基于红外与可见光图像融合的目标检测算法

Target detection algorithm based on infrared and visible light image fusion

为了解决红外与可见光图像融合在光线不足的情况下,融合图像纹理细节较弱、算法识别能力差等问题,提出了一种基于红外与可见光图像融合的目标检测算法。设计了QDOB模块分别用于提取两种图像的特征,从而获得丰富信息的融合图像。将融合图像送入YOLOv5网络中训练得到检测模型。实验结果表明,该文融合算法要优于传统的融合算法,并且通过网络训练出的检测模型精度由源图像的67.23%提升到84.79%,能够达到实时检测的需求。

In order to solve the problems of infrared and visible light image fusion in the case of insufficient light,the texture details of the fused image are weak,and the algorithm recognition ability is poor,this paper proposes a target detection algorithm based on infrared and visible light image fusion.The QDOB module is designed to extract the features of the two kinds of images respectively,so as to obtain the fused image with rich information.The fusion image is sent to the YOLOv5 network to train the detection model.The experimental results show that the fusion algorithm of this paper is superior to the traditional fusion algorithm,and the accuracy of the trained detection model is increased from 67.23%of the source image to 84.79%,which can meet the needs of real⁃time detection.