Flame Edge Detection Method Based on a Convolutional Neural Network

Haoliang Sun; Xiaojian Hao; Jia Wang; Baowu Pan; Pan Pei; Bin Tai; Yangcan Zhao; Shenxiang Feng

doi:10.1021/acsomega.2c02858

Flame Edge Detection Method Based on a Convolutional Neural Network

ACS Omega. 2022 Jul 22;7(30):26680-26686. doi: 10.1021/acsomega.2c02858. eCollection 2022 Aug 2.

Authors

Haoliang Sun^{1

2}, Xiaojian Hao^{1

2}, Jia Wang^{2

3}, Baowu Pan⁴, Pan Pei^{1

2}, Bin Tai^{1

2}, Yangcan Zhao⁴, Shenxiang Feng^{1

2}

Affiliations

¹ Science and Technology on Electronic Test and Measurement Laboratory, North University of China, Taiyuan 030051, China.
² School of Instrument and Electronics, North University of China, Taiyuan 030051, China.
³ Shanxi Key Laboratory of Signal Capturing & Processing, North University of China, Taiyuan, Shanxi Province 030051, China.
⁴ School of Materials Science and Engineering, North University of China, Taiyuan 030051, China.

Abstract

In this study, an improved flame edge detector based on convolutional neural network (CNN) was proposed. The proposed method can generate edge graphs and extract edge graphs relatively effectively. Our network architecture was based on VGG16 primarily, the last two max-pooling operators and all full connection layers of the VGG16 network were deleted, and the rest was taken as the basic network. The images output by the five convolution layers were upsampled to the size of the input images and finally fused to the edge image. Error calculation and back propagation of the fusion image and label image are carried out to form a weakly supervised model. Using the open datasets BSDS500 to train the network, the ODS F-measure can reach 0.810. Various experiments were carried out on different flame and fire images, including butane-air flame, oxygen-ethanol flame, energetic material flame, and oxygen-acetylene premixed jet flame, and the infrared thermogram was also verified by our method. The results demonstrate the effectiveness and robustness of the proposed algorithm.