Targets in infrared images typically lack distinct texture and color features, posing significant challenges for infrared small target detection. Although existing methods have made some progress, they still have limitations in terms of interpretability and are unable to provide sufficient theoretical grounds to explain their effectiveness. Moreover, these methods generally overlook the temperature information in the imaging process, failing to fully exploit the subtle thermal differences in infrared images, which consequently limits detection accuracy. To this end, we propose a novel temperature-aware Transformer network (TATransNet). By introducing temperature information, it allows the model to be more focused on the target area. Specifically, inspired by the temperature inversion technique in remote sensing, we propose a learnable temperature inversion attention module (TIAM), which simulates the inverse process of infrared imaging to perceive the temperature distribution across feature maps of different scales, thereby enhancing the distinguishability between foreground and background. We further integrate TIAM with Swin Transformer to construct a Transformer-CNN hybrid encoder unit, termed temperature-aware Transformer block (TATB). By stacking multiple TATBs, both global context and local temperature features can be captured simultaneously, thereby strengthening the representation of dim and small targets effectively. Experimental results on five benchmark datasets, i.e., Small-ExtIRShip, Small-SSDD, NUAA-SIRST, IRSTD-1K, and IHAST demonstrate that our method not only significantly improves detection accuracy and reduces false alarm rates, but also demonstrates strong generalization capability, enabling effective transfer to other approaches with different types of encoders.

Object detection in infrared images poses a considerable challenge due to its small-scale targets, low contrast and poor signal-to-clutter ratio, often resulting in a high false alarm rate. To improve the detection accuracy on infrared small targets, we introduce Light-SGMTLM, a lightweight and saliency-guided multi-task learning model. This model integrates saliency detection into the YOLOv5x framework through a parallel multi-task learning structure and employs a joint loss function during training. Such integration significantly alleviates the impact of complex backgrounds and improves the precision of small target localization. Moreover, we have developed a streamlined module, termed SIWD, to create a more agile backbone, which establishes an optimal balance between precision and efficiency, making the model more suitable for situations with limited computational resources. Comprehensive comparative experiments were conducted on six infrared small target datasets, namely, Small-ExtIRShip, Small-SSDD, IHAST, NUAA-SIRST, IRSTD-1k, and IRDST, and we assessed the model’s performance against ten leading target detection models, such as YOLOv7, YOLOv8, DINO, and Relation-DETR. The findings reveal that our method’s unique joint learning architecture, combining saliency and object detection tasks, significantly improves accuracy for infrared small target detection. Notably, it achieved impressive mean average precision (mAP) values of 92.60% and 75.71% on the NUAA-SIRST and IRSTD-1k datasets, respectively.

Fault recognition is a difficult problem in seismic exploration data interpretation, and there is still no solution both well in terms of accuracy and signal-to-noise ratio. To solve this problem, based on the region energy algorithm, a novel fault recognition method is proposed, which determines the direction of fault tracking based on region energy when identifying fault points. First, the third-generation coherence cube algorithm is adopted to calculate the coherence attribute of the seismic data volume. Then, fault tracking is performed on each seismic section. When conducting fault tracking, the seismic sample is scanned and identified one by one. If it is a fault point, it is assigned to the corresponding fault in the connected area, and then, track along a certain direction of the current pixel point in the front left, directly ahead, or front right direction. The selection of the tracking directions is based on the energy of the corresponding area in the direction. The direction with the highest energy is tracked in the direction until the complete fault is tracked or the stopping condition is reached. If the point is not judged as a fault point, a certain distance is tracked down continue and the path is stored temporarily. If a fault point is tracked, the tracking path is classified as a fault, otherwise return to continue scanning. When all the sample points on the seismic section are scanned, the fault tracking on the corresponding section is completed. Subsequently, the fault points are fitted using the least squares fitting algorithm, and the fault line is obtained. Finally, comparative experiments were conducted on actual seismic data, and the effectiveness of the novel method was validated.

Infrared (IR) small target detection is a challenging task due to the low contrast and low signal-to-noise ratio, generally yields high false alarm rates. To improve the performance of IR small target detection, we propose a saliency guided multi-task leaning model (SGMTLM). The model consists of two parts: feature fusion and saliency detection. The feature fusion module is to integrate shallow information and deep semantic information of small targets. The saliency detection module is used to guide the Feature Pyramid Networks (FPN) to focus on the small target area. It can effectively suppress the non-target information while enhancing the small target information. Finally, experimental results on two datasets Small-ExtIRShip and Small-SSDD demonstrated that, with the help of saliency detection, the proposed method can effectively improve the accuracy of IR small target detection, achieving 95.78% and 98.70% mAP on the two datasets, respectively.

Ship target segmentation in infrared scenes has always been a hot topic, since it is an important basis and prerequisite for infrared-guided weapons to reliably capture and recognize ship targets in the sea level background. However, given the small target and fuzzy boundary characteristics of infrared ship images, obtaining accurate pixel-level labels for them is hardly achievable, which brings difficulty to train segmentation networks. To improve the segmentation accuracy of infrared ship images, we propose a two-stage domain adaptation method for infrared ship target segmentation, where the segmentation model is trained using visible ship images with clear target boundaries. In this case, the source domain is the labeled visible ship images, while the target domain is the unlabeled infrared ship images. Specifically, in the first stage, we use an image style transfer network to convert the infrared ship images into those with visible light style, so that the visual disparity between the two domain images can be reduced. Next, the visible, infrared and converted infrared images are input into the Deeplab-v2 segmentation network for training, thereby obtaining the initial network weights. At this time, random attention modules are added separately to the low- and high-level spaces of Deeplab-v2, in order to improve its feature extraction capability. In the second stage, we mix the visible and infrared images through region mixing to acquire the mixed domain images, as well as their corresponding labels. Subsequently, Deeplab-v2 is further trained using the mixed domain images to attain better segmentation accuracy. Experimental results on both the home-made visible-infrared ship image dataset and the public infrared image dataset are superior to those existing mainstream methods, demonstrating its effectiveness.

Feature clustering is a powerful technique for dimensionality reduction. However, existing approaches require the number of clusters to be given in advance or controlled by parameters. In this paper, by combining with affinity propagation (AP), we propose a new feature clustering (FC) algorithm, ca lled APFC, for dimensionality reduction. For a given training dataset, the original features automatically form a bunch of clusters by AP. A new feature can then be extracted from each cluster in three different ways for reducing the dimensionality of the original data. APFC requires no provision of the number of clusters (or extracted features) beforehand. Moreover, it avoids computing the eigenvalues and eigenvectors of covariance matrix which is often necessary in many feature extraction methods. In order to demonstrate the effectiveness and efficiency of APFC, extensive experiments are conducted to compare it with three well-established dimensionality reduction methods on 14 UCI datasets in terms of classification accuracy and computational time.