Due to the limitation of the optical lens focal length and the resolution of the infrared detector, distant Closely-Spaced Infrared Small Target (CSIST) groups typically appear as mixing spots in the infrared image. In this paper, we propose a novel task, Sequential CSIST Unmixing, namely detecting all targets in the form of sub-pixel localization from a highly dense CSIST group. However, achieving such precise detection is an extremely difficult challenge. In addition, the lack of high-quality public datasets has also restricted the research progress. To this end, firstly, we contribute an open-source ecosystem, including SeqCSIST, a sequential benchmark dataset, and a toolkit that provides objective evaluation metrics for this special task, along with the implementation of 23 relevant methods. Furthermore, we propose the Deformable Refinement Network (DeRefNet), a model-driven deep learning framework that introduces a Temporal Deformable Feature Alignment (TDFA) module enabling adaptive inter-frame information aggregation. To the best of our knowledge, this work is the first endeavor to address the CSIST Unmixing task within a multi-frame paradigm. Experiments on the SeqCSIST dataset demonstrate that our method outperforms the state-of-the-art approaches with mean Average Precision (mAP) metric improved by 5.3%. Our dataset and toolkit are available from https://github.com/GrokCV/SeqCSIST.

Weakly supervised object detection (WSOD) methods that trains an object detection network using image-level labels has attracted much attention due to its cost-effective annotation and broad applied requirement. However, applying such weak label to detect targets in infrared images is not trivial due to the less discriminative target information and interference of complex backgrounds. This article proposes a multi-grained and confidence-aware multiple instance network (MCMIN) to detect infrared targets given the imprecise labels. The multiscale multi-grained feature extraction module is designed to capture discriminative features from different receptive fields for dim-small targets. The hierarchical multiple instance target detection module first applies L1-sparsity regularization to encourage the model generate reliable pseudo ground truth (GT), and then leverages the confidence-aware instance adaptive weighting strategy to refine proposals with particular emphasis, achieving more accurate target detection. The experimental results on two infrared target detection datasets illustrate that the proposed MCMIN outperforms other state-of-the-art WSOD methods with higher average precision (AP). The proposed approach decreases the false alarms.

Single-frame infrared small target (SIRST) detection has been a challenging task due to a lack of inherent characteristics, imprecise bounding box regression, a scarcity of real-world datasets, and sensitive localization evaluation. In this article, we propose a comprehensive solution to these challenges. First, we find that the existing anchor-free label assignment method is prone to mislabeling small targets as background, leading to their omission by detectors. To overcome this issue, we propose an all-scale pseudobox-based label assignment scheme that relaxes the constraints on the scale and decouples the spatial assignment from the size of the ground-truth target. Second, motivated by the structured prior of feature pyramids, we introduce the one-stage cascade refinement network (OSCAR), which uses the high-level head as soft proposal for the low-level refinement head. This allows OSCAR to process the same target in a cascade coarse-to-fine manner. Finally, we present a new research benchmark for infrared small target detection, consisting of the SIRST-V2 dataset of real-world, high-resolution single-frame targets, the normalized contrast evaluation metric, and the DeepInfrared toolkit for detection. We conduct extensive ablation studies to evaluate the components of OSCAR and compare its performance to state-of-the-art model- and data-driven methods on the SIRST-V2 benchmark. Our results demonstrate that a top-down cascade refinement framework can improve the accuracy of infrared small target detection without sacrificing efficiency. The DeepInfrared toolkit, dataset, and trained models are available athttps://github.com/YimianDai/open-deepinfrared.

Infrared small-dim target detection is an important technology in the fields of infrared guidance, anti-missile, and tracking system. Due to the small size of targets, no obvious structure information, and low image signal-to-noise ratio (SNR), infrared small-dim target detection is still a challenging task. In this letter, a cross-connected bidirectional pyramid network (CBP-Net) is proposed for infrared small-dim target detection. The main body of the CBP-Net is to embed a bottom-up pyramid in the feature pyramid network (FPN), which is designed to provide more comprehensive target information by connecting with the original multi-scale features and the top-down pyramid. The bottom-up pyramid together with the top-down pyramid forms the proposed bidirectional pyramid structure. Then, an region of interest (ROI) feature augment module (RFA) composed of deformable ROI pooling and position attention is designed to fuse multi-scale ROI features and enhance the spatial information of the small-dim target. Besides, a regular constraint loss (RCL) is introduced to restrict multi-scale feature fusion to learn more precise target location information. Experimental results on two challenging datasets show that the performance of the proposed CBP-Net is superior to the state-of-the-art methods.

Fast and robust small infrared (IR) target detection is a challenging task and critical to the performance of IR searching and tracking (IRST) systems. However, the current algorithms generally have difficulty in striking a good balance between speed and performance. In this letter, we propose a new approach to small IR target detection that can significantly accelerate the detection process by first performing a fast adaptive masking and scaling algorithm. We then propose to enhance the target characteristics and suppress the background clutter using both contrast and gradient information. Finally, we propose to accurately extract the targets via iterative segmentation. The experimental results demonstrated that our proposed method yields the best and the most robust performance, with a speed of at least two times faster than the state-of-the-art methods.