Search Results (105)

Near-infrared (NIR) photoelectric synaptic devices show great potential in studying NIR artificial visual systems integrating excellent optical characteristics and bionic synaptic plasticity. However, NIR synapses based on transition metal dichalcogenides (TMDCs) suffer from low stability and poor environmental performance. Thus, an environmentally friendly NIR synapse was fabricated based on lanthanide-doped upconversion nanoparticles (UCNPs) and two-dimensional (2D) WSe₂ via solution spin coating technology. Biological synaptic functions were simulated successfully through 975 nm laser regulation, including paired-pulse facilitation (PPF), spike rate-dependent plasticity, and spike timing-dependent plasticity. Handwritten digital images were also recognized by an artificial neural network based on device characteristics with a high accuracy of 97.24%. In addition, human and animal identification in foggy and low-visibility surroundings was proposed by the synaptic response of the device combined with an NIR laser and visible simulation. These findings might provide promising strategies for developing a 24/7 visual response of humanoid robots. Full article

Despite deep learning-based object detection techniques showing promising results, identifying items from low-quality images under unfavorable weather settings remains challenging because of balancing demands and overlooking useful latent information. On the other hand, YOLO is being developed for real-time object detection, addressing limitations of current models, which struggle with low accuracy and high resource requirements. To address these issues, we provide an Adaptive Enhancement Algorithm YOLO (AEA-YOLO) framework that allows for an enhancement in each image for improved detection capabilities. A lightweight Parameter Prediction Network (PPN) containing only six thousand parameters predicts scene-adaptive coefficients for a differentiable Image Enhancement Module (IEM), and the enhanced image is then processed by a standard YOLO detector, called the Detection Network (DN). Adaptively processing images in both favorable and unfavorable weather conditions is possible with our suggested method. Extremely encouraging experimental results compared with existing models show that our suggested approach achieves 7% and more than 12% in mean average precision (mAP) on the PASCAL VOC Foggy artificially degraded and the Real-world Task-driven Testing Set (RTTS) datasets. Moreover, our approach achieves good results compared with other state-of-the-art and adaptive domain models of object detection in normal and challenging environments. Full article

The synthesis of realistic fog in images is critical for applications such as autonomous navigation, augmented reality, and visual effects. Traditional methods based on Koschmieder’s law or GAN-based image translation typically assume homogeneous fog distributions and rely on oversimplified scattering models, limiting their physical realism. In this paper, we propose a physics-driven approach to fog synthesis by discretizing the Radiative Transfer Equation (RTE). Our method models spatially inhomogeneous fog and anisotropic multi-scattering, enabling the generation of structurally consistent and perceptually plausible fog effects. To evaluate performance, we construct a dataset of real-world foggy, cloudy, and sunny images and compare our results against both Koschmieder-based and GAN-based baselines. Experimental results show that our method achieves a lower Fréchet Inception Distance ($-10\%$ vs. Koschmieder, $-42\%$ vs. CycleGAN) and a higher Pearson correlation ($+4\%$ and $+21\%$, respectively), highlighting its superiority in both feature space and structural fidelity. These findings highlight the potential of RTE-based fog synthesis for physically consistent image augmentation under challenging visibility conditions. However, the method’s practical deployment may be constrained by high memory requirements due to tensor-based computations, which must be addressed for large-scale or real-time applications. Full article

In fields such as military reconnaissance, forest fire prevention, and autonomous driving at night, there is an urgent need for high-precision three-dimensional reconstruction in low-light or night environments. The acquisition of remote sensing data by RGB cameras relies on external light, resulting in a significant decline in image quality and making it difficult to meet the task requirements. The method based on lidar has poor imaging effects in rainy and foggy weather, close-range scenes, and scenarios requiring thermal imaging data. In contrast, infrared cameras can effectively overcome this challenge because their imaging mechanisms are different from those of RGB cameras and lidar. However, the research on three-dimensional scene reconstruction of infrared images is relatively immature, especially in the field of infrared binocular stereo matching. There are two main challenges given this situation: first, there is a lack of a dataset specifically for infrared binocular stereo matching; second, the lack of texture information in infrared images causes a limit in the extension of the RGB method to the infrared reconstruction problem. To solve these problems, this study begins with the construction of an infrared binocular stereo matching dataset and then proposes an innovative perspective projection positional encoding-based transformer method to complete the infrared binocular stereo matching task. In this paper, a stereo matching network combined with transformer and cost volume is constructed. The existing work in the positional encoding of the transformer usually uses a parallel projection model to simplify the calculation. Our method is based on the actual perspective projection model so that each pixel is associated with a different projection ray. It effectively solves the problem of feature extraction and matching caused by insufficient texture information in infrared images and significantly improves matching accuracy. We conducted experiments based on the infrared binocular stereo matching dataset proposed in this paper. Experiments demonstrated the effectiveness of the proposed method. Full article

This research addresses visibility challenges in surveillance systems under foggy conditions through a novel synthetic fog generation method leveraging the GridNet dehazing architecture. Our approach uniquely reverses GridNet, originally developed for fog removal, to synthesize realistic foggy images. The proposed Fog Generator Model incorporates perceptual and dark channel consistency losses to enhance fog realism and structural consistency. Comparative experiments on the O-HAZY dataset demonstrate that dehazing models trained on our synthetic fog outperform those trained on conventional methods, achieving superior Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores. These findings confirm that integrating high-performance dehazing networks into fog synthesis improves the realism and effectiveness of fog removal solutions, offering significant benefits for real-world surveillance applications. Full article

Cracks in concrete structures are key indicators for structural health diagnosis, and the demand for automated detection is gradually increasing. Although various non-destructive testing (NDT) methods and concrete defect detection software have been widely applied, their detection performance varies significantly when dealing with cracks of different shapes and scales. In particular, under complex environmental conditions, detecting fine, irregular, or occluded cracks remains a major challenge. Traditional image-processing-based methods face clear limitations in feature extraction and detection efficiency in practical applications. To address these issues, we propose the CGSW-YOLOv5 algorithm, which enhances detection performance through the following innovations: First, a Concrete Crack Feature Enhancement Block (CNeB) is introduced to improve fine-detail capture. Second, an Adaptive Multi-Scale Feature Aggregation attention mechanism (AMFA) is designed to optimize convolutional kernel selection. Third, the Dynamic Gradient Focusing Weighted IoU loss (DGFW-IoU) is adopted to improve localization accuracy for small targets. Finally, a Lightweight Dual-Stream Convolutional Feature Enhancement module (LDSConv) is constructed to achieve efficient feature utilization. Experimental results show that the CGSW-YOLOv5 algorithm achieves detection accuracies of 71.74% and 72.85% on a self-built dataset and a concrete crack dataset under various environmental conditions (windy, rainy, and foggy), respectively. These results represent improvements of 4.49% and 4.6% over the baseline algorithm, demonstrating superior detection performance and strong environmental adaptability. The proposed method provides an effective solution for intelligent crack detection in concrete structures. Full article

With the rapid advancement of UAV technology, robust object detection under adverse weather conditions has become critical for enhancing UAVs’ environmental perception. However, object detection in such challenging conditions remains a significant hurdle, and standardized evaluation benchmarks are still lacking. To bridge this gap, we introduce the Adverse Weather Object Detection (AWOD) dataset—a large-scale dataset tailored for object detection in complex maritime environments. The AWOD dataset comprises 20,000 images captured under three representative adverse weather conditions: foggy, flare, and low-light. To address the challenges of scale variation and visual degradation introduced by harsh weather, we propose WRRT-DETR, a weather-robust object detection framework optimized for small objects. Within this framework, we design a gated single-head global–local attention backbone block (GLCE) to fuse local convolutional features with global attention, enhancing small object distinguishability. Additionally, a Frequency–Spatial Feature Augmentation Module (FSAE) is introduced to incorporate frequency-domain information for improved robustness, while an Attention-based Cross-Fusion Module (ACFM) facilitates the integration of multi-scale features. Experimental results demonstrate that WRRT-DETR outperforms SOTA methods on the AWOD dataset, exhibiting superior robustness and detection accuracy in complex weather conditions. Full article

The high cost and difficulty of collecting real-world foggy scene images mean that automatic driving datasets produce limited images in bad weather and lead to deficient training in automatic driving systems, causing unsafe judgments and leading to traffic accidents. Therefore, to effectively promote the safety and robustness of an autonomous driving system, we improved the CycleGAN model to achieve dataset augmentation of foggy images. Firstly, by combining the self-attention mechanism and the residual network architecture, the sense of hierarchy of the fog effect in the synthesized image was significantly refined. Then, LPIPS was employed to adjust the calculation method for cycle consistency loss to make the synthetic picture more similar to the original one in terms of perception. The experimental results showed that the FID index of the foggy image generated by the improved CycleGAN network was reduced by 3.34, the IS index increased by 15.8%, and the SSIM index increased by 0.1%. The modified method enhances the generation of foggy images, while retaining more details of the original image and reducing content distortion. Full article

In foggy environments, infrared images suffer from reduced contrast, degraded details, and blurred objects, which impair detection accuracy and real-time performance. To tackle these issues, we propose IDDNet, a lightweight infrared object detection network that integrates multi-scale fusion dehazing. IDDNet includes a multi-scale fusion dehazing (MSFD) module, which uses multi-scale feature fusion to eliminate haze interference while preserving key object details. A dedicated dehazing loss function, DhLoss, further improves the dehazing effect. In addition to MSFD, IDDNet incorporates three main components: (1) bidirectional polarized self-attention, (2) a weighted bidirectional feature pyramid network, and (3) multi-scale object detection layers. This architecture ensures high detection accuracy and computational efficiency. A two-stage training strategy optimizes the model’s performance, enhancing its accuracy and robustness in foggy environments. Extensive experiments on public datasets demonstrate that IDDNet achieves 89.4% precision and 83.9% AP, showing its superior accuracy, processing speed, generalization, and robust detection performance. Full article

Foggy weather poses significant challenges to outdoor computer vision tasks, such as object detection, by degrading image quality and reducing algorithm reliability. In this paper, we present a novel model for estimating fog density in outdoor scenes, aiming to enhance object detection performance under varying foggy conditions. Using a support vector machine (SVM) classification framework, the proposed model categorizes unknown images into distinct fog density levels based on both global and local fog-relevant features. Key features such as entropy, contrast, and dark channel information are extracted to quantify the effects of fog on image clarity and object visibility. Moreover, we introduce an innovative region selection method tailored to images without detectable objects, ensuring robust feature extraction. Evaluation on synthetic datasets with varying fog densities demonstrates a classification accuracy of 85.8%, surpassing existing methods in terms of correlation coefficients and robustness. Beyond accurate fog density estimation, this approach provides valuable insights into the impact of fog on object detection, contributing to safer navigation in foggy environments. Full article

To address the problems that exist in the target detection of vehicle-mounted visual sensors in foggy environments, a vehicle target detection method based on an improved YOLOX network is proposed. Firstly, to address the issue of vehicle target feature loss in foggy traffic scene images, specific characteristics of fog-affected imagery are integrated into the network training process. This not only augments the training data but also improves the robustness of the network in foggy environments. Secondly, the YOLOX network is optimized by adding attention mechanisms and an image enhancement module to improve feature extraction and training. Additionally, by combining this with the characteristics of foggy environment images, the loss function is optimized to further improve the target detection performance of the network in foggy environments. Finally, transfer learning is applied during the training process, which not only accelerates network convergence and shortens the training time but also further improves the robustness of the network in different environments. Compared with YOLOv5, YOLOv7, and Faster R-CNN networks, the mAP of the improved network increased by 13.57%, 10.3%, and 9.74%, respectively. The results of the comparative experiments from different aspects illustrated that the proposed method significantly enhances the detection performance for vehicle targets in foggy environments. Full article

Peplography is a technology for removing scattering media such as fog and smoke. However, Peplography only removes scattering media, and decisions about the images are made by humans. Therefore, there are still many improvements to be made in terms of system automation. In this paper, we combine Peplography with You Only Look Once (YOLO) to attempt object detection under scattering medium conditions. In addition, images reconstructed by Peplography have different characteristics from normal images. Therefore, by applying Peplography to the training images, we attempt to learn the image characteristics of Peplography and improve the detection accuracy. Also, when considering autonomous driving in foggy conditions or rescue systems at the scene of a fire, three-dimensional (3D) information such as the distance to the vehicle in front and the person in need of rescue is also necessary. Furthermore, we apply a stereo camera to this algorithm to achieve 3D object position and distance detection under scattering media conditions. In addition, when estimating the scattering medium in Peplography, it is important to specify the processing area, otherwise the scattering medium will not be removed properly. Therefore, we construct a system that continuously improves processing by estimating the size of the object in object detection and successively changing the area range using the estimated value. As a result, the PSNR result by our proposed method is better than the PSNR by the conventional Peplography process. The distance estimation and the object detection are also verified to be accurate, recording values of 0.989 for precision and 0.573 for recall. When the proposed system is applied, it is expected to have a significant impact on the stability of autonomous driving technology and the safety of life rescue at fire scenes. Full article

Ship detection under cloudy and foggy conditions is a significant challenge in remote sensing satellite applications, as cloud cover often reduces contrast between targets and backgrounds. Additionally, ships are small and affected by noise, making them difficult to detect. This paper proposes a Cloud Removal and Target Detection (CRTD) network to detect small ships in images with thin cloud cover. The process begins with a Thin Cloud Removal (TCR) module for image preprocessing. The preprocessed data are then fed into a Small Target Detection (STD) module. To improve target–background contrast, we introduce a Target Enhancement module. The TCR and STD modules are integrated through a dual-stage supervision network, which hierarchically processes the detection task to enhance data quality, minimizing the impact of thin clouds. Experiments on the GaoFen-4 satellite dataset show that the proposed method outperforms existing detectors, achieving an average precision (AP) of 88.9%. Full article

The application value of low-quality photos taken in foggy conditions is significantly lower than that of clear images. As a result, restoring the original image information and enhancing the quality of damaged images on cloudy days are crucial. Commonly used deep learning techniques like DehazeNet, AOD-Net, and Li have shown encouraging progress in the study of image dehazing applications. However, these methods suffer from a shallow network structure leading to limited network estimation capability, reliance on atmospheric scattering models to generate the final results that are prone to error accumulation, as well as unstable training and slow convergence. Aiming at these problems, this paper proposes an improved end-to-end convolutional neural network method based on the denoising self-encoder-DenseNet (DAE-DenseNet), where the denoising self-encoder is used as the main body of the network structure, the encoder extracts the features of haze images, the decoder performs the feature reconstruction to recover the image, and the boosting module further performs the feature fusion locally and globally, and finally outputs the dehazed image. Testing the defogging effect in the public dataset, the PSNR index of DAE-DenseNet is 22.60, which is much higher than other methods. Experiments have proved that the dehazing method designed in this paper is better than other algorithms to a certain extent, and there is no color oversaturation or an excessive dehazing phenomenon in the image after dehazing. The dehazing results are the closest to the real image and the viewing experience feels natural and comfortable, with the image dehazing effect being very competitive. Full article

To overcome the challenges posed by limited garbage datasets and the laborious nature of data labeling in urban garbage object detection, we propose an innovative unsupervised domain adaptation approach to detecting garbage objects in urban aerial images. The proposed method leverages a detector, initially trained on source domain images, to generate pseudo-labels for target domain images. By employing an attention and confidence fusion strategy, images from both source and target domains can be seamlessly integrated, thereby enabling the detector to incrementally adapt to target domain scenarios while preserving its detection efficacy in the source domain. This approach mitigates the performance degradation caused by domain discrepancies, significantly enhancing the model’s adaptability. The proposed method was validated on a self-constructed urban garbage dataset. Experimental results demonstrate its superior performance over baseline models. Furthermore, we extended the proposed mixing method to other typical scenarios and conducted comprehensive experiments on four well-known public datasets: Cityscapes, KITTI, Sim10k, and Foggy Cityscapes. The result shows that the proposed method exhibits remarkable effectiveness and adaptability across diverse datasets. Full article