Research Article 
A Vector Quantization Based Automatic Fire Detection System
Yu-Chun Wen, Fa-Xin Yu, Xiao-Lin Zhou and Zhe-Ming Lu
Information Technology Journal, 2010, 9(4), 758-765.
Abstract
This study presents a novel fire detection method based on vector quantization. Before online fire detection, we generate a fire codebook and a non-fire codebook by the LBG algorithm based on the training set that are selected from 10 video clips under different scenes and conditions. For encoding convenience, we merged the two codebooks into one codebook and sorted the codewords in the ascending order of their mean values for the future Equal-average Equal-variance Equal-norm Nearest Neighbor Search (EEENNS) based fast encoding process. In the online fire detection process, the video to be detected was first segmented into successive frames and we performed the VQ (Vector Quantization) encoding process to find fire-colored frames and recorded the grade of each fire-colored area. Then, the moving pixel detection process was performed on each fire-colored frame to find candidate fire frames. Finally, we verified whether a fire occurs or not and graded the fire by analyzing the change in the number of blocks belonging to each grade between consecutive frames. Experimental results demonstrated the effectiveness of the proposed scheme and a 93.3% detection rate was obtained with 25 test video clips.
ASCI-ID: 28-1025
Related Articles
Improving Speaker Verification in Noisy Environments using Adaptive Filtering and Hybrid Classification Technique
Information Technology Journal, 2010, 9(1), 107-115.
Realization of a Covert Communication System Over the Public Switching Telephone NetworkInformation Technology Journal, 2009, 8(8), 1140-1149.
3D Mesh Compression by Generalized Parallelogram Predictive Vector QuantizationInformation Technology Journal, 2011, 10(4), 877-882.
Robust Speech Feature Prediction Using Mel-LPC to Improve Recognition AccuracyInformation Technology Journal, 2012, 11(11), 1644-1649.
A Tool for Compressing Images Based on Genetic AlgorithmInformation Technology Journal, 2007, 6(3), 457-462.
Lossless Image Coding Using Conditional Entropy Constrained Vector QuantizationInformation Technology Journal, 2006, 5(6), 1136-1139.