Infrared Small Target Detection Based on Dilated Convolutional Conditional Generative Adversarial Networks
Deep-learning based object detection methods have achieved great performance in general object detection tasks by vir-tue of their powerful modeling capabilities.However,the design of deeper network and the abuse of pooling operations also lead to semantic information loss which suppress their performance when detecting infrared small targets with low signal-noise-ratio and small pixel essential features.This paper proposes a novel infrared small target detection algorithm based on dilated convolu-tion conditional generative adversarial network.A dilated convolution stacked generative network makes full use of context infor-mation to establish layer-to-layer correlations and facilitate semantic information retainment of infrared small targets in the deep network.In addition,the generative network integrates the channel-space-mixed attention module which selectively amplifies tar-get information and suppresses background clusters.Furthermore,a self-attention association module is proposed to deal with se-mantic conflict generated during the fusion process between layers.A variety of evaluation metrics are used to compare the pro-posed method with other state-of-the-arts at present to demonstrate the superiority of the proposed method in complex back-grounds.On the public SIRST dataset,the F score of the proposed model is 64.70％which is 8.29％higher than the traditional method and 7.29％higher than the deep learning method.On the public ISOS dataset,the F score is 64.54％,which is 23.59％higher than the traditional method and 6.58％higher than the deep learning method.
Infrared small target detectionConditional generative adversarial networkFeature fusionAttention mechanismDi-lated convolution
万方数据
维普
