Flame detection method based on improved RetinaNet network

Abstract

The invention discloses a flame detection method based on an improved RetinaNet network, and the method comprises the steps: S1, collecting N pictures with flame pictures as a training data set, and marking flames in the training data set; S2, a SandGlass module being used for replacing the residual error module, so that an improved RetinaNet network is obtained, and the improved RetinaNet network is recorded as SG-ResNet 50, wherein the SandGlass module comprises a first depth separable convolution, a first convolution, a second convolution and a second depth separable convolution which are connected in sequence; S3, constructing a feature pyramid network, and adding a segmentation branch behind each layer of features output by the feature pyramid network; S4, training the constructed improved RetinaNet network to obtain a trained flame detection model; and S5, carrying out flame detection on the obtained video by adopting the flame detection model obtained in the step S4. According to the invention, the SandGlass module is used for replacing a residual error module of the existing RetinaNet network, so that the flame detection speed is improved; segmented supervision signals are provided by utilizing the color characteristics of flame, and the flame detection precision is improved.

Description

technical field [0001] The invention relates to the technical field of flame detection, in particular to a flame detection method based on an improved RetinaNet network. Background technique [0002] Traditional flame detection techniques usually use artificially extracted features, such as flame texture features, edge features, etc. However, these methods are often slow and have low precision. [0003] With the development of deep learning, more and more people start to use deep learning for flame detection. Compared with traditional methods, the target detection method based on deep learning can improve the speed and accuracy of flame detection, and the generalization performance of the detection model is better, which can be applied to flame detection in various scenarios. [0004] The more popular flame detection methods based on deep learning include two-stage Faster R-CNN and one-stage YOLOv3, SSD, etc. Although Faster R-CNN has high accuracy, its detection speed is ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem of low flame detection accuracy in the prior art, the present invention proposes a flame detection method based on the improved RetinaNet network, by using the SandGlass module to replace the residual module of the existing RetinaNet network, and using the color characteristics of the flame to provide segmentation supervision signal, which reduces the amount of parameters and calculations of the network, thus improving the speed and accuracy of flame detection

Images