Adaptive Image Enhancement Algorithm with Complex Background

Environment awareness technology is one of the most critical technologies for autonomous vehicles, and traffic sign recognition is an important branch of environment awareness system, which has important research significance for ensuring traffic safety. To solve the problems of easy omission and inaccurate positioning for traffic sign detection under complex illumination conditions, there are two main innovations in this paper: firstly, an adaptive image enhancement algorithm was proposed to improve the image quality under complex illumination conditions; Secondly, a novel and lightweight attention block named Feature difference (FD) model was proposed to detect and recognize traffic signs. Unlike state-of-the-art attention models, which utilizes the difference between two feature maps to generate the attention mask. In this work, the single-stage target detection algorithm SSD was selected as the basic network, the backbone network was set as ResNet and VGG respectively and FD module was added. A large number of experiments were carried out to evaluate the optimization effect of FD module. The following conclusions can be drawn: image enhancement algorithms can provide better image samples; The FD model can be integrated into most of CNNs just by adding some shortcut connections, which does not introduce any additional parameters and layers; The average detection accuracy with FD module is 1.80% higher and the average recall rate was 1.51% higher than that without FD module, which has no great influence on the running speed. The FD module has better enhancement effect for dark image detection; The detection accuracy of the FD module is slightly better than other attention modules including BAM, CBAM and SE; The FD model can be used to evaluate the effect of the convolutional operation on features, which could help to find convolutional layers that have little effect on the accuracy of recognition for the network pruning.

Channel adaptive underwater image enhancement algorithm based on pixel level

Adaptive Fractional Order Differential Image Enhancement Algorithm Based on Image Complexity

Infrared imaging plays a crucial role in the detection of weak targets (e.g., low-altitude vehicles) against complex backgrounds. However, challenges such as low contrast, high noise and uneven illumination often degrade image quality and hinder reliable target detection. In this paper, In order to address these problems, we systematically investigate six image enhancement algorithms: grey-scale transformation, histogram equalisation (HE), contrast-constrained adaptive histogram equalisation (CLAHE), Laplace filtering, single-scale Retinex (SSR), and multi-scale Retinex with colour reduction (MSRCR). We use objective metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) to evaluate the enhancement performance. In addition, we refine the evaluation by analysing PSNR and SSIM for the entire image as well as for regions of interest (ROIs) containing weak targets. This regional evaluation allows us to gain a more targeted understanding of the impact of enhancement on the detection of critical regions. Experimental results show that the Retinex-based method with Raschmann filtering significantly improves target visibility while suppressing background noise. This work provides a solution for infrared image enhancement and evaluation that has practical implications for aerospace sensing systems.

Indoor and outdoor real-time monitoring of scenes has become a hot topic for decades. This paper analyzes the median filter and its shortcomings and proposes a modified detection method for moving objects with complex background. Using the method based on decision-making data gives the weights of a consecutive sequence of frames to calculate the weighted average of the corresponding values of pixel in them and the background is modeled for real-time updating. Besides, the thrice threshold processing used to detect and extract objects is presented, which is by using a combination of standard deviation in weighted algorithm and the adaptive threshold algorithm. The experiment results indicate that adopting this method can separate the object from the background and remove the background mistaken for objects and meet the system's real-time requirements of monitoring.

To solve the complex background problems (e.g. Noise interference, object overlap, and different illumination) that affect the classification performance on plant leaf images, this paper proposes an instance segmentation and classification method for plant leaf images based on IFPN SNMS CFFI-Mask R-CNN (ISC-MRCNN) and ACPSOSVM-Dual Channels Convolutional Neural Network (APS-DCCNN). To obtain the foreground of plant leaf images, the lateral connection structure of the feature map pyramid in ISC-MRCNN fuses the feature maps of different depths, so that the network learns more detailed features. Then, the Soft Non-Maximum Suppression Algorithm is employed to improve the detection performance of overlapping objects. Next, the pooling method of integrating the continuous function can reduce the precision loss during the alignment of the mapping between the feature map and the original image. Finally, by constructing a mask filter layer, complex backgrounds are masked. To distinguish the similarity between plant leaf images, APS-DCCNN is used to classify the foreground images. In this process, the Support Vector Machine is used to replace softmax and then an Adaptive Chaotic Particle Swarm Algorithm is employed to optimize it. The experimental results show that compared with Mask R-CNN, the average precision of ISC-MRCNN has increased by 1.89% under different thresholds. The proposed method is suitable for the object detection and instance segmentation problems with complex background. Besides, compared with traditional CNN, the average precision of the classification results obtained by APS-DCCNN has improved by 1.59%. This has shown that the proposed method is suitable for the classification of plant leaves.

Coal gangue separation serves as an effective method to enhance coal quality, and machine vision-based coal gangue detection methods hold significant research and application potential. Industrial dust leads to unclear imaging and affects detection accuracy. However, there is currently little research on the impact of dust. To achieve high visual detection performance of coal and gangue under dust conditions, this study researched visual characteristics and detection methods under smoke-simulated dust conditions. Firstly, we analyze the influence of smoke concentration on the coal gangue images captured by a line array camera, showing that the higher the smoke concentration, the lower the image brightness and clarity. Subsequently, we proposed an adaptive image enhancement algorithm MSRCP-Ada-BR by integrating an adaptive brightness regularization method into the MSRCP algorithm. Experimental results demonstrate that this algorithm significantly enhances the brightness and clarity of coal gangue images across varying smoke concentrations, aligning the pixel distribution of the enhanced images more closely with that of smoke-free images. Ultimately, by integrating the MSRCP-Ada-BR into the input of YOLOx network, we construct a coal gangue detection model suitable for dusty environments. Compared to the original YOLOx model, the detection model integrated with MSRCP-Ada-BR achieves a 5.59% improvement in accuracy.

The paper presents a new Adaptive Gain calculating approach when using the Adaptive Image Enhancement algorithm based on Wavelet Transform. The basic technique is to select two different thresholds which divide the input into three parts after the wavelet coefficients are normalized. For the wavelet coefficients less than the smaller threshold, just make the output zero. And this provides a de-noise effect. The output remains unchanged when the wavelet coefficients are greater than the larger one. For the last part, find a function to make the output figure S shape. So the algorithm can give a clear contrast and the function is the key. The final goal is to use this method in the process of Online Vision Measure, we have chosen the TI TMS320 DM642 Digital Signal Processor or DSP because of its powerful multimedia processing capability. What's more, the TI corporation has provided a variety of software develop libraries as well as the 3rd party tools. All such tools make the development more rapid and convenient. After the technique this paper provides is implemented on DSP, a series of optimization will be performed to make it suitable for industry real-time usage.

Accurate and robust localization of roadheaders is essential for intelligent control in underground coal mining, where visual perception systems face significant challenges such as low illumination, abrupt lighting changes, dust interference, and complex backgrounds. This paper proposes a stereo vision-based localization method for roadheaders that integrates point and line features to enhance pose estimation accuracy and robustness under complex lighting conditions. To address image degradation caused by the coexistence of low-light and overexposed regions, an adaptive multi-region image enhancement approach is developed. The method dynamically segments the image into high-, medium-, and low-illumination regions based on average brightness and standard deviation, applying region-specific enhancement strategies such as gamma correction, CLAHE, and contrast adjustment. A gradient-based weighted fusion mechanism and bilateral filtering are introduced to improve image quality and feature extraction stability. Line features are extracted using EDLines and represented via Plücker coordinates. A joint point-line optimization model with a dynamic weighting scheme is constructed to improve localization robustness. Experiments on public datasets including EuRoc MAV and KITTI demonstrate that the proposed method achieves an absolute pose error (APE) of 0.10 m and root mean square error (RMSE) of 0.13 m, outperforming existing methods such as PL-SLAM and PL-EDLines-SLAM. Further validation in a dust- and glare-simulated underground environment yields an APE of 0.15 m and RMSE of 0.17 m, confirming the method’s environmental adaptability and practical applicability. This study provides a reliable visual localization solution for underground roadheaders, supporting downstream tasks such as path planning, tracking control, and autonomous operation.

The traffic block port monitors and manages the road traffic by shooting and recording the motor vehicles. However, due to the complex factors such as shooting angle, light condition, environmental background, etc., the recognition rate of license plate is not high enough. High light and low light under complex lighting conditions are symmetry problems. This paper analyzes and solves the low light problem in detail, an image adaptive enhancement algorithm under low light conditions is proposed in the paper. The algorithm mainly includes four modules, among which, the fast image classification module uses the deep and separable convolutional neural network to classify low-light images into low-light images by day and low-light images by night, greatly reducing the computation burden on the basis of ensuring the classification accuracy. The image enhancement module inputs the classified images into two different image enhancement algorithms and adopts the idea of dividing and ruling; the image quality evaluation module adopts a weighted comprehensive evaluation index. The final experiment shows that the comprehensive evaluation indexes are all greater than 0.83, which can improve the subsequent recognition of vehicle face and license plate.

For camera movement causes moving objects detecting and tracking problems under complex background, we propose an adaptive object detection scope algorithm based on SIFT features. Firstly, let camera stationary and obtain three images to detect the moving object by using three-frame-difference method, then extract the object SIFT features. Secondly, according to the location and displacement of the object in the dynamic background, we determine the detection scope which matches the object well and obtain the minimum rectangle which can surround the right matching points in the detection scope, and then update the object template. The algorithm avoids the analysis of the complex relative motion between the object and the background, and reduces mismatch points and the calculation amount. This algorithm can quickly and accurately track the object without occlusion, and performs robust in small occlusion case.

Spread spectrum signal have some characteristics, for example anti multipath fading, anti-interception and so on, it had been widely used in the field of unmanned aerial vehicle communication. So studying the identification of spread spectrum signal in UAV communication link has important meaning. Combining practical application, this paper advance an improved method for the identification of spread spectrum signal in UAV communication link. This method is based on the adaptive filter, combining with multiple correlation spectrum calculation to enhance the recognition effect of spread spectrum signal, and optimizing process, thus can suppress the interference and enhance the recognition effect of spread spectrum signal in complex background. At the same time, using the MATLAB simulation experiment test the recognition function of the improved method, this can establish the theory basis for practical application.

Multi-Frame Adaptive Image Enhancement Algorithm for vehicle-mounted dynamic scenes

Efficient defect detection in photovoltaic (PV) panels is essential for optimizing the efficiency and reliability of solar power systems, crucial for advancing sustainable energy solutions. Traditional defect detection methods, relying on physical inspections or electrical analyses, are not only labor-intensive but also become economically inefficient when applied on a large scale. Addressing these challenges, this study introduces SG-YOLOv8, an enhanced version of the YOLOv8 algorithm tailored for automated defect detection in PV panels through sophisticated infrared image analysis. This novel algorithm enhances detection capabilities by integrating spatial attention mechanisms and depthwise separable convolutions, which significantly optimize the feature extraction process for improved accuracy. Furthermore, SG-YOLOv8 employs an advanced soft-NMS technique, innovatively designed to prevent the loss of detection accuracy caused by improper threshold settings in traditional NMS algorithms. Experimental results confirm that SG-YOLOv8 surpasses traditional methods, showing superior accuracy and processing speed, especially in detecting minute defects and operating effectively against complex backgrounds. These findings not only demonstrate the potential of advanced machine learning techniques in the field of PV defect detection but also underscore the algorithm’s effectiveness and scalability as a crucial tool for enhancing solar power system maintenance.

In this paper a new skin detection method based on adaptive thresholds is proposed. Compared with the fixed threshold histogram method used widely, ours can find optimal thresholds to the different complex backgrounds. Four clues are summarized from the skin probability distribution histogram (SPDH) to help search candidates of optimum thresholds, and an ANN classifier is trained to select the final optimum threshold. A color deviation histogram (CDH) is also proposed to eliminate confusing backgrounds and refine optimal thresholds. The selection process of optimal thresholds is fast thus appropriate for real-time applications since no iterative operation is involved. Experimental results show that the proposed method can achieve better performance than the fixed threshold histogram method.