The Traveling Salesman Problem (TSP), a classic combinatorial optimization problem, has been extensively studied for many years. Recently, the Multi-solution Traveling Salesman Problem (MSTSP) has received increasing attention and achieved significant progress. Compared to the traditional TSP, MSTSP can identify more optimal solutions, providing more satisfactory solutions in urgent situations or according to user preferences. However, research on MSTSP remains relatively limited. Most existing algorithms primarily focus on the traditional TSP and pay little attention to the search for multiple solutions. As a result, there are very few algorithms specifically designed for MSTSP. This paper proposes a hierarchical genetic algorithm of “preprocessing -approximate search -precise search”. In the preprocessing stage, simple evolution of the initial population is performed to enhance the reliability of critical edges. In the approximate search, individual generation strategy is designed to achieve global rapid convergence. A new environment selection mechanism is designed for the deletion and retention of multimodal solutions. In the precise search, individual clustering and regeneration strategy, and a local search strategy based on jump operator are designed to find more multimodal solutions. The hierarchical approach, which progresses sequentially, can discover more multimodal solutions while also achieving the global optimal solution. To validate the proposed algorithm’s performance, comprehensive experiments are conducted on multi-solution optimization test suite, and compared it with the latest algorithms. Experimental results show that the proposed algorithm outperforms compared algorithms.

When capturing scenes with intense light sources, extensive flare artifacts often obscure the background and degrade image quality. Most flare removal methods directly process the flare-corrupted image as the optimization target, limiting the model’s understanding and generalization in complex real-world scenarios. In this paper, we propose a novel Self-prior Guided Spatial and Fourier Transformer (SGSFT) for nighttime flare removal. Specifically, we first establish a Self-prior Extraction Network to capture inherent priors in different scenes. Subsequently, we introduce a Semantic Contrast Enhancement Strategy to reinforce the semantic irrelevance between flare and light source, enabling the flare removal network to learn pattern differences between them and thus preserve light source. Finally, we build a Spatial and Frequency Flare Removal Network with Spatial Contextual Attention Block (SCAB) and Frequency Global Information Adjustment Block (FGIAB) to generate flare-free image. SCAB can perceive rich contextual information from self-prior guided regions and infer reasonable content. FGIAB captures global luminance representation in the frequency domain to maintain luminance consistency between the inferred regions and the flare-free areas. Extensive experiments demonstrate that the proposed approach achieves optimal performance in real nighttime scenes and exhibits robust generalization across various flare scenarios captured by different electronic devices. Note to Practitioners—The motivation of this paper is to remove flare artifacts in imaging. Flares degrade image quality and impact the performance of advanced vision tasks such as semantic segmentation and depth estimation in autonomous driving. Existing methods that indiscriminately extract contextual information from the entire image limit the model’s understanding of flares. This study proposes a self-prior guided flare removal network. The network first extracts self-prior information from flare-damaged images, then aggregates non-local information from the context indicated by the self-prior information to remove flares and infer semantically plausible fill content. Additionally, we model the global luminance information of the image in the frequency domain to enhance the global luminance consistency of the flare-free image. Experimental results show that our method has strong flare removal capabilities, but it also has a limitation. The training phase of this method requires paired flare-damaged images and flare images, which are difficult to obtain in real-world scenarios. Therefore, we will explore unsupervised flare removal methods in the future.

The success of deep learning methods heavily relies on the availability of adequate samples. However, in the task of infrared small target detection (ISTD), the lack of high-quality training samples is a challenging problem due to the confidentiality of the application field and the difficulty of labeling. This limitation often leads to suboptimal detection performance of convolutional neural networks (CNNs). To address this challenge, we propose an adaptive labeling strategy and an ISTD network called the multi-criteria decision network (MCDNet) to achieve higher-quality sample labeling and more accurate detection results. In the adaptive labeling strategy, we propose a second-order differential autocorrelation method to determine the size of fuzzy edge targets accurately. In addition, we introduce local backgrounds to enhance the saliency information in the labels and improve the richness and contrast of training label content. To obtain accurate and robust detection results with limited target feature information, we design MCDNet. In particular, we propose a multi-criteria decision method that can combine the CNN decisions and the infrared small target prior saliency decisions through weighted fusion, and set decision weights based on the importance of different decision criteria in the decision-making process. This method can integrate the advantages of both the CNN decisions and the prior saliency decisions, avoid the one-sidedness of a single criterion, and improve the reliability and stability of the decision-making. The experimental results indicate that our method has a higher accuracy compared to other contrastive methods.

Infrared small target detection plays a crucial role in various domains like early warning, national defense, and monitoring. Although existing detection methods have achieved some good results, they only rely on the original size and information of small targets for detection and are faced with challenges, such as the small size and obscure feature information of small targets. To overcome these limitations, this article introduces a coarse-to-fine detection network named MSMA-Net. This network initially determines the rough location of targets through a coarse preliminary screening, aiming to reduce false alarms and improve computational efficiency. Simultaneously, to improve the discriminability of the features and enhance the spatial details and resolution of the targets, the network utilizes multiscale super-resolution to transform low-resolution feature maps into high-resolution representations, gradually refining and strengthening the feature representation. Finally, the network employs a multilevel feature fusion attention mechanism to facilitate effective information transmission and fusion in multiscale and multilevel feature representations. This attention mechanism enhances the accuracy as well as robustness of object detection, ultimately obtaining accurate detection results. Extensive experimental results demonstrate that compared with existing detection methods, our approach can effectively suppress false alarms and get better performance even when the target has a small size and obscure feature information.

To solve the problems of slow detection speed and poor robustness of existing infrared (IR) small target detection methods in complex environments, a lightweight detection model MiniIR-net is proposed in this letter. In the MiniIR-net model, to reduce the number of parameters required for model fitting, a multiscale target context feature extraction (TCVE) module is proposed to enrich the feature expression of the target. In addition, to improve the feature mapping capability of MiniIR-net, a feature mapping upsampling network by fusing the deep and shallow features is designed. In the process of feature mapping upsampling, the network uses target features with different depths to make up for the loss of target features caused by pooling. It is proven by the experiment that the proposed MiniIR-net network is superior to the existing detection methods in detection speed, accuracy and robustness in a complex environment. The model size of MiniIR-net is at least 1/260 of the current detection model, and the detection accuracy is improved by at least 5%. The source code of this article can be obtained athttps://github.com/yangzhen1252/MiniIR-net.

Intractable sparse feature extraction, over-weight model size, and limited training samples are currently bewildering in infrared dim small target detection, which are not adequately addressed by current state-of-the-art (SOTA) methods. Here, to synchronously address these issues, a dense multi-level feature extraction and fusion network (DMEF-net) is designed, mainly consisting of two modules: target context and Gaussian saliency feature extraction module (TCGS) and multi-level dense feature fusion structure (MLDF). Inspired by the physical thermal diffusion model and the human visual mechanism for small-scale targets, Gaussian salience features and local context features are introduced into the target feature expression through the designed TCGS module to solve the sparse feature extraction problem. Then, to solve the over-weight model size problem, a novel MLDF module is designed to incorporate the feature reuse mechanism into our model, thereby significantly reducing the number of trainable parameters. Finally, in the training procedure, an efficient saliency labeling strategy is proposed to jointly supervise the model training in both Euclidean and Gaussian spaces, ultimately enhancing the model’s ability to explore the target features and alleviate performance deterioration when the training samples are limited. Extensive experiments on several large-scale open datasets, including TDSATUA and MTDUCB, prove that the proposed DMEF-net outperforms other SOTA methods by 8% in accuracy and has 4800% less model size.

Infrared (IR) small target detection in a complex environment has become a hot topic. Due to the dim intensity and small scale of the target and the strong background clutter, the existing algorithms cannot achieve satisfactory results, namely poor detection performance and poor real-time performance. In this letter, a new real-time small target detection algorithm based on smoothness measure and thermal diffusion (STD) is proposed. First, the smoothness measure is proposed to extract smoothness features of small targets and suppress the clutter background. Then, we improve the existing thermal diffusion equation and design a thermal diffusion operator to extract the target’s thermal diffusion feature. The operator will further enhance the small and dim target’s energy. Finally, the fusion result image—in which the background is suppressed and the target is enhanced—is acquired after combining smoothness and thermal diffusion flowmetry. The experimental results demonstrate that the detection speed of the proposed algorithm is at least four times faster than that of existing algorithms under the same detection conditions. In addition, the proposed algorithm can achieve outstanding detection performance for IR images with different types of complex backgrounds and targets’ sizes within$7\times7$.

In the complex background, the contrast and signal-to-noise (SNR) ratio of the infrared (IR) small target are low. Therefore, the traditional IR small target detection algorithms are difficult to achieve good detection performance when the characteristics of small targets are sparse. To solve this problem, an IR small target detection network with generate label and feature mapping (GLFM)-net is proposed in this letter. First, in the GLFM-net model, a scale adaptive feature extraction network is proposed for the IR small target sparse features extraction, and then, the multilayer joint upsampling feature mapping network is proposed for small target feature mapping and background suppression. Based on this model, the feature mapping results of IR dim and small targets with the greatly suppressed background are obtained. Second, in model training, we designed a 2-D Gaussian label generation strategy for the problem of sample imbalance, which can achieve excellent detection performance by using small training samples. The experimental results show that the network can detect IR small targets with different sizes and low SNRs in various complex backgrounds and has good effectiveness and robustness compared with the existing algorithms.

Aiming at the problems of large parameters and low detection speed of the existing remote sensing road detection network model, a lightweight remote sensing road detection network (LRSR-net) model is proposed in this paper. In the feature encoding stage of LRSR-net, an efficient road target feature extraction module dilated joint convolution module is proposed. This module can eliminate the feature loss caused by the pooling layer, so that the network model can use a small amount of parameters to learn the characteristics of road targets. In addition, in the feature decoding stage, to eliminate the damage of the target data structure caused by the upsampling operation, a joint decoding module is proposed. The joint decoding module can effectively map the characteristics of road targets and suppress the background clutter. The systematic experimental results have demonstrated that the proposed lightweight road target detection model has excellent detection performance under the condition of small model parameters, and most performance indexes are better than those of the existing advanced detection methods. The source code of this article can be obtained from https://github.com/yangzhen1252/IRSR-net.