Paying more attention to local contrast: Improving infrared small target detection performance via prior knowledge

Abstract

The data-driven methods for InfraRed Small Target Detection (IRSTD) have achieved promising results. However, these methods typically incorporate modules with high computational complexity, which enhance performance at the expense of computational efficiency. Utilizing human expert knowledge to assist data-driven methods in better learning with less costs is worthy of exploration. To effectively guide the model to focus on targets’ spatial features, this paper proposes the Local Contrast Attention Enhanced infrared small target detection Network (LCAE-Net), combining prior knowledge with data-driven deep learning methods. LCAE-Net is a U-shaped neural network model which consists of two developed modules: a Local Contrast Enhancement (LCE) module and a Channel Attention Enhancement (CAE) module. The LCE module takes advantage of prior knowledge, leveraging handcrafted convolution operators to acquire Local Contrast Attention (LCA), which could realize background suppression while enhancing the potential target region, thus guiding the neural network to pay more attention to potential infrared small targets’ location information. To effectively utilize the response information throughout the downsampling progresses, the CAE module is proposed to achieve the information fusion among feature maps’ different channels. Experimental results indicate that our LCAE-Net outperforms comparison methods on the three public datasets, and its detection speed could reach up to 70 Frames Per Second (FPS). Meanwhile, our model has a parameter count and Floating-Point Operations (FLOPs) of 1.945 Million (M) and 4.862 Giga (G) respectively, which is suitable for deployment on edge devices. Our code will be available at https://github.com/boa2004plaust/LCAENet.