Download presentation
Presentation is loading. Please wait.
Published byAlexis James Modified over 5 years ago
1
A Novel Smoke Detection Method Using Support Vector Machine
By Mounica
2
Content: Purpose of the paper Introduction Technical Aspects Results
Conclusion Drawbacks and Future Work
3
Early Fire detection is a big problem in large facilities like port facilities, large factories and power plants to keep them safe, due to its large harmful effect to surrounding areas. In such areas Smoke is an important and useful sign to detect fire. The Paper aims on a novel and robust smoke detection methods based on image information. Purpose Of The Paper
4
Introduction Previous approaches of the smoke detection, using pixel and block-based, or color-based image processing methods detect edge or contour information of smoke. In this paper novel smoke detection method is being presented with the image information obtained from the surveillance cameras. In the pre-processing stage moving objects are detected as smoke regions. Texture analysis and non-linear classiο¬cation with SVM to extract smoke regions in image sequences is used here.
5
Technical Aspects Pre-Processing:
This is an important step before we proceed towards the smoke detection method. In this step moving objects are detected from the images as smoke regions with the help of some methods Subtraction and Accumulation : A subtracted image frame is written as π(π‘)=π(π‘)βπ(π‘β1) Smoke is not clear in the subtracted image So, we use β(π‘) which combines two subtracted images, i.e. β(π‘)= β£π(π‘)+π(π‘β1)β£
6
Technical Aspects (contd.β¦..)
7
Technical Aspects (contd.β¦..)
Binarization and Morphological operation: Binarization and Morphological operations are done to remove noise like regions in the binary images. Binarization is the process of converting an image into black and white image by choosing a threshold value. That is β(π‘) is converted to π(π‘) binary images. Otsuβs method is used to choose a threshold Morphological operations probe an image with a small shape or template called aΒ structuring element. The structuring element is positioned at all possible locations in the image and it is compared with the corresponding neighbourhood of pixels. Some operations test whether the element "fits" within the neighbourhood, while others test whether it "hits" or intersects the neighbourhood. A morphological operation on a binary image creates a new binary image in which the pixel has a non- zero value only if the test is successful at that location in the input image.
8
Technical Aspects (contd.β¦..)
Extraction of Feretβs regions: In this to determine the shape and position of the moving objects Feretβs diameter is extracted as a circumscribed rectangle whose horizontal and vertical lengths are Feretβs diameter. We obtain the position and the approximated shape of the object as the rectangle thgis is called Feretβs region F(π‘;π).
9
Technical Aspects (contd.β¦..)
Texture Features: After detecting Feretβs region texture patterns of smoke are collected as feature vectors. The texture feature is stored in a coβ occurrence matrix, so it does not depend on the visible size of smoke in images. So, texture features are very useful for the method of detection. Technical Aspects (contd.β¦..)
10
Technical Aspects (contd.β¦..)
Methodology: SVM(Support Vector Machine): A Support Vector Machine (SVM) is a discriminative classifier formally defined by a separating hyperplane. In other words, given labeled training data (supervised learning), the algorithm outputs an optimal hyperplane which categorizes new examples. In two dimensional space this hyperplane is a line dividing a plane in two parts where in each class lay in either side. We use texture features as input vector to SVM We use nonβlinear kernel (RBF kernel) of SVM as πΎ(π₯π,π₯) = exp(βπΎβ£β£π₯π βπ₯β£β£2) , where π₯π β β14 is a texture feature vector of a Feretβs region.
11
Technical Aspects (contd.β¦..)
To train the SVM, we prepare manually selected Feretβsβ region of smoke, which we call ideal smoke. Using trained SVM, we discriminate whether Feretβsβ regions are smoke or not. If the SVMβs output is smoke, we set the label ππ(π₯,π¦;π‘) of the point (π₯,π¦) in the Feretβsβ region to be 1 and else to be 0. ππ(π₯,π¦;π‘)= 1((π₯,π¦) ππ π ππππ.) and 0(πππ π) In real-time situation along with smoke there may be many moving objects as noise in the image. To obtain the accurate result of the smoke detection, we consider to accumulate the labeling results ππ(π₯,π¦;π‘) with SVM about time. The accumulation is deο¬ned as follows: ππ(π₯,π¦;π‘)= β π‘=π π+ππ ππ(π₯,π¦;π‘) When there exist a point (π₯,π¦) whose ππ(π₯,π¦;π‘) is higher than the manually selected threshold, all Feretβs regions which contain that point discriminated as smoke at time π‘ is extracted.
12
Results Experiment 1:
13
Results Experiment 1(contdβ¦):
14
Results
15
Results:
16
Conclusion Thus the paper presents the novel smoke detection method based on the texture analysis and the support vector classiο¬er. Focusing on the image information of smoke as the texture pattern, which does not affect the size of smoke in the images. For the evaluation the method, we examine it with some examples of image sequences. In the experiments, there exist smoke and other moving objects which are considered as obstructions in image sequences. Experimental results show the effectiveness of our method under general conditions.
17
Drawbacks and Future work
The method is not evaluated for different types of smoke. To use this method in real situation, we must compile the smoke detection system with other systems. One way is to combine our method with multi camera system to cover the wide target area.
18
Thank You!!!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.