3DVSD: An end-to-end 3D convolutional object detection network for video smoke detection

• Published in: Fire safety journal 2022-12, Vol.134, p.103690, Article 103690
• Main Authors: Huo, Yinuo, Zhang, Qixing, Zhang, Yongming, Zhu, Jiping, Wang, Jinjun
• Format: Article
• Language: English
• Subjects: 3D convolutional; Algorithms; Convolution; End-to-end; False alarms; Feature extraction; Information processing; Localization; Neural networks; Object detection; Object recognition; Sequences; Smoke; Spatial data; Tensors; Video frame sequence; Video smoke detection
• ISSN: 0379-7112; 1873-7226
• DOI: 10.1016/j.firesaf.2022.103690

In addition to static features, dynamic features are also important for smoke recognition. 3D convolution can extract temporal and spatial information from video sequences. Currently, for video smoke detection, 3D convolution is usually used as a tool for secondary judgment of the detection results of single frame approaches. In this work, an end-to-end object detection neural network based on 3D convolution for video smoke detection, named 3DVSD, is proposed for the first time. The network captures moving objects from the input video sequences by the dynamic feature extraction part first and then inputs the feature tensor to the static feature extraction part for recognition and localization, which makes full use of the spatiotemporal features of smoke and improves the reliability of the algorithm. In addition, a time-series smoke video dataset for network training is proposed. The proposed algorithm is compared with other related studies. The experimental results demonstrated that the 3DVSD is promising with an accuracy rate of 99.54%, a false alarm rate of 1.11%, and a missed detection rate of 0.14%, and meets the requirements of real-time detection.