Robust aerial infrared target recognition with multi-scale and multi-angle characteristics is a key technique in infraredsystems. However, traditional algorithms often fail to achieve a high accuracy and robustness due to simple features andclassifiers. Moreover, deep learning algorithms mainly focus on improving accuracy with the price of high complexity.To address above issues, we propose a two-stage lightweight aerial infrared target recognition based on convolutionalneural networks(CNN). We propose the coarse region extraction based on the local contrast in the first stage, whichcombines infrared image characteristics properly. In the second stage, we propose the find target recognition, whichconstructs lightweight CNN by changing network layers and convolution kernels. Experimental results demonstrate thealgorithm proposed can achieve recognition for six kinds of aerial infrared target. Compared with other algorithms, ouralgorithm obtains higher accuracy and robustness.
展开▼
