ZHANG Bin,WEI Wei,HE Bing-qian.An Early Wildfire Smoke Detection Methodbased on Multi-features Fusion[J].Journal of Chengdu University of Information Technology,2018,(04):408-412.[doi:10.16836/j.cnki.jcuit.2018.04.010]
基于多特征融合的早期野火烟雾检测
- Title:
- An Early Wildfire Smoke Detection Methodbased on Multi-features Fusion
- 文章编号:
- 2096-1618(2018)04-0408-05
- Keywords:
- four-frame difference; Gaussian mixture model; multi-features linear fusion; KNN classifier; smoke detection
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- (成都信息工程大学计算机学院,四川 成都 610225)
- Abstract:
- With the development of computer technology, video-based forest fire smoke detection algorithms based on computer vision and pattern recognition have great application prospects. Because the current detection methods are not flexible and recognition rate is not high, this paper proposed a novel wildfire smoke detection algorithm based on multi-features fusion. Firstly, the algorithm extracts the motion foreground by an improved four-frame difference method and Gaussian Mixture Model. Then, the linear combination of smoke color features, wavelet transform analysis and LBP texture features are used to identify the video by multi-feature linear fusion and KNN classifier. Experiments in different video scenes verify the effectiveness of the proposed method in smoke detection.
参考文献/References:
[1] Toreyin B U.Wavelet based real-time smoke detection in video[C].2005 European Signal Processing Conference,2005:1-4.
[2] Krstini D,Stipanicˇev D,Jakovcˇevi T.Histogram-Based Smoke Segmentation in Forest Fire Detection System[J]. Information Technology & Control,2015,38(3):237-244.
[3] Deldjoo Y,Nazary F,Fotouhi A M.A novel fuzzy-based smoke detection system using dynamic and static smoke features[C].Electrical Engineering,2015:729-733.
[4] Cai M.Intelligent video analysis-based forest fires smoke detection algorithms[C].International Conference on Natural Computation,Fuzzy Systems and Knowledge Discovery,2016,1504-1508.
[5] Ko B,Park J,Nam J Y.Spatiotemporal bag-of-features for early wildfire smoke detection[J].Image and Vision Computing,2013,31(10):786-795.
[6] Li S.A novel smoke detection algorithm based on Fast Self-tuning background subtraction[C].Control and Decision Conference,2016:3539-3543.
[7] Yuan F.Real-time image smoke detection using staircase searching-based dual threshold AdaBoost and dynamic analysis[J].Image Processing Iet,2015,9(10):849-856.
[8] Wang Y.Fire smoke detection based on texture features and optical flow vector of contour[C].World Congress on Intelligent Control and Automation,2016:2879-2883.
[9] Li J.A Method of Fire and Smoke Detection Based on Surendra Background and Gray Bitmap Plane Algorithm[C].International Conference on Information Technology in Medicine and Education,2016:370-374.
[10] Stauffer C.Adaptive Background Mixture Models for Real-Time Tracking[C].Proc Cvpr,1999:2246.
[11] 张文,李榕,朱建武.基于混合高斯模型与三帧差分的目标检测算法[J].现代电子技术,2012,35(8):57-60.
[12] Chen T H.An intelligent real-time fire-detection method based on video processing[C].IEEE 2003 International Carnahan Conference on Security Technology,2003. Proceedings,2004:104-111.
[13] 吴爱国,杜春燕,李明.基于混合高斯模型与小波变换的火灾烟雾探测[J].仪器仪表学报,2008,29(8):1622-1626.
[14] Ojala T.Multi-resolution grays-cale and Rotation Invariant Texture Classification with Local Binary Patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,24(7):971-987.
[15] 叶继华,陈亚慧,胡蕾.融合加权颜色相关图和改进LBP的彩色人脸图像识别[J].小型微型计算机系统,2015,36(12):2778-2783.
[16] Yuan Feiniu.A double mapping framework for extraction of shape-invariant features based on multi-scale partitions with AdaBoost for video smoke detection[J].Pattern Recognition,2012,45(12):4326-4336.
备注/Memo
收稿日期:2017-12-13基金项目:四川省教育厅重点科研资助项目(17ZA0064)