An efficient image dehazing method based on improved FFANet

Automatic color equalization (ACE) algorithm is an effective method for color image enhancement, but its computational complexity is extremely high. In this paper, we first modify the ACE algorithm to reduce the computational complexity and realization cost while maintaining good visual quality. Subsequently, an efficient VLSI architecture for the hardware-friendly ACE algorithm is proposed to meet the requirement of real-time image enhancement. FPGA (Field Programmable Gate Arrays) implementation result shows that the proposed architecture can operate at 120MHz and achieve a throughput of 60 frame/s for 256×256 resolution images using about 1.15k and 1.78k of FPGA's logic (LUT) and register resources, respectively. Compared with the existing design, the proposed architecture can achieve higher performance with fewer hardware resources and comparable visual quality.

With the increasing popularity of digital image applications, the importance of image enhancement technology is becoming more and more prominent. In recent years, the continuous progress of deep learning (DL) technology has led to the improvement of the performance of image enhancement algorithm. However, there are still some challenges in improving the learning efficiency of deep network, improving the performance of algorithm in actual scene and optimizing algorithm according to task orientation. Traditional stochastic resonance (SR) mostly relies on experience to manually adjust parameters in image processing, which leads to low efficiency. Therefore, this paper proposes a method that combines computer DL technology with SR image enhancement. In addition, the existing enhancement algorithms generally have the problem that the quality of some dimensions cannot be achieved at the same time. Based on this phenomenon, we further discuss the task-oriented optimization of the enhancement model based on deep network and the hybrid multi-distortion enhancement model. It has a good denoising effect on low-quality images and effectively improves the overall quality of images.

This paper studies the implementation of an algorithm to enhance the color of an image by considering global and local effects. The implementation is done on Matlab((and also on a FPGA using VHDL. The algorithm is called ACE (automatic color equalization). The paper presents the optimization of the algorithm using a subset or window. The algorithm performs the color enhancement automatically by equalizing the colors and improving the image. The results show an image with more contrast, higher number of details and visually better. Indeed, ACE maximizes the information of the image. The optimization of the algorithm reduces the complexity of the original one. Additionally, the VHDL implementation is quite faster than Matlab's.

Remote robotic exploration holds vast potential for gaining knowledge about extreme environments, which is difficult to be accessed by humans. In the last two decades, various underwater devices were developed for detecting the mines and mine‐like objects in the deep‐sea environment. However, there are some problems in recent equipment, like poor accuracy of mineral objects detection, without real‐time processing, and low resolution of underwater video frames. Consequently, the underwater objects recognition is a difficult task, because the physical properties of the medium, the captured video frames, are distorted seriously. In this paper, we are considering use of the modern image processing methods to determine the mineral location and to recognize the mineral actually within a little computation complex. We firstly analyze the recent underwater imaging models and propose a novel underwater optical imaging model, which is much closer to the light propagation model in the underwater environment. In our imaging system, we remove the electrical noise by dual‐tree complex wavelet transform. And then we solve the nonuniform illumination of artificial lights by fast guided trilateral bilateral filter and recover the image color through automatic color equalization. Finally, a shape‐based mineral recognition algorithm is proposed for underwater objects detection. These methods are designed for real‐time execution on limited‐memory platforms. This pipeline is suitable for detecting underwater objects in practice by our experiences. The initial results are presented and experiments demonstrate the effectiveness of the proposed real‐time visualization system.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Image enhancement is a crucial pre-processing step for various image processing applications and vision systems. Many enhancement algorithms have been proposed based on different sets of criteria. However, a direct multi-scale image enhancement algorithm capable of independently and/or simultaneously providing adequate contrast enhancement, tonal rendition, dynamic range compression, and accurate edge preservation in a controlled manner has yet to be produced. In this paper, a multi-scale image enhancement algorithm based on a new parametric contrast measure is presented. The parametric contrast measure incorporates not only the luminance masking characteristic, but also the contrast masking characteristic of the human visual system. The formulation of the contrast measure can be adapted for any multi-resolution decomposition scheme in order to yield new human visual system-inspired multi-scale transforms. In this article, it is exemplified using the Laplacian pyramid, discrete wavelet transform, stationary wavelet transform, and dual-tree complex wavelet transform. Consequently, the proposed enhancement procedure is developed. The advantages of the proposed method include: 1) the integration of both the luminance and contrast masking phenomena; 2) the extension of non-linear mapping schemes to human visual system inspired multi-scale contrast coefficients; 3) the extension of human visual system-based image enhancement approaches to the stationary and dual-tree complex wavelet transforms, and a direct means of; 4) adjusting overall brightness; and 5) achieving dynamic range compression for image enhancement within a direct multi-scale enhancement framework. Experimental results demonstrate the ability of the proposed algorithm to achieve simultaneous local and global enhancements.

Imaging through the fog is valuable for many areas, such as autonomous driving and cosmic exploration. However, due to the influence of strong backscattering and diffuse reflection generated by the dense fog on the temporal-spatial correlations of photons returning from the target object, the reconstruction quality of most existing methods is significantly reduced under dense fog conditions. In this study, we describe the optical scatter imaging process and propose a physics-driven Swin Transformer method utilizing Time-of-Flight (ToF) and Deep Learning principles to mitigate scattering effects and reconstruct targets in conditions of heterogeneous dense fog. The results suggest that, despite the exponential decrease in the number of ballistic photons as the optical thickness of fog increases, the Physics-Driven Swin Transformer method demonstrates satisfactory performance in imaging targets obscured by dense fog. Importantly, this article highlights that even in dense fog imaging experiments with optical thickness reaching up to 3.0, which exceeds previous studies, commonly utilized quantitative evaluation metrics like PSNR and SSIM indicate that our method is cutting-edge in imaging through dense fog.

In image processing applications, one of the main preprocessing phases is image enhancement that is used to produce high quality image or enhanced image than the original input image. These enhanced images can be used in many applications such as remote sensing applications, geo-satellite images, etc. The quality of an image is affected due to several conditions such as by poor illumination, atmospheric condition, wrong lens aperture setting of the camera, noise, etc [2]. So, such degraded/low exposure images are needed to be enhanced by increasing the brightness as well as its contrast and this can be possible by the method of image enhancement. In this research work different image enhancement techniques are discussed and reviewed with their results. The aim of this study is to determine the application of deep learning approaches that have been used for image enhancement. Deep learning is a machine learning approach which is currently revolutionizing a number of disciplines including image processing and computer vision. This paper will attempt to apply deep learning to image filtering, specifically low-light image enhancement. The review given in this paper is quite efficient for future researchers to overcome problems that helps in designing efficient algorithm which enhances quality of the image.

Real-time smoke detection is of great significance for early warning of fire, which can avoid the serious loss caused by fire. Detecting smoke in actual scenes is still a challenging task due to large variance of smoke color, texture, and shapes. Moreover, the smoke detection in the actual scene is faced with the difficulties in data collection and insufficient smoke datasets, and the smoke morphology is susceptible to environmental influences. To improve the performance of smoke detection and solve the problem of too few datasets in real scenes, this paper proposes a model that combines a deep convolutional generative adversarial network and a convolutional neural network (DCG-CNN) to extract smoke features and detection. The vibe algorithm was used to collect smoke and nonsmoke images in the dynamic scene and deep convolutional generative adversarial network (DCGAN) used these images to generate images that are as realistic as possible. Besides, we designed an improved convolutional neural network (CNN) model for extracting smoke features and smoke detection. The experimental results show that the method has a good detection performance on the smoke generated in the actual scenes and effectively reduces the false alarm rate.

Due to the complexity of medical images, traditional medical image classification methods have been unable to meet the actual application needs. In recent years, the rapid development of deep learning theory has provided a technical approach for solving medical image classification. However, deep learning has the following problems in the application of medical image classification. First, it is impossible to construct a deep learning model with excellent performance according to the characteristics of medical images. Second, the current deep learning network structure and training strategies are less adaptable to medical images. Therefore, this paper first introduces the visual attention mechanism into the deep learning model so that the information can be extracted more effectively according to the problem of medical images, and the reasoning is realized at a finer granularity. It can increase the interpretability of the model. Additionally, to solve the problem of matching the deep learning network structure and training strategy to medical images, this paper will construct a novel multiscale convolutional neural network model that can automatically extract high-level discriminative appearance features from the original image, and the loss function uses the Mahalanobis distance optimization model to obtain a better training strategy, which can improve the robust performance of the network model. The medical image classification task is completed by the above method. Based on the above ideas, this paper proposes a medical classification algorithm based on a visual attention mechanism-multiscale convolutional neural network. The lung nodules and breast cancer images were classified by the method in this paper. The experimental results show that the accuracy of medical image classification in this paper is not only higher than that of traditional machine learning methods but also improved compared with other deep learning methods, and the method has good stability and robustness.

- Visibility degradation caused by haze presents a major challenge for computer vision systems in outdoor environments. This project introduces an enhanced image dehazing method based on Bright and Dark Channel Prior (BDCP), an improvement over traditional dark channel technique. By incorporating both bright and dark channel information, the method more effectively estimates the transmission map and atmospheric light, resulting in clearer and more natural dehazed images. The proposed algorithm refines visual quality through a fusion-based enhancement and edge-preserving filtering. Extensive experiments demonstrate that this approach significantly outperforms conventional methods in terms of contrast restoration and color fidelity, particularly under dense haze conditions. Key Words: Image Dehazing, Dark Channel Prior, Bright Channel Prior, Transmission Estimation, Atmospheric Light, Visibility Restoration, Haze Removal, Image Enhancement.

Fast single image dehazing based on a regression model

Simultaneous Localization and Mapping (SLAM) has become a critical technology for intelligent transportation systems and autonomous robots and is widely used in autonomous driving. However, traditional manual feature-based methods in challenging lighting environments make it difficult to ensure robustness and accuracy. Some deep learning-based methods show potential but still have significant drawbacks. To address this problem, we propose a feature-based visual SLAM system based on the LightGlue deep learning network. It uses deep local feature descriptors to replace traditional hand-crafted features and a more efficient and accurate deep network to achieve fast and precise feature matching. Thus, we use the robustness of deep learning to improve the whole system. We have combined traditional geometry-based approaches to introduce a complete visual SLAM system for monocular, binocular, and RGB-D sensors. We thoroughly tested the proposed system on four public datasets: KITTI, EuRoC, TUM, and 4Season, as well as on actual campus scenes. The experimental results show that the proposed method exhibits better accuracy and robustness in adapting to low-light and strongly light-varying environments than traditional manual features and deep learning-based methods. It can also run on GPU in real time.

We evaluate the error performance of a free space optical (FSO) downlink from a geostationary earth orbit satellite to an earth station in presence of turbulence and different weather conditions such as fog, clouds, etc. Combined channel state probability density function (pdf) is derived by using log-normal model for weak turbulence, gamma–gamma model for moderate to strong turbulence and Beer–Lambert Law for weather effects. Bit error rate (BER) expressions are derived using the combined channel state pdf for on-off keying (OOK), M-ary pulse position modulation (M-PPM) and M-ary differential PPM (M-DPPM) schemes. It is observed that the link performance degrades with increase in the strength of ground level turbulence. Presence of weather conditions causes additional degradation with moderate fog causing the worst effect followed by light and thin fog with respect to clear air condition. Dense or thick fog and/or clouds may lead to complete link failure owing to their large attenuation coefficient. Further, enhancement in the link performance by using aperture averaging and receiver diversity techniques is examined and compared for all three schemes. It is seen that performance improves with increase in the receiver diameter and number of multiple independent receivers. Among the three modulation schemes, link with M-PPM scheme gives the best performance in terms of BER followed by M-DPPM and OOK schemes with or without diversity techniques. Thus, an M-PPM based FSO downlink with an array of finite sized receivers i.e., single input multiple output link can be a viable alternative for efficient data transfer in presence of atmospheric turbulence and different weather conditions from a satellite to an earth station.

Gait recognition is a biometric recognition technology that supports long-distance, multi-target recognition with resistance to partial occlusions and does not require active user cooperation; thus, it is more suitable than other technologies for individual identification in mass video surveillance systems. Gait recognition based on deep learning has become the mainstream technology in this field because of its strong self-learning and model prediction abilities. However, there is still a lack of research focusing on actual scenes and application requirements for gait recognition, such as multi-target, real-time, and robust recognition. Therefore, this paper analyzes the basic tasks of deep gait recognition methods and encapsulates the application scope of deep gait recognition. Subsequently, this paper investigates the methods of large-space deep gait recognition from three aspects: image preprocessing, gait feature extraction with deep learning, and classifier and evaluation. In particular, the study investigated and analyzed the gait input templates often used in mass surveillance, auto encoder with deep learning, and performance evaluation indexes for the first time. Finally, the unresolved issues in deep gait recognition are summarized, and suggestions and directions for future research are presented.