基于Lazy Snapping混合模拟退火算法的高压开关柜温度场红外三维图像重建仿真

Simulation of Infrared 3D Image Reconstruction of High Voltage Switchgear Temperature Field Based on Lazy Snapping Hybrid Simulated Annealing Algorithm

提出基于Lazy Snapping混合模拟退火算法的高压开关柜温度场红外三维图像重建仿真方法,以提升高压开关柜温度场仿真效果。该方法利用主动式红外图像传感器采集高压开关柜温度场红外图像后,使用直方图非线性拉伸算法对其实施增强处理;再使用Lazy Snapping算法对增强后的高压开关柜温度场红外图像进行分割,并通过混合遗传模拟退火算法合成二维纹理流场图像;以该图像为基础,使用Image Quiltingh纹理合成算法合成高压开关柜温度场三维图像,完成高压开关柜温度场红外三维图像重建仿真过程。实验结果表明:该方法可有效增强高压开关柜温度场红外图像,其分割红外图像时的交并比数值接近1.0;可依据其生成的二维纹理流场图像生成三维图像,温度场仿真数值最大偏差仅为0.03℃。

A simulation method for the infrared three-dimensional(3D)image reconstruction of a high-voltage switchgear temperature field based on a lazy snapping hybrid simulated annealing algorithm is proposed to improve the simulation effect of the high-voltage switchgear temperature field.In this method,the active infrared image sensor was used to collect an infrared image of the temperature field of a high-voltage switchgear,and the square-graph nonlinear stretching algorithm was used to enhance it.Subsequently,the enhanced infrared image was segmented by lazy snapping algorithm,and the two-dimensional texture flow-field image was synthesized by a hybrid genetic simulated annealing algorithm.Based on the image,an image quilting texture synthesis algorithm was used to synthesize the 3D image of the high-voltage switchgear temperature field,and the infrared 3D image reconstruction simulation process of the temperature field was completed.The experimental results demonstrated that this method effectively enhanced the infrared image of the temperature field of a high-voltage switchgear,and the intersection and union ratio of the segmented infrared image had a value that was approximately 1.0.The 3D image was effectively generated according to the generated two-dimensional texture flow-field image,and the maximum deviation of the temperature field simulation value was only 0.03℃.