Detecting infrared small targets lacking texture and shape information in cluttered environments is extremely challenging. With the development of deep learning, convolutional neural network (CNN)-based methods have achieved promising results in generic object detection. However, existing CNN-based methods with pooling layers may lose the targets in the deep layers and, thus, cannot be directly applied for infrared small target detection. To overcome this problem, we propose an enhanced asymmetric attention (EAA) U-Net. Specifically, we present an efficient and powerful EAA module that uses both same-layer feature information exchange and cross-layer feature fusion to improve feature representation. In the proposed approach, spatial and channel information exchanges occur between the same layers to reinforce the primitive features of small targets, and a bottom-up global attention module focuses on cross-layer feature fusion to enable the dynamic weighted modulation of high-level features under the guidance of low-level features. The results of detailed ablation studies empirically validate the effectiveness of each component in the network architecture. Compared to state-of-the-art methods, the proposed method achieved superior performance, with an intersection-over-union (IoU) of 0.771, normalised IoU (nIoU) of 0.746, and F-area of 0.681 on the publicly available SIRST dataset.

EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection

The detection of small infrared targets lacking texture and shape information in the presence of complex background clutter is a challenge that has attracted considerable research attention in recent years. Typical deep learning-based target detection methods are designed with deeper network structures, which may lose targets in the deeper layers and cannot directly be used for small infrared target detection. Therefore, we designed the attention fusion feature pyramid network (AFFPN) specifically for small infrared target detection. Specifically, it consists of feature extraction and feature fusion modules. In the feature extraction stage, the global contextual prior information of small targets is first considered in the deep layer of the network using the atrous spatial pyramid pooling module. Subsequently, the spatial location and semantic information features of small infrared targets in the shallow and deep layers are adaptively enhanced by the designed attention fusion module to improve the feature representation capability of the network for targets. Finally, high-performance detection is achieved through the multilayer feature fusion mechanism. Moreover, we performed a comprehensive ablation study to evaluate the effectiveness of each component. The results demonstrate that the proposed method performs better than state-of-the-art methods on a publicly available dataset. Furthermore, AFFPN was deployed on an NVIDIA Jetson AGX Xavier development board and achieved real-time target detection, further advancing practical research and applications in the field of unmanned aerial vehicle infrared search and tracking.

/pdf/affpn-attention-fusion-feature-pyramid-network-for-small-2v5yi96j.pdf

AFFPN: Attention Fusion Feature Pyramid Network for Small Infrared Target Detection

Fast and robust detection of a small target in an infrared image is one of the key techniques in infrared search and track systems. The top-hat transformation is an important technology in the field of infrared target detection. Many algorithms have been proposed to improve the top-hat transformation by modifying different structural elements. However, these methods can cause a high false alarm rate under conditions of small dim targets, low signal-to-noise, and complex background. To overcome this limitation, considering both detection performance and speed, an effective and robust detection model using multidirectional structural elements is proposed in this article. First, the nonconcentric multidirectional ring structural elements are designed. Then, using the morphological transformation with designed structural elements, the background is suppressed, and a small target is enhanced in different directions. Finally, the results of the morphological transformations are fused to obtain the final result, further highlighting a small target. The experimental results demonstrate the robust performance of the proposed method for various backgrounds and targets. In addition, the proposed method can achieve a detection speed of up to 10.4 ms per frame under the image resolution of 240 $ \times $ 320 pixels. Therefore, the proposed method is suitable for real-time applications.

/pdf/multidirectional-ring-top-hat-transformation-for-infrared-3uj8nryg07.pdf

Multidirectional Ring Top-Hat Transformation for Infrared Small Target Detection

Modeling and analysis of infrared radiation dynamic characteristics for space micromotion target recognition

In space target recognition using spectral analysis technology, there is the problem that the composition or chemical properties of surface materials of the space target are similar. This problem leads to the high similarity of spectral curves and low accuracy of space target recognition. Similar object recognition is important in the study of actual space target observation. In this paper, an entropy weight fuzzy-rough nearest neighbor (EFRNN) algorithm is proposed to enhance the recognition accuracy of similar space targets, which is an improvement of the fuzzy-rough nearest neighbor algorithm. By introducing the feature weight determined using information entropy, the features of all the training samples are considered and quantified. Moreover, the proposed algorithm combined with fuzzy rough set theory can overcome the fuzzy uncertainty caused by overlapping classes and the rough uncertainty caused by insufficient features, to a certain extent. The simulation results show that the proposed algorithm achieves very promising performance compared with existing algorithms. The EFRNN classifier yields an overall classification accuracy of 95.83%. The proposed algorithm is simple and efficient for similar space target recognition. Furthermore, the EFRNN algorithm does not require preset parameters and complex preprocessing.

Method for Fine Pattern Recognition of Space Targets Using the Entropy Weight Fuzzy-Rough Nearest Neighbor Algorithm

Object discrimination plays an important role in an infrared (IR) imaging system. However, at a long observing distance, the presence of detector noise and the absence of robust features make space objects' discrimination difficult to tackle with. In this paper, a multi-scale convolutional neural network (MCNN) is proposed for feature learning and classification. It consists of three parts: transformation, local convolution, and full convolution. Different from previous objects' classification methods, the MCNN can automatically extract features of objects at multi-timescales and multi-frequencies. Low-level features are combined with high-level features to simultaneously capture long-term tendency and short-term fluctuations of the time sequences of IR radiation intensity. Training data are generated from IR radiation models considering micro-motion dynamics and inherent properties of space point objects under different scenarios. The simulation results indicate that our method not only promotes the performance but is also robust to the detector noise. The classification accuracy can reach 96% at a strong noise level (signal-to-noise ratio is 10 dB) in a simulation scenario.

/pdf/multi-scale-convolutional-neural-networks-for-space-infrared-4pai857p1i.pdf

Fei Zhao

Papers

Multi-Scale Convolutional Neural Networks for Space Infrared Point Objects Discrimination