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.