Illumination Problem Research Articles

Rethinking of Underwater Image Restoration Based on Circularly Polarized Light

Polarimetric imaging technology plays a crucial role in de-scattering, particularly in the field of underwater image restoration. Circularly polarized light (or the underlying circular polarization memory effect) has been proven to better preserve the polarization characteristics of detected light. Utilizing circularly polarized light as illumination can further enhance the effectiveness of polarization de-scattering techniques. After rethinking the advantages of circularly polarized light, this paper proposes a new method for underwater polarimetric imaging restoration that leverages the pre-processing of polarized sub-images and the correlation of polarization characteristics (i.e., the angle of polarization and degree of polarization). Additionally, to address the challenge of selecting scattering light parameters due to uneven light fields in target scenes, an intensity adjustment factor search algorithm is designed. This algorithm eliminates the need for the manual selection of scattering light parameters, effectively solving the problem of uneven illumination in restoration results. A series of experiments demonstrate that, compared to traditional algorithms, the proposed method offers superior detail restoration and higher robustness.

Single-molecule localization microscopy at 2.4-fold resolution improvement with optical lattice pattern illumination

Traditional camera-based single-molecule localization microscopy (SMLM), with its high imaging resolution and localization throughput, has made significant advancements in biological and chemical researches. However, due to the limitation of the fluorescence signal-to-noise ratio (SNR) of a single molecule, its resolution is difficult to reach to 5 nm. Optical lattice produces a nondiffracting beam pattern that holds the potential to enhance microscope performance through its high contrast and penetration depth. Here, we propose a new method named LatticeFLUX which utilizes the wide-field optical lattice pattern illumination for individual molecule excitation and localization. We calculated the Cramér-Rao lower bound of LatticeFLUX resolution and proved that our method can improve the single molecule localization precision by 2.4 times compared with the traditional SMLM. We propose a scheme using 9-frame localization, which solves the problem of uneven lattice light illumination. Based on the experimental single-molecule fluorescence SNR, we coded the image reconstruction software to further verify the resolution enhancement capability of LatticeFLUX on simulated punctate DNA origami, line pairs, and cytoskeleton. LatticeFLUX confirms the feasibility of using 2D structured light illumination to obtain high single-molecule localization precision under high localization throughput. It paves the way for further implementation of ultra-high resolution full 3D structured-light-illuminated SMLM.

Converted wave tomography based on inverse level set and adjoint formulation

SUMMARY Shear wave velocity (Vs) is a fundamental property of elastic media whose estimation from PS converted waves is challenging and requires modelling the boundary where P to S conversion occurs. This paper presents a PS tomography where seismic wave conversion/reflection points correspond to reflectors modelled with the level-set function set to zero [ϕ(x, z) = 0]. The proposed method aims for stable Vs inversion in a seismic acquisition setting using multicomponent receivers. Synthetic models simulating true Vs, Vp and the location of the geological reflector are used in the study. The inversion starts by locating a flat reflector, ϕ(x, z) = 0, which defines the zone Ω1 between the surface and the reflector, where the initial Vs and Vp fields are also set. To calculate the traveltimes of incident PT (P wave that propagates in Ω1 from source to the reflector), converted PS and reflected PP waves, for both observed and modelled data (forward problem), the methodology proposed by Rawlinson and Sambridge is adopted. This method uses the arrival times of the P waves, Tpt, from the seismic source at each reflector point as secondary sources generating the times Tps and Tpp. These times are calculated as a solution to the eikonal equation by using the Fast Marching method. The PS and PP residual times are minimized by updating Vs, Vp and ϕ(x, z) = 0 through adjoint variables designed from a formulation using Lagrange Multipliers in a variational context. The performance of the algorithm is evaluated for models with synclinal, sinusoidal and monoclinal reflector geometries using numerical tests considering the inversion of: (1) ϕ, given the true values of Vs and Vp; (2) ϕ and Vs, given the true value of Vp; (3) ϕ and Vp, given the true value of Vs and (4) the three parameters ϕ, Vs and Vp, simultaneously. Good results are obtained by inverting Vs and ϕ, given the true value of Vp. The simultaneous inversion of the three parameters exhibits promising results, despite the illumination problems caused by the different distribution of the PS, PP and PT time gradients due to the geometry of the reflectors and the acquisition setting (sources–receivers in the same plane). The proposed tomography estimates Vs and reflector positions which could help in statics corrections and improve the lithological characterization of near surface.

Lightweight underwater image adaptive enhancement based on zero-reference parameter estimation network

Underwater images suffer from severe color attenuation and contrast reduction due to the poor and complex lighting conditions in the water. Most mainstream methods employing deep learning typically require extensive underwater paired training data, resulting in complex network structures, long training time, and high computational cost. To address this issue, a novel ZeroReference Parameter Estimation Network (Zero-UAE) model is proposed in this paper for the adaptive enhancement of underwater images. Based on the principle of light attenuation curves, an underwater adaptive curve model is designed to eliminate uneven underwater illumination and color bias. A lightweight parameter estimation network is designed to estimate dynamic parameters of underwater adaptive curve models. A tailored set of non-reference loss functions are developed for underwater scenarios to fine-tune underwater images, enhancing the network’s generalization capabilities. These functions implicitly control the learning preferences of the network and effectively solve the problems of color bias and uneven illumination in underwater images without additional datasets. The proposed method examined on three widely used real-world underwater image enhancement datasets. Experimental results demonstrate that our method performs adaptive enhancement on underwater images. Meanwhile, the proposed method yields competitive performance compared with state-of-the-art other methods. Moreover, the Zero-UAE model requires only 17K parameters, minimizing the hardware requirements for underwater detection tasks. What’more, the adaptive enhancement capability of the Zero-UAE model offers a new solution for processing images under extreme underwater conditions, thus contributing to the advancement of underwater autonomous monitoring and ocean exploration technologies.

A fluorescence detection method for postharvest tomato epidermal defects based on improved YOLOv5m.

Tomato quality visual grading is greatly affected by the problems of smooth skin, uneven illumination and invisible defects that are difficult to identify. The realization of intelligent detection of postharvest epidermal defects is conducive to further improving the economic value of postharvest tomatoes. An image acquisition device that utilizes fluorescence technology has been designed to capture a dataset of tomato skin defects, encompassing categories such as rot defects, crack defects and imperceptible defects. The YOLOv5m model was improved by introducing Convolutional Block Attention Module and replacing part of the convolution kernels in the backbone network with Switchable Atrous Convolution. The results of comparison experiments and ablation experiments show that the Precision, Recall and mean Average Precision of the improved YOLOv5m model were 89.93%, 82.33% and 87.57%, which are higher than YOLOv5m, Faster R-CNN and YOLOv7, and the average detection time was reduced by 47.04 ms picture-1. The present study utilizes fluorescence imaging and an improved YOLOv5m model to detect tomato epidermal defects, resulting in better identification of imperceptible defects and detection of multiple categories of defects. This provides strong technical support for intelligent detection and quality grading of tomatoes. © 2024 Society of Chemical Industry.

LVIF-Net: Learning synchronous visible and infrared image fusion and enhancement under low-light conditions

In recent years, the fusion of infrared and visible images has gained significant prominence in the effort to seamlessly integrate salient objects and intricate textures within the fused imagery. While numerous fusion techniques have demonstrated commendable performance, the image quality is notably compromised in low-light environments. This predicament can be attributed to insufficient feature extraction, the inherent low-illumination characteristics of the source images, and the suppression of dark backgrounds. In this study, we introduce a novel approach for simultaneous image fusion and enhancement, aiming to achieve robust fusion performance even in low-light conditions. Our proposed method involves the development of an image fusion network, known as LVIF-Net, which is designed to facilitate multi-layer feature interactions for the enhancement of complementary low-light visible and infrared feature extraction. To solve the problem of low illumination in fused images, we further introduce an Image Decomposition Network (IDN) to guide the LVIF-Net to correct the illumination component of the fused image to obtain enhanced fused images. In addition, for coping with influence of dark background, we design a local region content loss to enhance infrared information in different intensity regions between source images. Extensive experiments on the low-light images on LLVIP and MFNet datasets have shown that the proposed method achieves significant advantages under low-light conditions.

Human intrusion detection for high-speed railway perimeter under all-weather condition

PurposeThe paper aims to solve the problem of personnel intrusion identification within the limits of high-speed railways. It adopts the fusion method of millimeter wave radar and camera to improve the accuracy of object recognition in dark and harsh weather conditions.Design/methodology/approachThis paper adopts the fusion strategy of radar and camera linkage to achieve focus amplification of long-distance targets and solves the problem of low illumination by laser light filling of the focus point. In order to improve the recognition effect, this paper adopts the YOLOv8 algorithm for multi-scale target recognition. In addition, for the image distortion caused by bad weather, this paper proposes a linkage and tracking fusion strategy to output the correct alarm results.FindingsSimulated intrusion tests show that the proposed method can effectively detect human intrusion within 0–200 m during the day and night in sunny weather and can achieve more than 80% recognition accuracy for extreme severe weather conditions.Originality/value(1) The authors propose a personnel intrusion monitoring scheme based on the fusion of millimeter wave radar and camera, achieving all-weather intrusion monitoring; (2) The authors propose a new multi-level fusion algorithm based on linkage and tracking to achieve intrusion target monitoring under adverse weather conditions; (3) The authors have conducted a large number of innovative simulation experiments to verify the effectiveness of the method proposed in this article.

Research on Pedestrian Re-identification Techniques in Dynamic Scenes Using Convolutional Neural Networks

Abstract Pedestrian re-recognition is the process of retrieving pedestrians with the same identity information as a given pedestrian from a cross-domain view candidate image dataset or a non-overlapping surveillance video sequence using computer vision techniques. The goal of this paper is to use convolutional neural network techniques to re-recognize pedestrians in dynamic scenes. Through the use of convolutional calculations, activation function selection, and other techniques, this paper provides basic technical support for the research of pedestrian re-recognition technology. A Siamese network is obtained by applying convolutional neural networks to pedestrian recognition as the main discriminative model for subsequent research. In order to effectively solve the problem of occlusion, illumination, and other possible interference with the recognition effect in dynamic scenes, this paper adopts the image enhancement method of random erasure and introduces the attention mechanism to improve the robustness of the model to the occlusion of pedestrian images. Through the examination of the model on the dataset of the average accuracy mean (MAP) and other indicators and the actual application in the construction site and other scenes, it is proved that the pedestrian re-recognition model used in this paper has a more significant recognition performance compared with other models, and can still maintain more than 80% of the accuracy rate under the application of dynamic and complex scenes.

Fractional and B-COSFIRE filter based approach for efficient segmentation of retinal blood vessels

The morphological structure of retinal blood vessels plays an important role in diagnosing ophthalmic diseases such as glaucoma and diabetic retinopathy. Diabetic retinopathy is one of the leading causes of blindness worldwide. Because of the need to examine a large number of individuals on a daily basis, it is indeed challenging for ophthalmologists to analyze the complex retinal vasculature of every outpatient. Automated segmentation of retinal blood vessels can be of significant aid in this labor-intensive process. This work proposes an unsupervised approach for retinal blood vessel segmentation. Here, we enhance the performance of the B-COSFIRE filters for segmentation of the retinal vasculature by denoising a retinal image using a fractional filter derived from a left/forward weighted fractional integral prior to the vascular enhancement by B-COSFIRE filters. Also, we utilize hysteresis thresholding rather than a single global threshold to obtain the final segmented vessels enhanced by the B-COSFIRE filters. This helps to avoid the problem of nonuniform illumination and poor contrast in retinal images.

Segmentation of Seabed Sediment Images Based on Convolutional Neural Network

The analysis of particle sizes in seabed sediments plays an important role in various fields. However, acquiring digital sediment images has been challenging due to the characteristics of sediment particles and the complexity of the seabed exploration environment. The goal of this study is to address the issue of particle segmentation in sediment images and propose an innovative network called SAMU-Net. Innovations are as follows. Firstly, SAMU-Net combines spatial attention modules with the traditional U-Net model, which allows for contextual information extraction and adaptive perception of feature variations. Secondly, the model adopts the idea of multi-scale fusion, enabling networks to better understand the structural and semantic information of the images by fusing feature maps at different scales. In addition, using the drop blocks and normalization, we speed up the training convergence of the model and avoid the overfitting phenomenon. The results show that the segmentation results predicted by the SAMU-Net network are highly similar to the ground truth and have a better segmentation performance compared to the existing algorithms. At the same time, it provides a new solution idea to uneven illumination and other noise interference problems in the digital imaging information of sediments.

Automatic Control Method for Street Lights in Unideal Lighting Environments Based on Deep Learning

In response to the control problem and power consumption problem of outdoor illumination in imperfect lighting environments, a deep learning based automatic control method for street luminaires in imperfect lighting environments is studied and an automatic control model for street lights in an imperfect lighting environment based on deep learning is constructed. Use sensors to collect temperature, humidity, air pressure, and haze values that are significantly correlated with the brightness of ilumination in the same environment. Based on the collected data, use a deep learning short-term memory network to predict the current street illumination brightness, and use the Whale Optimization Algorithm to optimize network parameters. Using window filtering and one-dimensional Kalman filtering to filter the predicted data of illumination, the predicted street illuminance data after filtering is compared with the expected values. Based on this, a discretized PID controller (proportional–integral–derivative controller) is used to output the dimming value to achieve street lamp control. The experimental results show that this method can accurately predict the current characteristic of street lamps, and has good brightness control results in poor lighting environments, as well as better energy-saving performance.

Cognitive Inspired & Computationally-Intelligent Early Melanoma Detection Using Feature Analysis Techniques

Melanoma is the most malignant kind of skin cancer, and it is responsible for the majority of deaths caused by skin cancer. However, this can be easily addressed by reverting to the standard method of damage removal if it is discovered in a timely manner. In this view, it is of the utmost importance to develop procedures for the early and reliable identification of melanomas. Since images for melanoma diagnosis are recorded in the clinic as an epiluminance image using a specific kind of equipment, the technique is machine-dependent. We make use of a method for managing images as well as a high-resolution shading image of a skin ulcer captured by a high-resolution camera or other device. Instead of depending on the epilumination images that are produced by the emergency equipment, the initial task that needs to be done in the present research is to capture high-resolution photographs of the skin injuries. The category limit will be determined with the use of machine learning, and then highlight extraction will take place. The research focuses on clinical photos obtained from fast cameras that were taken of individuals suffering from skin cancer. The problem of uneven illumination was kept at a strategic distance by the use of medial separation and pre-processing using the histogram. Utilisation of a brand new image segmentation method called "Otsu" for the extraction of sores. The extraction of ABCD (Asymmetry, Border, Color, and Dimension) involves the use of innovative methodologies as well as the Total Dermoscopic Value in order to characterise the weight coefficients. A solution to the problem of upgrading the categorization error that is based on machine learning. The parameters that are taken into consideration for evaluating the proposed model are senstivity, specificity, precision and accuracy and the results obtained are 1, 0.93, 0.93, and 0.93 respectively. It has been observed that the proposed model performs better as compared to the ones present in existing literature.

The New Kernel-based Multiple Instances Learning Algorithm for Object Tracking

Background:: Visual tracking is a crucial component of computer vision systems. Objective:: To deal with the problems of occlusion, pose variation, and illumination in long-time tracking, we propose a new kernel-based multiple instances learning tracker. objective: visual tracking Method:: The tracker captures five positive bags, including the occlusion bag, pose bag, illumination bag, scale bag, and object bag, to deal with the appearance changes of an object in a complex environment. A Gaussian kernel function is used to compute the inner product for selecting the powerful weak classifiers, which further improves the efficiency of the tracker. Moreover, the tracking situation is determined by using these five classifiers, and the correlating classifiers are updated. Results:: The experimental results show that the proposed algorithm is robust in terms of occlusion and various appearance changes. Conclusion:: The proposed algorithm preforms well in complex situations. conclusion: And it preforms well in complex situation.

A lightweight object detection framework for underwater imagery with joint image restoration and color transformation

Traditional underwater detectors struggle to match the demands of visual observation and icon detection because of the underwater optical pictures' color distortion, uneven illumination, and excessive noise levels. In this paper, a lightweight deep-water object detection network is proposed, which consists of three key components, namely image restoration, color transformation, and object detection. First, we propose a lightweight attention module for the problems of color distortion and uneven illumination in underwater images. This module pays more attention to the areas with a greater influence of underwater color when dealing with different types of poor-quality images. Second, to reduce the computational complexity of object detection, we propose a color conversion module based on the laplacian pyramid decomposition. This module incorporates multi-scale features to effectively address the loss of details in the brightest or darkest regions. Finally, we propose a multi-scale dense residual object detection network. The network applies a multi-scale kernel to an improved residual module to realize the extraction and fusion of feature information of multiple receptive fields. Furthermore, to deal with the problem of underwater small-sample object detection, we propose a mutually exclusive loss function. The mutual exclusion loss promotes the update of network parameters so that the classes with different characteristics of samples generated by the network are mutually exclusive. We ran tests on the Pycharm platform to show that the suggested lightweight joint underwater object identification algorithm outperformed the most sophisticated ones. The proposed system was put to the test in an intricate underwater setting, achieving 92.56 percent accuracy and 19.2 frames per second.

Quantum Network Discrimination

Discrimination between objects, in particular quantum states, is one of the most fundamental tasks in (quantum) information theory. Recent years have seen significant progress towards extending the framework to point-to-point quantum channels. However, with technological progress the focus of the field is shifting to more complex structures: Quantum networks. In contrast to channels, networks allow for intermediate access points where information can be received, processed and reintroduced into the network. In this work we study the discrimination of quantum networks and its fundamental limitations. In particular when multiple uses of the network are at hand, the rooster of available strategies becomes increasingly complex. The simplest quantum network that capturers the structure of the problem is given by a quantum superchannel. We discuss the available classes of strategies when considering n copies of a superchannel and give fundamental bounds on the asymptotically achievable rates in an asymmetric discrimination setting. Furthermore, we discuss achievability, symmetric network discrimination, the strong converse exponent, generalization to arbitrary quantum networks and finally an application to an active version of the quantum illumination problem.

An Accurate Reading Algorithm for Substation Pointer Meters Based on Improved 2-D Gamma Function and PA-RetinaNet

Aiming at the low reading accuracy of the substation pointer meter caused by illumination and shooting angle, an accurate reading algorithm based on improved 2-D Gamma function and PA-RetinaNet is proposed. Firstly, the multi-scale Gaussian function is used to extract the illumination components and the 2-D Gamma function is reconstructed to adaptively adjust pointer meter images under different illumination intensity. Then, the path augmentation is integrated into the RetinaNet to detect the dial scale digital key points. Meanwhile, combined with the elliptical transformation theory, the correction reference point in the perspective transformation is reselected to realize the tilt correction of the pointer meter image. Finally, the centripetal constraint is added to the line segment detector to achieve accurate positioning of the pointer, and the function between the pointer angle and the meter reading is deduced. Experimental results demonstrated that the method can effectively solve the problem of illumination and shooting angle in the reading of the substations pointer meter.

Ensemble Convolution Neural Network for Robust Video Emotion Recognition Using Deep Semantics

Human emotion recognition from videos involves accurately interpreting facial features, including face alignment, occlusion, and shape illumination problems. Dynamic emotion recognition is more important. The situation becomes more challenging with multiple persons and the speedy movement of faces. In this work, the ensemble max rule method is proposed. For obtaining the results of the ensemble method, three primary forms, such as CNNHOG-KLT, CNNHaar-SVM, and CNNPATCH are developed parallel to each other to detect the human emotions from the extracted vital frames from videos. The first method uses HoG and KLT algorithms for face detection and tracking. The second method uses Haar cascade and SVM to detect the face. Template matching is used for face detection in the third method. Convolution neural network (CNN) is used for emotion classification in CNNHOG-KLT and CNNHaar-SVM. To handle occluded images, a patch-based CNN is introduced for emotion recognition in CNNPATCH. Finally, all three methods are ensembles based on the Max rule. The CNNENSEMBLE for emotion classification results in 92.07% recognition accuracy by considering both occluded and nonoccluded facial videos.

A novel cancelable finger vein templates based on LDM and RetinexGan

In this paper, we propose a new biometric template protection scheme, which can deal with the finger vein biometric security threats, through using the LDM and RetinexGAN model. The RetinexGAN model is mainly used to handle the illumination and low contrast problems effectively, while efficiently extracting discriminative features from the finger vein images. The projection of extracted features into dissimilarity space is done using Local Dissimilarity Map (LDM). LDM is an efficient way for finger vein features representation, which investigates the relationships and correlation inter and intra classes, while effectively coming up with the accidental shifts/rotations caused by the arbitrary position of the finger during image acquisition. The proposed approach is successfully evaluated in terms of non-invertibility, non-linkability, revocability and performances. Experimental results and comparison analysis with the state of arts methods confirm that the proposed framework can achieve promising results.

ELFPIE: an error-laxity Fourier ptychographic iterative engine

We present a simple but efficient and robust reconstruction algorithm for Fourier ptychographic microscopy, termed error-laxity Fourier ptychographic iterative engine (Elfpie), that is simultaneously robust to (1) noise signal (including Gaussian, Poisson, and salt & pepper noises), (2) problematic background illumination problem, (3) vignetting effects and (4) misaligning of LED positions, without the need of calibrating or recovering these system errors. In Elfpie, we embed the inverse problem of FPM under the framework of feature extraction/recovering and propose a new image gradient-based data fidelity cost function regularized by the global second-order total-variation regularization. The closed-form complex gradient for the cost function is derived and is back-propagated using the AdaBelief optimizer with an adaptive learning rate. The Elfpie was tested on both simulation and experimental data. In general, compared against SOTA methods, the Elfpie is robust to Gaussian noise with a 100 times larger noise, salt & pepper noise with 1000 times larger noise and Poisson noise with 10 times larger noise. The Elfpie is able to reconstruct high-fidelity samples under LED position misalignments up to 2 mm. It can also bypass the vignetting effect, for which all SOTA methods fail to reconstruct the sample pattern. The MATLAB code for ELFPIE is available on Github.

Instant deep sea debris detection for maneuverable underwater machines to build sustainable ocean using deep neural network

Deep sea debris is any persistent man-made material that ends up in the deep sea. The scale and rapidly increasing amount of sea debris are endangering the health of the ocean. So, many marine communities are struggling for the objective of a clean, healthy, resilient, safe, and sustainably harvested ocean. That includes deep sea debris removal with maneuverable underwater machines. Previous studies have demonstrated that deep learning methods can successfully extract features from seabed images or videos, and are capable of identifying and detecting debris to facilitate debris collection. In this paper, the lightweight neural network (termed DSDebrisNet), which can leverage the detection speed and identification performance to achieve instant detection with high accuracy, is proposed to implement compound-scaled deep sea debris detection. In DSDebrisNet, a hybrid loss function considering the illumination and detection problem was also introduced to improve performance. In addition, the DSDebris dataset is constructed by extracting images and video frames from the JAMSTEC dataset and labeled using a graphical image annotation tool. The experiments are implemented on the deep sea debris dataset, and the results indicate that the proposed methodology can achieve promising detection accuracy in real-time. The in-depth study also provides significant evidence for the successful extension branch of artificial intelligence to the deep sea research domain.