| |
|
|
Introduction |
| |
|
|
You can down load these videos and images freely only for research purposes. Any commerical use is not allowed before we agree.
Please cite the corresponding article in your publications if the data set helps your research.
|
 |
| |
|
Smoke detection in video sequences based on dynamic texture using volume local binary patterns
(accepted by KSII Transactions on Internet & Information Systems PDF) |
| |
|
|
Smoke videos used in "Smoke detection in video sequences based on dynamic texture using volume local binary patterns": train_set consisted of 10 smoke videos and 5 non-smoke videos,
test_set contained another 10 smoke videos that are similar to the train_set and the same 5 non-smoke videos in the train_set. block_label consisted the labels of smoke blocks and nonsmoke blocks in video_train_set. |
| |
|
Deep Domain Adaptation Based Video Smoke Detection using Synthetic Smoke Images
(Fire Safety Journal, 2017, 93:53-59. PDF)£¨preprint in arxiv PDF) |
| |
|
|
Smoke videos used in "Deep Domain Adaptation Based Video Smoke Detection using Synthetic Smoke Images": The test_set contains 500 smoke images(testsmoke) and 500 non-smoke images(testnon);
The train_synthetic_smoke_set are produced by Blender-python.The train_real_smoke_set are captured by ourselves. The background images and non-smoke images are collected from ImageNet. We render each frame of smoke image with a new background image. The parameters of rendering, lighting and wind are set randomly in a certain range for diversity. We give a reference - smoke.blend for parameter sets of smoke rendering. As differnet sets of the parameters influence directly the appearance of synthetic smoke images, these images will be realistic or non-realistic.
Experiment showed that the non-realistic synthetic smoke images works just as well as more realistic synthetic smoke images. |
| |
|
Adversarial Adaptation From Synthesis to Reality in Fast Detector For Smoke Detection
(preprint in arxiv PDF£© |
| |
|
|
The source (synthetic smoke samples) dataset: synthetic_set contains 30000 images.The target (real smoke samples) dataset: real_set contains 2549 images. The test dataset: test_set contains 1029 images.
|
| |
|
Video Smoke Detection Base on Deep Saliency Network
preprint in arxiv PDF |
| |
|
|
The dataset used in "Deep Network for Salient Smoke Detection": The initial_test_set contains 1399 smoke images and 1401 non-smoke images; The initial_train_set contains 1401 smoke images and 1499 non-smoke images.
The augment_test_set contains 1399 smoke images and 1212 non-smoke images;
The augment_train_set contains 5596 smoke images and 4852 non-smoke images.
|
| |
|
| |
|
|
Smoke Detection Based on Scene Parsing and Salienct Segmentation |
| |
|
|
The dataset used in "Smoke Detection Based on Scene Parsing and Saliency Segmentation": The The dataset for wildfire smoke detection contains 4695 images, which consists of 2695 images for training and 2000 images for test. Our dataset is mainly for the wild scene, composed from the video shot through video surveilance cameras in lookout towers and unmanned aerial vehicle (UAV).
|
| |
|
| |
|
Wildland Forest Fire Smoke Detection Based on Faster R-CNN using Synthetic Smoke Images
Procedia Engineering Volume, 2018, 211:441-446 PDF |
| |
|
|
The Real smoke + Forest background dataset: RF_dataset contains 12620 images; The Simulative smoke + Forest background dataset: SF_dataset SF_dataset also contains 12620 images.
|
| |
|
|
donglv1 donglv2
|
| |
|
