Light Variations Research Articles

Multi-Neural Network Localisation System with Regression and Classification on Football Autonomous Robots

In environments like the RoboCup Middle Size League (MSL), precise and rapid localisation of robots is crucial for effective autonomous interaction. This study addresses the limitations of conventional localisation approaches—often based on single-camera systems or sensors such as LiDAR (Light Detection and Ranging) and infrared—by developing a robust Artificial Intelligence (AI)-based multi-camera system solution. This method uses multiple neural networks, breaking down the problem while taking advantage of both classification and regression methods. The solution includes a classification neural network to detect field markers, such as line intersections, and two regression neural networks: one for calculating the position of the markers, and another for determining the robot’s position in real-time. It takes advantage of both approaches while maintaining the desired performance, accuracy, and robustness, simplifying the training process and adapting it to different scenarios. Designed specifically to meet MSL robotics’s high-speed demands and precision requirements, the system employs data augmentation techniques to ensure resilience against lighting, angles, and position variations. The results show that this optimised approach improves spatial awareness and accuracy, promising robot football advancements. Beyond MSL applications, this method has the potential for broader real-world uses that require dependable, real-time localisation in dynamic settings.

Contactless in vitro detection of carboxyhemoglobin using hyperspectral imaging (HSI).

Hyperspectral imaging (HSI) allows for the contactless analysis of the composition of substances based on the reflected light and is already used in various areas of medicine. The carboxyhemoglobin (CO-Hb) concentration in blood of suspected fire victims serves to prove vitality and the cause of death. However, this metric is usually determined by spectrophotometry in the laboratory. The present study provides the basis for the future development of methods for determining CO-Hb concentrations right at the scene of a corpse or at necropsy using mobile HSI. Human erythrocyte concentrate was mixed with gaseous carbon monoxide using an aerator to produce a series of samples, which were analyzed for their CO-Hb concentration (2.9; 9.7; 18; 27.9; 39.9; 51.9; 62.3; 73.4% CO-Hb) using established spectrophotometric blood gas analysis. These blood samples were stored in a cool place at 4°C, dripped onto a spot plate every 7 days over a period of 6 weeks, and photographed under standardized conditions (ambient lighting, distance and angle of the camera to the sample, camera settings) using the HSI camera SPECIM IQ. This device analyzes each image in the wavelength range from 400 to 1000 nm in 204 spectral bands. The data sets were used to train a lasso regression model, which provides predicted values for the CO-Hb concentration of the blood sample based on their hyperspectral properties. The results were then compared with the results of spectrophotometric measurements. The lasso regression model allowed the prediction of the CO-Hb concentration of the samples with a mean prediction error of 4.46 percentage points, independent of the sample age. Further investigations regarding pre-analytical influencing factors such as variable ambient light and tissue scattering effects, are planned to validate the robustness of the method and realize practical implementations.

Estimation of passion fruit yield based on YOLOv8n + OC-SORT + CRCM algorithm

The precise estimation of passion fruit yield is crucial for efficient orchard management, but it poses challenges such as occlusion, light variations, and camera shake, which can lead to problems such as missed detection, error detection, and double counting of small fruits. In this study, we propose a robust computer vision algorithm named YOLOv8n + OC-SORT + CRCM (Central Region Counting Method) to accomplish three tasks: detection, tracking, and yield estimation of passion fruits. Firstly, we compare the passion fruit detection results using various YOLO series detection algorithms and choose YOLOv8n for detector. Then, OC-SORT algorithm is chosen as the tracker due to its effectiveness in addressing issues like occlusion, vertical shaking, and uneven speeds. Finally, we design CRCM counting algorithm for fruit counting for addressing challenges in estimating passion fruit yield. To validate the effectiveness of these methods, a real-world passion fruit video dataset including 24 videos for each with a 1-minute length was established. In the detection results on the test set, YOLOv8n detector achieved the best results with a mAP@0.5 (mean Average Precision) of 86.3 % and a model size of only 6.2 MB among YOLOv5n, YOLOv7 and YOLOv8n three detectors. Furthermore, the HOTA (higher order tracking accuracy) of OC-SORT tracker was 67.10 %, surpassing three mainstream trackers named BoT-SORT, Byte Track, and Strong SORT by 2.98 %, 4.71 %, and 8.82 %, respectively. In the fruit yield estimation, CRCM demonstrated an average counting accuracy of 87.0 %, surpassing ID number and Single Line Method (SLM) methods by 49.8 % and 10.5 %, respectively. In conclusion, the YOLOv8n + OC-SORT + CRCM algorithm effectively addresses issues of misidentification, missed detections of small fruits, and repeated counts, achieving stable, real-time, and accurate estimation of passion fruit yield.

Abstract WP172: Invariant Pupil Reactivity (PuRe) Score: Robust Smartphone-based Pupillometry for Critical Care Across Lighting, Measurement Conditions, and Hardware Variations

Abstract WP172: Invariant Pupil Reactivity (PuRe) Score: Robust Smartphone-based Pupillometry for Critical Care Across Lighting, Measurement Conditions, and Hardware Variations

Rotation of polarization plane of a laser beam by fluid vorticity

The polarization plane of a beam of light experiences angular drag when it traverses a medium rotating about an axis parallel to the direction of the beam. Here, fluid vorticity in a horizontal Rijke tube is used to cause rotation in the polarization plane of a continuous laser beam. The vorticity distribution and acoustic pressure history in the tube have been predicted numerically. The thermo-acoustic phenomenon in the tube has been found to generate the vorticity. A suitable optical arrangement has been used to capture the light intensity variation due to the rotation of the plane of polarization of the beam, and up to 4° of rotation has been observed.

In search of light: Estimating diffuse attenuation coefficient of downwelling irradiance and its variation in optically complex shallow water habitats using Sentinel-2 imagery.

Frequent resuspension of sediments in the water column hampers photosynthesis in submerged aquatic vegetation due to decreased light, reduces gas exchange from sediment deposition and affects their anchoring ability. Remote sensing of light attenuation of the water column in form of diffuse attenuation coefficient of downwelling photosynthetically available radiation (KdPAR) provides a spatial perspective to study light attenuation of water column. This study aims to use Sentinel-2 derived KdPAR to characterize light variation and test its significance in relation to occurrence of eelgrass (Zostera marina) at Horsens and Roskilde fjords located in coastal waters of Denmark. Areas with maximum of KdPAR (mean>75th percentile) coinciding with maximum and minimum variation (standard deviation >75th and <25th percentile respectively) were identified at the study sites. The standard deviation (SD) of KdPAR and fraction of surface irradiance reaching bottom (PARZ) was used to predict occurrences of eelgrass using Logistic regression (LR) and Support Vector Machine (SVM). The LR and SVM (linear kernel) could predict eelgrass presence-absence with 65% overall accuracy and precision of 63% and 62% respectively on the test set (n=238). SD correlation with eelgrss occurrences (Point-biserial correlation=-0.11, p=0.002) and with predicted probabilities of logistic regression (Pearson's r=-0.46) indicates increased KdPAR variation reduces chances of eelgrass. The KdPAR for this study was derived using Quasi Analytical Algorithm Version-5 (QAA-V5) and Case-2 Regional Coast Colour (C2RCC) and validated against in-situ matched observations (n=113) for duration of March to October of 2016-2018.

Online lane mapping based on multi-sensor SLAM and Catmull–Rom splines

Abstract Traditional offline high-definition maps have significant limitations owing to their high cost and difficulty in updating. Online vector maps represent a new trend in the development of autonomous driving. In this paper, we propose an online lane mapping system, which leverages both multi-sensor simultaneous localization and mapping (SLAM) and Catmull–Rom splines. The map is constructed in real-time through the localization provided by SLAM and the fitting of splines. Existing SLAM algorithms perform poorly in complex urban environments, a deep learning network is incorporated into the visual front-end of our system to improve stability. Deep learning can extract and study deeper and less observable features, so that the system enhances the accuracy of visual tracking in scenarios characterized by low texture, lighting variations, and rapid motion. The system state is optimized by a factor graph framework to achieve precise localization. To construct continuous and consistent online lane maps, our system combines SLAM localization results with spline curves to achieve lane connection. Additionally, we develop a convenient method for initializing, extending, and optimizing the control points of splines to obtain more precise results. Our method combines the geometric characteristics with historical observations of lanes, enhancing the association and consistency of maps. Experiments conducted on the mainstream datasets demonstrate that our system exhibits greater robustness and improves the accuracy of localization and mapping across diverse environments.

Diagnosing anaemia via smartphone colorimetry of the eye in a population of pregnant women

Objective.Screening for disease using a smartphone camera is an emerging tool for conditions such as jaundice and anaemia, which are associated with a colour change (yellowing in jaundice; pallor in anaemia) of the external tissues. Based on this, we aimed to test a technique to non-invasively screen for anaemia in a population highly affected by anaemia: pregnant women in India. In this group, anaemia can have severe health consequences for both the mother and child.Approach.Over 3 years of data collection, in 486 pregnant women in India, we attempted to replicate a previously successful smartphone imaging technique to screen for anaemia. Using smartphone images of the eye and eyelid, we compared two techniques (white balancing and ambient subtraction) to control for variation in ambient lighting, and then extracted 'redness' features from images, which we used as features to predict anaemia via statistical modelling.Main results.We found that we were not able to predict anaemia with enough accuracy to be clinically useful, at 89.6% sensitivity and 26.1% specificity. We consider the hypothesis that this may be due to pigmentation on the sclera and palpebral conjunctiva. Visual judgement showed that pigmentation on the sclera, which may affect the measured colour, is more prevalent in pregnant women in India than in preschool aged children in Ghana (a population previously studied in this context). When participants with subjectively judged visible scleral pigmentation are removed, ability to screen for anaemia using the smartphone images slightly improves (93.1% sensitivity, 28.6% specificity).Significance.These findings provide evidence to reinforce that applying smartphone imaging techniques to understudied populations in the real world requires caution-a promising result in one group may not necessarily transfer to another demographic.

Hand Gesture Recognition for Virtual Mouse Control

Our work delved into the complexities of real-time hand motion interpretation and fingertip recognition to simulate the functionality of a traditional mouse. We developed a python-based technique that seamlessly translates hand movements into mouse commands by analyzing the angles between fingers and calculating the ratio of the hand’s silhouette to its convex hull. Our methodology was refined to ensure an intuitive and accurate user experience. However, challenges remained in achieving robustness and accuracy in gesture recognition systems in various scenarios, including variations in lighting, hand orientation, and individual human characteristics. These factors had a significant impact on system performance and reliability. To address these challenges, our approach incorporated the algorithms and machine learning models designed to adapt to different conditions. Despite these advances, further research and development were essential to improve the reliability and comprehensiveness of gesture recognition technologies.

A Coarse-to-Fine Feature Aggregation Neural Network with a Boundary-Aware Module for Accurate Food Recognition

Food recognition from images is crucial for dietary management, enabling applications like automated meal tracking and personalized nutrition planning. However, challenges such as background noise disrupting intra-class consistency, inter-class distinction, and domain shifts due to variations in capture angles, lighting, and image resolution persist. This study proposes a multi-stage convolutional neural network-based framework incorporating a boundary-aware module (BAM) for boundary region perception, deformable ROI pooling (DRP) for spatial feature refinement, a transformer encoder for capturing global contextual relationships, and a NetRVLAD module for robust feature aggregation. The framework achieved state-of-the-art performance on three benchmark datasets, with Top-1 accuracies of 99.80% on the Food-5k dataset, 99.17% on the Food-101 dataset, and 85.87% on the Food-2k dataset, significantly outperforming existing methods. This framework holds promise as a foundational tool for intelligent dietary management, offering robust and accurate solutions for real-world applications.

Seasonal plasticity in daily timing of flight activity in Anopheles stephensi is driven by temperature modulation of dawn entrainment.

The Asian malaria vector Anopheles stephensi is invading Africa, requiring it to adapt to novel climates and ecosystems. In part, this may be facilitated by An. stephensi's poorly understood seasonal behavioural plasticity in flight timing, leading to earlier biting activity in cold Asian winters and later biting times in the warm summer. Changes in behavioural timing could be directly imposed by seasonal variation in ambient light and temperature levels or result from altered entrainment of intrinsically expressed circadian rhythms by these factors. We demonstrate that An. stephensi entrained flight activity timing is phase-locked to dawn and is not affected by constant ambient temperature, which cannot explain earlier biting activity in colder winters with later dawn. Instead, we show that where night temperatures are the colder part of daily temperature cycle; the entrained phase-angle between dawn and flight activity is altered, hereby increasingly colder, winter-like nights progressively advance flight activity onset. We propose that seasonal timing plasticity optimizes behaviour to warmer daytime in winter, and colder nights in summer, providing protection against both heat-desiccation and cold immobility. The adaptive advantage of this plasticity could be relevant to the successful invasion and survival of An. stephensi in African climates, and changing climate worldwide.This article is part of the Theo Murphy meeting issue, 'Circadian rhythms in infection and immunity'.

Integrating EnlightenGAN for enhancing car logo detection under challenging lighting conditions

Abstract Detecting small objects in challenging lighting conditions is a critical task with broad applications in computer vision, surveillance, and medical imaging. Small objects are especially vulnerable to detection errors due to their size and the significant impact of varying lighting conditions, such as low-light environments or high glare. Furthermore, the lack of a benchmark dataset that accurately simulates real-world scenarios makes it difficult to evaluate the performance of detection models in such conditions. In the proposed paper, we address these challenges by developing a comprehensive dataset specifically designed for car logo detection under diverse and challenging lighting environments. The dataset incorporates variations in lighting, viewing angles, and object scales to replicate real-world conditions. We also introduce a detection pipeline integrating EnlightenGAN for low-light image enhancement, which preserves fine details and textures, and YOLOv7 and YOLOv8 for improved detection accuracy. By enhancing image quality and refining object detection models, our approach significantly boosts the detection of small car logos, even in challenging lighting scenarios where traditional models tend to fail. Experimental results show that YOLOv8 outperforms YOLOv7 by approximately 7%, with YOLOv8 achieving a mean Average Precision (mAP) of 73.3% on the augmented dataset compared to 68.4% for the original dataset and 67.2% for the processed images. These results validate the effectiveness of GAN-based enhancement techniques in preserving small object details and improving detection performance. Additionally, introducing a new dataset and benchmark provides a valuable resource for future research in small object detection under complex lighting conditions.

A Model for Detecting Xanthomonas campestris Using Machine Learning Techniques Enhanced by Optimization Algorithms

The bacterium Xanthomonas campestris poses a significant threat to global agriculture due to its ability to infect leaves, fruits, and stems under various climatic conditions. Its rapid spread across large crop areas results in economic losses, compromises agricultural productivity, increases management costs, and threatens food security, especially in small-scale agricultural systems. To address this issue, this study developed a model that combines fuzzy logic and neural networks, optimized with intelligent algorithms, to detect symptoms of this foliar disease in 15 essential crop species under different environmental conditions using images. For this purpose, Sugeno-type fuzzy inference systems and adaptive neuro-fuzzy inference systems (ANFIS) were employed, configured with rules and clustering methods designed to address cases where diagnostic uncertainty arises due to the imprecision of different agricultural scenarios. The model achieved an accuracy of 93.81%, demonstrating robustness against variations in lighting, shadows, and capture angles, and proving effective in identifying patterns associated with the disease at early stages, enabling rapid and reliable diagnoses. This advancement represents a significant contribution to the automated detection of plant diseases, providing an accessible tool that enhances agricultural productivity and promotes sustainable practices in crop care.

ADL-Net: attention-driven densenet-LSTM network for underwater images classification

Abstract Imaging in marine environment is a challenging task due to several reasons, including light variations, color distortions, noise, and limited datasets, which causes inaccurate target classification problems. This paper presents a methodology for image classification in marine biology and environmental research. We proposed the Attention-Driven DenseNet-LSTM Network (ADL-Net), aiming to improve classification accuracy of underwater imagery. Initially, feature extraction is performed using multi-levels of DenseNet201, which excels in hierarchical feature extraction, offering stability and rapid convergence. In the next stage, two modified attention mechanisms are designed: the squeeze and excitation operations are used to refine channel-specific feature responses, while the convolutional block attention module refines attention for both channels and spatial dimensions. These attention mechanisms help the model to highlight important features and minimize distractions. Additionally, a Bi-directional Long Short-Term Memory layer is integrated to capture spatial dependencies and improve classification robustness. Various training strategies are used to find the best parameter tuning. Our method demonstrates excellent performance when tested on fish datasets: LifeCLEF 2015 and Fish4Knowledge, achieving accuracies of 98.02%, and 99.52%, respectively. These findings underscore ADL-Net's potential for enhancing automated underwater image classification, advancing research in marine ecology.

In vivo Metabolic Investigation of Oxygen, Light, and Temperature Effects on Dormancy Alleviation of Sesame (Sesamum indicum L.) Seeds

As an edible seed, sesame seeds require careful storage to maintain their quality. Dormancy helps seeds extend their lifespan by slowing down metabolic processes, reducing energy consumption and natural aging. However, seeds may exit dormancy and begin germination during storage due to variations in temperature, light, and oxygen conditions. This transition is not easily visible, but nutritional components within the seeds can start to deplete. In this study, non-invasive magnetic resonance spectroscopy and imaging were used to monitor sesame seeds stored under different temperature, light, and oxygen conditions for over 120 hours. Results showed that seeds remained dormant at 15 °C under oxygen deprivation and in the absence of light. When exposed to continuous light at 15 °C, under anaerobic or aerobic conditions, changes in metabolic resonances were observed through spectroscopy, indicating moisture and fatty acid transfer between seed structures. Despite these changes, magnetic resonance imaging showed that the embryo did not develop. At 24 °C with continuous light and aerobic conditions, both spectroscopy and imaging analyses revealed significant metabolic changes, and all internal seed structures developed normally, with visible signs of germination. This study highlights that although sesame seeds are non-photoblastic, light can still trigger metabolic activity within the seeds, while suitable temperature is essential for complete seed development. These findings provide valuable insights into the dynamic molecular-level metabolic changes from dormancy to early seed germination using magnetic resonance technology and offer guidance for maintaining seed dormancy during storage.

A Lightweight Model for Shine Muscat Grape Detection in Complex Environments Based on the YOLOv8 Architecture

Automated harvesting of “Sunshine Rose” grapes requires accurate detection and classification of grape clusters under challenging orchard conditions, such as occlusion and variable lighting, while ensuring that the model can be deployed on resource- and computation-constrained edge devices. This study addresses these challenges by proposing a lightweight YOLOv8-based model, incorporating DualConv and the novel C2f-GND module to enhance feature extraction and reduce computational complexity. Evaluated on the newly developed Shine-Muscat-Complex dataset of 4715 images, the proposed model achieved a 2.6% improvement in mean Average Precision (mAP) over YOLOv8n while reducing parameters by 36.8%, FLOPs by 34.1%, and inference time by 15%. Compared with the latest YOLOv11n, our model achieved a 3.3% improvement in mAP, with reductions of 26.4% in parameters, 14.3% in FLOPs, and 14.6% in inference time, demonstrating comprehensive enhancements. These results highlight the potential of our model for accurate and efficient deployment on resource-constrained edge devices, providing an algorithmic foundation for the automated harvesting of “Sunshine Rose” grapes.

Robot Closed-Loop Grasping Based on Deep Visual Servoing Feature Network

Robot visual servoing for grasping has long been challenging to execute in complex visual environments because of issues with efficient feature extraction. This paper proposes a novel visual servoing grasping approach based on the Deep Visual Servoing Feature Network (DVSFN) to tackle this issue. The approach enables feasible to extract scale-invariant point features and target bounding boxes in real time by building an effective single-stage multi-dimensional feature extractor. The DVSFN is then integrated into a Levenberg–Marquardt–based image visual servoing (LM-IBVS) controller. The above creates a mapping link between the robot’s joint space and image features. The robot is then guided in positioning and grabbing by converting the difference between the expected and present features into the corresponding robot joint velocities. Experimental results demonstrate that the proposed method achieves a mean average precision (mAP) of 0.80 and 0.87 for detecting target bounding boxes and point features, respectively, in scenarios with significant lighting variations and occlusions. Under low-light and partial occlusion conditions, the method achieves an average grasping success rate approximately 80%.

Image-Based Detection and Classification of Malaria Parasites and Leukocytes with Quality Assessment of Romanowsky-Stained Blood Smears.

Malaria remains a global health concern, with 249 million cases and 608,000 deaths being reported by the WHO in 2022. Traditional diagnostic methods often struggle with inconsistent stain quality, lighting variations, and limited resources in endemic regions, making manual detection time-intensive and error-prone. This study introduces an automated system for analyzing Romanowsky-stained thick blood smears, focusing on image quality evaluation, leukocyte detection, and malaria parasite classification. Using a dataset of 1000 clinically diagnosed images, we applied feature extraction techniques, including histogram bins and texture analysis with the gray level co-occurrence matrix (GLCM), alongside support vector machines (SVMs), for image quality assessment. Leukocyte detection employed optimal thresholding segmentation utility (OTSU) thresholding, binary masking, and erosion, followed by the connected components algorithm. Parasite detection used high-intensity region selection and adaptive bounding boxes, followed by a custom convolutional neural network (CNN) for candidate identification. A second CNN classified parasites into trophozoites, schizonts, and gametocytes. The system achieved an F1-score of 95% for image quality evaluation, 88.92% for leukocyte detection, and 82.10% for parasite detection. The F1-score-a metric balancing precision (correctly identified positives) and recall (correctly detected instances out of actual positives)-is especially valuable for assessing models on imbalanced datasets. In parasite stage classification, CNN achieved F1-scores of 85% for trophozoites, 88% for schizonts, and 83% for gametocytes. This study introduces a robust and scalable automated system that addresses critical challenges in malaria diagnosis by integrating advanced image quality assessment and deep learning techniques for parasite detection and classification. This system's adaptability to low-resource settings underscores its potential to improve malaria diagnostics globally.

Linguistic Attitudes and Activities of Petras Klimas. Diplomat’s Written Language in Private Correspondence

The epistolary legacy of diplomat Petras Klimas is valuable not only in terms of disclosing the geopolitical, social and cultural reality of the interwar Lithuania and Europe, but also as an important corpus of manuscripts enabling us to trace the development of the written language. Having evaluated the field of P. Klimas’ activities that is currently rather overlooked by the modern scholarly discourse, i. e. his endeavors to accumulate the resources of the living language, to enhance the prestige of the Lithuanian language, and to solve issues related to its development, the author of the article identified the typical features of his written language and compiled a collection of paremias. The study is based on a hitherto unanalyzed correspondence of P. Klimas and his wife Bronislava Klimienė.An analysis of his personal writings has brought to light orthographical variations and causes, as well as the national attitudes reflected in his modified spelling. P. Klimas, it turns out, often inserted paremia, various French words and even words of his own making following Lithuanian standard word-formation, into his speech. This has allowed him to shape a unique, distinctive prose style that merges traditional (ethnic) and modern (Western) elements.

An insight into recent PM1 aerosol light scattering properties and particle number concentration variabilities at the suburban site ATOLL in Northern France.

Aerosol particles in the PM1 fraction considerably influence the climate-related effects of aerosols and impact human health despite representing very variable fractions of the total aerosol mass concentration. Aerosol optical measurement techniques (aerosol light scattering) may not be sufficiently effective for detecting all particles in the PM1 fraction, particularly regarding number concentration. The present study investigates temporal variations of aerosol light scattering properties and particle number concentration (PNC) at different size modes in the PM1 fraction at the atmospheric site ATOLL (The Atmospheric Observations in Lille), Northern France from January 2018 to February 2023. The total scattering coefficient σsp decreased annually by 6% and 8% at 525 and 635nm, respectively. Maximum annual changes occur in winter and summer seasons with a decrease above 10% per year. Although the backscattering coefficient (σbsp) at 525nm significantly decreased in winter, this did not result in a significant overall decline over time. Despite a decrease in aerosol light scattering, PNC exhibited a notable annual increase in concentration of N20-30 nm and N30-60 nm, which led to an increase in the total N20-800 nm size range. N20-30nm increased by 10% annually, with the highest increase by 37% in spring. Both traffic and photooxidative processes influenced PNCs, underscoring the need for a more comprehensive investigation of the detailed particle number size distribution to assess air quality and the health effects of increased ultrafine PNC at urban/suburban sites in Europe.