharma's Dataset (Sharma et al.)
【若觉文章质量良好且有用,请别忘了点赞收藏加关注,这将是我继续分享的动力,万分感谢!】
网址:
Sample Fire and Smoke Video Clips
数据描述:
12 个火的视频,无标注,还有其他的烟雾视频
论文:
Improving fire detection reliability by a combination of videoanalytics. In: Image analysis and recognition
Real-time fire detection for video-surveillance applications using a combination of experts based on color, shape, and motion
网址:
https://github.com/arpit-jadon/FireNet-LightWeight-Network-for-Fire-Detection
数据描述:
46 个火的视频,16 个非火的视频,160 张非火的图片,无标注
论文:
Firenet: a specialized lightweight fire & smoke detection model for real-time iot applications
网址:
https://github.com/DeepQuestAI/Fire-Smoke-Dataset
数据描述:
Train: 火图片 900、中性图 900、烟雾图 900
Test:火图片 100、中性图 100、烟雾图 100
提出单位:Deep Quest AI
网址:
FIRESENSE database of videos for flame and smoke detection | Zenodo
数据描述:
火焰:11 个火的视频,16 个非火的视频
烟雾:13 个烟雾视频,9 个非烟雾视频
论文:
网址:
https://github.com/steffensbola/furg-fire-dataset
数据描述:
23 个视频,带有标注文件,标注信息为(int x, int y, int width, int height)
论文:
2017
First response fire combat: Deep leaning based visible fire detection
V. Hüttner, C. R. Steffens and S. Silva da Costa Botelho, "First response fire combat: Deep leaning based visible fire detection," 2017 Latin American Robotics Symposium (LARS) and 2017 Brazilian Symposium on Robotics (SBR), Curitiba, 2017, pp. 1-6, doi: 10.1109/SBR-LARS-R.2017.8215312.
2016
A Texture Driven Approach for Visible Spectrum Fire Detection on Mobile Robots
2015
An Unconstrained Dataset for Non-Stationary Video Based Fire Detection
2016
Non-stationary VFD Evaluation Kit: Dataset and Metrics to Fuel Video-Based Fire Detection Development
网址:
Computer Vision and Pattern Recognition Laboratory Homepage
数据描述:
Wildfire_smoke:4 个视频
Smoke_flame_like_moving_object:10 个视频
Indoor_outdoor(short_distance)smoke:2 个视频
Indoor_outdoor(short_distance)flame:22 个视频
相对比较模糊,历史比较悠久
单位:Computer Vision and Pattern Recognition Laboratory, Keimyung University, Korea
论文:Byoung Chul Ko, Jun-Yong Kwak, Jae-Yeal Nam, "Wildfire Smoke Detection using Temporal-Spatial Features and Random Forest Classifiers," Optical Engineering, Vol. 51, No. 01. ,pp.017208-1 - 017208-10, Jan. 2012.
网址:
gbdi / BowFire Dataset / Downloads — Bitbucket
数据描述:
有两个数据集
trainset:80 张火图,80 张正常图、80 张烟雾图
dataset:119 张火图(带二值图)、107 张非火图(带二值图)
论文:BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis. [Daniel Y. T. Chino and Letricia P. S. Avalhais]
链接: https://github.com/UIA-CAIR/Fire-Detection-Image-Dataset
训练集:59 火图,490 非火图(共 549 张图)
测试集:51 火图、51 非火图(共 102 张图)
论文:Deep Convolutional Neural Network for Fire Detection in Images
【若觉文章质量良好且有用,请别忘了点赞收藏加关注,这将是我继续分享的动力,万分感谢!】