一种干扰环境下线阵复合成像引信目标识别算法

In order to address the issue of the poor target recognition performance of laser imaging fuze under smoke,dust,and camouflage interference,a target recognition algorithm using linear array laser and linear array near-infrared compound imaging is proposed. A calibration matrix is established according to the imaging model,and the spatial mapping relationship between the laser point cloud and the near-infrared image is obtained. A deep learning-based target recognition algorithmic framework is constructed, and a voxel fusion module is proposed at the data input layer to enhance the point cloud by encoding near-infrared pixel-level features. A BEV fusion module is proposed at the middle layer to achieve feature-level fusion with adaptive dynamic adjustment of bimodal feature weights. The proposed algorithm is validated based on a custom simulation dataset. The experimental results show that the proposed algorithm can significantly improve the accuracy of target recognition under smoke,dust and camouflage interference.