Deyong Lu

Infrared moving small target detection is an important and challenging task in infrared search and track system, especially in the case of low signal-to-clutter ratio (SCR) and complex scenes. The spatial–temporal information has not been fully utilized, and there is a serious imbalance in their exploitation, especially the lack of long-term temporal characteristics. In this article, a novel method based on the spatial–temporal feature fusion tensor model is proposed to solve these problems. By directly stacking raw infrared images, the sequence can be transformed into a third-order tensor, where the spatial–temporal features are not reduced or destroyed. Its horizontal and lateral slices can be viewed as 2-D images, showing the change of gray values of horizontal/vertical fixed spatial pixels over time. Then, a new tensor composed of several serial slices are decomposed into low-rank background components and sparse target components, which can make full use of the temporal similarity and spatial correlation of background. The partial tubal nuclear norm is introduced to constrain the low-rank background, and the tensor robust principal component analysis problem is solved quickly by the alternating direction method of multipliers. By superimposing all the decomposed sparse components into the target tensor, small target can be segmented from the reconstructed target image. Experimental results of synthetic and real data demonstrate that the proposed method is superior to other state-of-the-art methods in visual and numerical results for targets with different sizes, velocities, and SCR values under different complex backgrounds.

Infrared small target detection is an important and core problem in infrared search and track systems. Many infrared small target detection methods work well under the premise of a static background; however, the detection effect decreases seriously when the background changes dynamically. In addition, the spatiotemporal information of the target and background of the image sequence are not fully developed and utilized, lacking long-term temporal characteristics. To solve these problems, a novel long-term spatial–temporal tensor (LSTT) model is proposed in this paper. The image registration technique is employed to realize the matching between frames. By directly superimposing the aligned images, the spatiotemporal features of the resulting tensor are not damaged or reduced. From the perspective of the horizontal slice of this tensor, it is found that the background component has similarity in the time dimension and correlation in the space dimension, which is more consistent with the prerequisite of low rank, while the target component is sparse. Therefore, we transform the problem of infrared detection of a small moving target into a low-rank sparse decomposition problem of new tensors composed of several continuous horizontal slices of the aligned image tensor. The low rank of the background is constrained by the partial tubal nuclear norm (PTNN), and the tensor decomposition problem is quickly solved using the alternating-direction method of multipliers (ADMM). Our experimental results demonstrate that the proposed LSTT method can effectively detect small moving targets against a dynamic background. Compared with other benchmark methods, the new method has better performance in terms of detection efficiency and accuracy. In particular, the new LSTT method can extract the spatiotemporal information of more frames in a longer time domain and obtain a higher detection rate.

Small target detection is a crucial and challenging task in infrared search and track system. Background estimation-based methods is an effective and important approach for infrared small target detection. Affected by the target pixels, existing background estimation methods may reconstruct an inaccurate background. Based on image inpainting technique, we propose a novel two-stage approach to predict more accurate backgrounds. At the first stage, the inner and outer window-based image inpainting is used to obtain a rough background estimation. Then, a mask of candidate target region is automatically obtained by calculating and evaluating the difference between raw image and rough background. In the second stage, the final accurate background is predicted by mask-based image inpainting. It recovers the removed candidate target area using the information of surrounding background pixels, avoiding target pixels to participate in the calculation of background reconstruction. Finally, the target saliency map is obtained by subtracting the final estimated background from the original image, and a simple adaptive threshold is used to segment the target. Experimental results on real infrared images and sequences demonstrate that the proposed method outperforms other state-of-the-arts. It is simple and effective, with strong robustness and good real-time performance.