The detection of infrared small targets under low signal-to-clutter ratio (SCR) and complex background conditions has been a challenging and popular research topic. In this article, a spatial-temporal feature-based detection framework is proposed. First, several factors, such as the infrared target’s small sample, the sensitive size, and the usual sample selection strategy, that affect the detection of small targets are analyzed. In addition, the small intersection over union (IOU) strategy, which helps to solve the false convergence and sample misjudgment problem, is proposed. Second, aiming at the difficulties due to the target’s dim information and complex background, the interframe energy accumulation (IFEA) enhancement mechanism-based end-to-end spatial-temporal feature extraction and target detection framework is proposed. This framework helps to enhance the target’s energy, suppress the strong spatially nonstationary clutter, and detect dim small targets. Experimental results show that using the small IOU strategy and IFEA mechanism, the proposed multiple frame-based detection framework performs better than some popular deep learning (DL)-based detection algorithms.

For the extremely small size and low signal‐to‐clutter ratio, target detection in infrared images is still a considerable challenge. Specifically, it is very difficult to detect the point targets because there is no texture and shape information can be used. A target‐oriented shallow‐deep feature‐based detection algorithm is proposed, opening up a promising direction for convolutional neural network‐based infrared dim small target detection algorithms. To ensure that small target instances can be used correctly for networks, the effective small anchor is designed according to the shallow layer of ResNet50. To determine whether a detection result belongs to the target, the authors depend on whether the detection centre is included in the ground truth area, rather than on the Intersection Over Union overlap rate, which avoids misjudging the detection result. In this way, small targets can be trained and detected correctly through ResNet50. More importantly, the authors demonstrate that spatially finer shallow features are crucial for small target detection and that semantically stronger deep features are helpful for improving detection probability. Experimental results on simulation data sets and real data sets show that the proposed algorithm can detect the point target when the local signal‐to‐clutter ratio is approximately 1.3, displaying infinite advantage and great potentiality.

To address the phenomenon of many small and hard-to-detect objects in drone images, this study proposes an improved algorithm based on the YOLOv7-tiny model. The proposed algorithm assigns anchor boxes according to the aspect ratio of ground truth boxes to provide prior information on object shape for the network and uses a hard sample mining loss function (HSM Loss) to guide the network to enhance learning from hard samples. This study finds that the aspect ratio difference of vehicle objects under drone perspective is more obvious than the scale difference, so the anchor boxes assigned by aspect ratio can provide more effective prior information for the network than those assigned by size. This study evaluates the algorithm on a drone image dataset (DroneVehicle) and compares it with other state-of-the-art algorithms. The experimental results show that the proposed algorithm achieves superior average precision values on both infrared and visible light images, while maintaining a light weight.

In recent years, due to its strong nonlinear mapping and research capacities, the convolutional neural network (CNN) has been widely used in the field of hyperspectral image (HSI) processing. Recently, pixel pair features (PPFs) and spatial PPFs (SPPFs) for HSI classification have served as the new tools for feature extraction. In this paper, on top of PPF, improved subtraction pixel pair features (subtraction-PPFs) are applied for HSI target detection. Unlike original PPF and SPPF, the subtraction-PPF considers target classes to afford the CNN, a target detection function. Using subtraction-PPF, a sufficiently large number of samples are obtained to ensure the excellent performance of the multilayer CNN. For a testing pixel, the input of the trained CNN is the spectral difference between the central pixel and its adjacent pixels. When a test pixel belongs to the target, the output score will be close to the target label. To verify the effectiveness of the proposed method, aircrafts and vehicles are used as targets of interest, while another 27 objects are chosen as background classes (e.g., vegetation and runways). Our experimental results on four images indicate that the proposed detector outperforms classic hyperspectral target detection algorithms.

The detection and recognition of dim and small infrared (IR) targets across domains pose two formidable challenges: distributional discrepancies in samples and scarcity or absence of annotated instances in the target domain. While current unsupervised domain adaptive object detection methods can somewhat alleviate the performance degradation caused by these issues, they fail to address the differences in semantic content between the background environments in different application scenarios. This results in a semantic gap that impedes the algorithm’s adaptability. We propose a content-decoupled unsupervised domain adaptive method to mitigate the adverse impact of the semantic gap on domain adaptation. Specifically, we introduce an unsupervised task-guided branch in the one-stage detector that executes style transfer in real-time during training, directing the feature representation via shared parameters. A novel content-decoupled feature alignment module aligns semantically unrelated features in the source and target domains while preserving the intrinsic semantics of dim and small IR targets. The experiments on a cross-band IR dataset reveal that the proposed method enhances the mean average precision by 18.3% compared to the baseline detector without increasing computational burden.

Traditional data-driven algorithms suffer from data reliance, hyperparameter sensitivity, and faint characteristics in infrared (IR) “low, slow, and small” unmanned aerial vehicle target detection and recognition, resulting in performance degradation in complex backgrounds. Inspired by model-driven methods, this article proposes a learnable feature modulation module that uses prior knowledge to enhance feature representation. Specifically, this method converts the local contrast measure into a nonlocal quadrature difference measure in deep feature space, considering feature points that break semantic continuity as the potential target locations through a self-attentive approach. On this basis, considering the scale changes of aircraft targets during radial approach to IR detectors, a multiscale single-stage detector is designed by effective receptive field calculation. In this network structure, a bidirectional serial feature modulation method is used to fully retain the multiscale features of the target and ensure adaptability to point, spot, and area targets while satisfying real-time requirements. The ablation studies verify the effectiveness of each component and help determine the optimal parameter configuration. Finally, comparison experiments with state-of-the-art methods are conducted on a 10k scale IR dataset. The experimental results show that the detection accuracy of this method is better than that of other baseline methods while ensuring real-time performance, especially in highly complex and low-contrast scenes, achieving superior higher target detection accuracy.