Fire must be extinguished early, as it leads to economic losses and losses of precious lives.\nVision-based methods have many difficulties in algorithm research due to the atypical nature fire\nflame and smoke. In this study, we introduce a novel smoke detection algorithm that reduces false\npositive detection using spatial and temporal features based on deep learning from factory installed\nsurveillance cameras. First, we calculated the global frame similarity and mean square error (MSE) to\ndetect the moving of fire flame and smoke from input surveillance cameras. Second, we extracted\nthe fire flame and smoke candidate area using the deep learning algorithm (Faster Region-based\nConvolutional Network (R-CNN)). Third, the final fire flame and smoke area was decided by local\nspatial and temporal information: frame difference, color, similarity, wavelet transform, coefficient of\nvariation, and MSE. This research proposed a new algorithm using global and local frame features,\nwhich is well presented object information to reduce false positive based on the deep learning method.\nExperimental results show that the false positive detection of the proposed algorithm was reduced\nto about 99.9% in maintaining the smoke and fire detection performance. It was confirmed that the\nproposed method has excellent false detection performance.
Loading....