Brightness Difference Research Articles

Construction and Validation of an Image Discrimination Algorithm to Discriminate Necrosis from Wounds in Pressure Ulcers.

Artificial intelligence (AI) in medical care can raise diagnosis accuracy and improve its uniformity. This study developed a diagnostic imaging system for chronic wounds that can be used in medically underpopulated areas. The image identification algorithm searches for patterns and makes decisions based on information obtained from pixels rather than images. Images of 50 patients with pressure sores treated at Kobe University Hospital were examined. The algorithm determined the presence of necrosis with a significant difference (p = 3.39 × 10-5). A threshold value was created with a luminance difference of 50 for the group with necrosis of 5% or more black pixels. In the no-necrosis group with less than 5% black pixels, the threshold value was created with a brightness difference of 100. The "shallow wounds" were distributed below 100, whereas the "deep wounds" were distributed above 100. When the algorithm was applied to 24 images of 23 new cases, there was 100% agreement between the specialist and the algorithm regarding the presence of necrotic tissue and wound depth evaluation. The algorithm identifies the necrotic tissue and wound depth without requiring a large amount of data, making it suitable for application to future AI diagnosis systems for chronic wounds.

A Wildfire Detection Algorithm Based on the Dynamic Brightness Temperature Threshold

Satellite remote sensing plays an important role in wildfire detection. Methods using the brightness and temperature difference of remote sensing images to determine if a wildfire has occurred are one of the main research directions of forest fire monitoring. However, common wildfire detection algorithms are mainly based on a fixed brightness temperature threshold to distinguish wildfire pixels and non-wildfire pixels, which reduces the applicability of the algorithm in different space–time regions. This paper presents an adaptive wildfire detection algorithm, DBTDW, based on a dynamic brightness temperature threshold. First, a regression dataset, MODIS_DT_Fire, was constructed based on moderate resolution imaging spectroradiometry (MODIS) to determine the wildfire brightness temperature threshold. Then, based on the meteorological information, normalized difference vegetation index (NDVI) information, and elevation information provided by the dataset, the DBTDW algorithm was used to calculate and obtain the minimum brightness temperature threshold of the burning area by using the Planck algorithm and Otsu algorithm. Finally, six regression models were trained to establish the correlation between factors and the dynamic brightness temperature threshold of wildfire. The root-mean-square error (RMSE) and mean absolute error (MAE) were used to evaluate the regression performance. The results show that under the XGBoost model, the DBTDW algorithm has the best prediction effect on the dynamic brightness temperature threshold of wildfire (leave-one-out method: RMSE/MAE = 0.0730). Compared with the method based on a fixed brightness temperature threshold, the method proposed in this paper to adaptively determine the brightness temperature threshold of wildfire has higher universality, which will help improve the effectiveness of satellite remote fire detection.

A review of the effect of the light environment of the VDT workspace on the "learning to learn" effect of video game training.

In recent years, the role of video games in enhancing brain plasticity and learning ability has been verified, and this learning transfer is known as the "learning to learn" effect of video game training. At the same time, against the background of healthy lighting, the influence of non-visual effects of light environment on the human rhythmic system has been gradually confirmed. As a special operation form of Visual Display Terminal (VDT) operation, video game training has a high dependence on VDT equipment and the VDT screen, and the background usually has a huge difference in brightness. Compared with the light environment of ordinary operation space, the light environment of VDT operation space is more complex. This complex light environment's non-visual effects cause human emotions, alertness, fatigue, cognitive ability, and other changes, which may affect the efficiency of the "learning to learn" effect of video game training. This article focuses on the impact of the light environment in the VDT workspace on the "learning to learn" effect of video game training. It first traces the factors that trigger the "learning to learn" effect of video game training, that is, the improvement of people's attention, perception, and cognitive ability. Then, the influencing mechanism and the evaluation method of the VDT workspace space light environment on the human rhythm system are discussed based on the basic theory of photobiological effect. In addition, the VDT display lighting light time pattern, photophysical properties, regulation, and protection mechanism on the human rhythm system are studied to demonstrate the VDT workspace light environment's special characteristics. Finally, combined with the progress of artificial lighting technology and the research results of health lighting, given the "learning to learn" effect of video game training, some thoughts on the design of the light environment of the workplace and future research directions are presented.

Design Method of Combined Gradient Dimming Structures for Highway Tunnels

The notable brightness difference between the inside and outside of a tunnel is a major issue restricting the safe driving and energy-saving conditions of highway tunnels. The installation of a shading structure at the entrance of a highway tunnel could resolve this problem. This method is equivalent to moving the entrance zone outside so that light is smoothly transmitted into the tunnel, which is called pretunnel lighting. In this research, the shading structure is selected as the research object. First, the shading effects of pergolas and sunshades of different cross-sectional forms are analyzed. Second, choosing the Jiulongpo Tunnel in Chongqing as an example, through DIALux software modeling and analysis, the tunnel sunshade is selected as the primary shading structure, which is better than the pergola in terms of the average luminance value and uniformity of luminance. Third, based on the idea of gradient dimming outside the tunnel, three kinds of combined gradient dimming sunshades are designed. Considering the influence of the season, weather and orientation, the optimal design scheme is determined in detail. Finally, the energy-saving benefits are calculated of the installation of a tunnel sunshade to replace the enhanced lighting in Threshold zone 1 (TH1) combined with gradient dimming lighting in Threshold zone 2 (TH2). The results show that the combined gradient dimming sunshade in Scheme 3 (70% + 40% + 20% + 10%) is optimal. The combined gradient dimming sunshade could decrease the variation in luminance inside and outside the tunnel and reduce the artificial lighting intensity in the entrance zone, which could facilitate safe driving and energy savings.

Leukocyte Esterase Strip Quantitative Detection Based on RGB Photometry is a Probable Method to Diagnose Periprosthetic Joint Infection: An Exploratory Study.

Leucocyte esterase (LE) strip test is the most rapid, convenient, and cheap method to diagnose chronic periprosthesis joint infection (PJI). However, the determination of LE strip mainly relies on colorimetric method with strong subjectivity, which leads to low diagnostic accuracy. Therefore, we try to convert LE strip images into digital data through the RGB photometric system to achieve objective diagnosis. This method will greatly improve the accuracy of LE strip detection and diagnosis of PJI. From January 2021 to September 2021, 46 patients with suspected PJI after total hip and knee arthroplasty underwent diagnostic joint puncture. After effective joint fluid samples were harvested, they were divided into original fluid and centrifuged fluid for LE strip detection. Real-time images of LE strip were taken at 90 s, 3min, 5min, 10 min, and 15 min after sampling, and their brightness (Y) was obtained after they were input into an RGB photometric system. Grouping was based on centrifugation, infection, and time points, and then the differences in brightness among groups were compared. The correlation between LE strip image brightness and WBC count was evaluated. Student t-test was used for the parametric data and chi-square test for qualitative data. Simple linear regression was utilized to analyze the correlation between brightness and WBC count in each group. Included were 19 cases of PJI and 27 Non-PJI subjects diagnosed against ICM2018 diagnostic criteria. The brightness was lower in the PJI group than in Non-PJI group (p < 0.05). The brightness of the uncentrifuged group was lower than that of the centrifuged group (p< 0.05). Irrespective of centrifugation or infection, the brightness of LE strip decreased with the exposure time after sampling. The brightness of LE strip was correlated with WBC count at different time points, with the correlation being strongest 5min after sampling (R2 (5min)=0.86, p< 0.0001). The correlation between LE strip brightness and WBC count was also found in the centrifugation group, with the correlation being most robust 15 min after sampling (R2 (15 min)=0.73, p< 0.0001). A remarkable correlation was found between LE strip brightness and the WBC count. It is feasible to directly quantify LE strip image on a RGB photometer to achieve quantitative detection of LE strip to diagnose PJI.

Coating Defects of Lithium-Ion Battery Electrodes and Their Inline Detection and Tracking

In order to reduce the cost of lithium-ion batteries, production scrap has to be minimized. The reliable detection of electrode defects allows for a quality control and fast operator reaction in ideal closed control loops and a well-founded decision regarding whether a piece of electrode is scrap. A widely used inline system for defect detection is an optical detection system based on line scan cameras and specialized lighting. The cameras scan the electrode, and brightness differences on the surface are detected and processed inline. The characteristics of the defect image are used for automated classification of the defects based on image features. Furthermore, the detailed detection of defects allows for the identification of causes. This paper describes the working principle of such an inline detection system, the catalog of typical defects, and the image features used to classify them automatically. Furthermore, we propose and discuss causes and effects of the different defect types on the basis of the literature and expert experience. In combination with tracking and tracing, this enables the manufacturer to reduce scrap by detecting defects early in the production chain.

Ultrasound characterization of mammary gland development in heifer calves fed at two different levels until weaning.

Ultrasound technologies allow for a non-invasive assessment of mammary gland (MG) development, the differentiation between the tissue types of the MG, and the evaluation of changes in its composition. This study aimed to work out a detailed description of the different stages of MG development that are visually discernible by ultrasonography for providing a template to classify the different structures. With this basis, the qualitative categorization of the developmental stage, as well as further quantitative assessments via pixel densities in the structures of interest, should be facilitated. Ultrasonic images were acquired from all four quarters of 37 German Holstein heifer calves fed either at a high feeding level of milk replacer (MR; 14% solids) at 10L/day (1.4 kg MR/day; HI, n= 18) or at a restrictive low level of 5.7L/day (0.8 kg MR/day; RES, n= 19) until linear weaning from week 13 to 14 of life. Ultrasound MG scans were performed first in week 3 of life, fortnightly from week 8-16, and in week 20 of life, in standing position, of each quarter, using a B-mode ultrasound device equipped with a linear probe (18 MHz). The developmental stages of the mammary gland parenchyma (PAR), visible in ultrasound images, obtained over 20 weeks of life, were categorized, described, and drawn by hand. On this basis, a template for classifying the visible categories of mammary PAR development and its surrounding tissue (SURR), and for measuring their pixel brightness was created thus providing an ultrasonographic atlas of the developing bovine MG, describing 11 categories. The ultrasound images were further classified by PAR structure, and pixel brightness was measured in PAR and SURR by using ImageJ Fiji. The difference in pixel brightness between PAR and SURR, the delta (Δ) pixel value was calculated. With increasing age, higher atlas categories of PAR developmental stages were shown. Pixel values, i.e. the brightness of PAR, its SURR, and Δ pixel value changed with age but were neither affected by the feeding group nor by a group × time interaction. With progressing PAR development, its pixel brightness increased from week 10 to 20 of life, i.e., the PAR became more hyperechoic since it spread and grew into its SURR. The atlas can serve as a template for the categorization and qualitative assessment of MG structures and for the quantitative assessment of PAR's development by measuring pixel brightness. With our study, we could show the structural development in PAR as well as in SURR in MG simultaneously in early life and confirm the spreading of PAR into its SURR by ultrasound scanning.

Female and male plumage brightness is positively correlated among populations of the dichromatic Variable Seedeater

Abstract Because studies of plumage coloration often focus on highly elaborate and conspicuous males, little is known about the factors driving theevolution of drab plumage in females of dichromatic species. We explored variation in the color properties of drab female plumage across subspecies of the Variable Seedeater (Sporophila corvina) and found a correlation between plumage brightness of male and female plumage patches. This correlation is consistent with the hypothesis that differences in plumage brightness among females result, at least partially, from a genetic correlation or shared developmental pathway with the more conspicuous male plumage traits that are shaped by sexual selection. Furthermore, we modeled the perception of female plumage using the avian visual system and found that most of the variation in color among females is undetectable by birds; therefore, it is unlikely for such variation to have evolved via direct sexual selection as a signal for recognition or assortative mating. Together, these results suggest that variation in S. corvina female color result from non-adaptive processes. However, we found a reduced variation on color of dorsal patches compared with that of ventral patches among females, which could be explained by natural selection on crypsis, reducing the variation on dorsal patches. Finally, we found little differences in plumage color between adult females and juveniles, which suggest selection for juveniles to resemble adult females possibly to reduce aggression from adult males. Additional within-population studies and behavioral experiments are needed to discern the evolutionary factors driving variation on S. corvina female color and its function.

Возможности технологии создания цифровых копий археологических артефактов на примере пешни с памятника Фирсово-XI (Барнаульское Приобье)

The article discusses the possibilities of using 3D-fixation technologies to create an exact digital copy of stone artifacts with irregular geometry using photogrammetry. This technology can be used for two main purposes: Firstly, as a means of creating and long-term storage of digital copies of objects for a more complete visualization and representation of the object, which may be necessary for various purposes, and easy access to databases; The second goal can be considered to be analytical studies - measurements of dimensions, volumes, surface areas, densities, roughness, etc.; determination of geometric characteristics - center of mass, axes of symmetry, deviations, construction of sections. In the process of research, a digital copy of a stone ice pick from the Firsovo-XI site (Barnaul Stretch of the Ob) was created. The product is made of a large elongated block of very viscous dark green stone. As a result of the study of traces of microwear, it turned out that this tool is a pawn, i.e. used to cut a hole in the ice. Traces of micro wear are concentrated on the ground, cone-shaped edge of the product. This edge is the working part of the tool. Polishing of the working part, traces of microfinishing, dislocation of wear is typical for such tools as a ice pick. The circumstances of the discovery do not allow us to accurately determine the age of the artifact, but most likely this item is synchronous with the Neolithic burials of Firsovo-XI. The paper states that the construction of orthogonal projections of an object is not a trivial task in working with stone artifacts. The use of photography leads to the inevitable distortion of perspective - the deformation or transformation of the object and its surrounding area. From such projections it is impossible to take measurements, make sections and conduct a study. The construction of clear projections with any angular step, without any perspective distortions, as well as the construction of sections, setting dimensions, is the basic function of most 3D graphics packages. An equally important function is rendering under a given illumination - that is, the process of constructing the final two-dimensional image of an object at the angle and intensity of the incident light that the researcher needs, etc. The position of the light source can help solve the problem of contrast sensitivity, that is, the ability of the eye to distinguish the minimum difference in brightness between the object in question or two adjacent surfaces. It is concluded that the absence of physical limitations in the use of the obtained 3D models makes photogrammetry an extremely useful tool both in research and for data exchange, public demonstrations and remote collaboration. It is noted that photogrammetry can be used as a tool for creating exact solid copies of objects using a 3D printer, as museum exhibits.

Accuracy and precision of sea-finding orientation as a function of dune proximity in hatchlings of two species of sea turtles

Context Sea turtle hatchlings generally emerge at night from nests on sand beaches and immediately orient using visual cues, which are believed to entail the difference in brightness between the light seen in the seaward direction and that seen in the duneward direction. Aim The aim of this study was to understand how dune proximity affected hatchling orientations in two sea turtle species that share a nesting beach 15 km long and 25.3 ± 9.4 m (N = 215) from dune to waterline, with low to moderate artificial light nearby. Methods For hatchling loggerhead and green turtles, we measured accuracy and precision of orientation, tested differences in distance from nest to dune, and investigated the effect of dune proximity on hatchling orientation. Key results We found a significant decrease in hatchling orientation accuracy and precision in both species as the distance increased from nests to dune. Loggerhead and green turtles showed similar orientation ability when in the same proximity to the dune. Conclusions We conclude that dune features provide important cues for hatchling orientation on sea turtle nesting beaches. Implications Restoring and maintaining natural beach profiles, especially dune systems, is likely to increase the accuracy and precision of sea finding in hatchling sea turtles.

99m-Tc MDP Bone Scan Image Enhancement using Pipeline Application of Dynamic Stochastic Resonance Algorithm and Block-Matching 3D Filter.

In this pilot study, we have proposed and evaluated pipelined application of the dynamic stochastic resonance (DSR) algorithm and block-matching 3D (BM3D) filter for the enhancement of nuclear medicine images. The enhanced images out of the pipeline were compared with the corresponding enhanced images obtained using individual applications of DSR and BM3D algorithm. Twenty 99m-Tc MDP bone scan images acquired on SymbiaT6 SPECT/CT gamma camera system fitted with low-energy high-resolution collimators were exported in DICOM format to a personal computer and converted into PNG format. These PNG images were processed using the proposed algorithm in MATLAB. Two nuclear medicine physicians visually compared each input and its corresponding three enhanced images to select the best-enhanced image. The image quality metrics (Brightness, Global Contrast Factor (GCF), Contrast per pixel (CPP), and Blur) were used to assess the image quality objectively. The Wilcoxon signed test was applied to find a statistically significant difference in Brightness, GCF, CPP, and Blur of enhanced and its input images at a level of significance. Images enhanced using the pipelined application of SR and BM3D were selected as the best images by both nuclear medicine physicians. Based on Brightness, Global Contrast Factor (GCF), CPP, and Blur, the image quality of our proposed pipeline was significantly better than enhanced images obtained using individual applications of DSR and BM3D algorithm. The proposed method was found to be very successful in enhancing details in the low count region of input images. The enhanced images were bright, smooth, and had better target-to-background ratio compared to input images. The pipelined application of DSR and BM3D algorithm produced enhancement in nuclear medicine images having following characteristics: bright, smooth, better target-to-background ratio, and improved visibility of details in the low count regions of the input image, as compared to individual enhancements by application of DSR or BM3D algorithm.

Evaluating the brightness difference of driver's visual adaptation between road and HMI using consensus model and PSO algorithm

Evaluating the brightness difference of driver's visual adaptation between road and HMI using consensus model and PSO algorithm

EFINet: Restoration for Low-Light Images via Enhancement-Fusion Iterative Network

The lighting environment in the real world is so complex that most existing low-light image restoration methods suffer from color cast and local over-exposure. In order to solve these problems, this paper proposes the enhancement-fusion iterative network (EFINet) for low-light image enhancement. Within each iteration of EFINet, a stretching coefficient estimation network based enhancement module is designed to adjust the input image pixel-wisely to obtain the initial enhancement result with the estimated coefficient maps. Then, an encoder-decoder based fusion network is devised to extract the deep features and combine the well-exposed local areas in both the input image and the initially enhanced image, to obtain a visually pleasing, high-quality image enhancement result. The coefficient estimation network and the fusion network are weight shared among all iterations. What’s more, most of the low-light image datasets are generated through illumination reduction in a global way. To better simulate the diverse illumination distribution in the real world, we put forward a new low-light image synthesis method to produce the low-light images with non-uniform illumination for the network training purpose. After conducting extensive experiments on both synthetic and real-world low-light images, the results verify the superiority of our algorithm over the state-of-the-art (SOTA) methods, especially in balancing the brightness difference and preventing over-enhancement.

High resolution UV spectral imaging and bio-detection with magnetic dipole quasi-BIC resonant dielectric metasurfaces

In this paper, we designed a ring-shaped metasurface based on diamond material that response in ultraviolet band, and with which the BIC mode is obtained by breaking the symmetry of its structural units. We show that only when the radiation rate of the magnetic dipole resonance of the BIC mode is equal to the dissipation loss brought by the surface covering material, the interaction between light and matter is maximally enhanced. The absorptivity of the film material is enhanced by an order of magnitude. The simulation results show that there is a linear relationship between the resonant positions of the structure and the scaling factor S varying structure sizes. When the metasurface is covered with a single DNA film, changes differently due to the absorption of the DNA. The reflection information of the system is further converted into ultraviolet absorption of DNA. Then the multiple absorption peaks form the absorption spectrum of DNA molecules. By Arranging the different scaling factor metasurface pixels on a same substrate we can obtain a specific absorption image. The absorptivity of DNA leads to the difference in brightness and darkness of the metasurface pixels, which can be processed into gray-scale images that give out the specific fingerprint information of the DNA. So, we realized calibration and analysis of DNA without spectroscopic measurements in the ultraviolet band now. The metasurface device can effectively detect the contamination of DNA by other biomolecules such as RNA. This work has great significance in promoting the application of metasurfaces in the field of biological detection and demonstrates that a specially designed metasurface can be applied in nucleic acid detection.

Applying Fuzzy Contrast Enhancement on Earthquake Impact Images

In this paper, fuzzy contrast enhancement technique is applied on earthquake impact images in Ranau, Sabah. The aim is to highlight the visible differences between adjacent structures in the images. The brightness differences between objects and its background is enhanced to improve the visibility. In fuzzy approach, the gray plane is mapped into fuzzy plane by using membership function. The membership values represent the degree of brightness or darkness of the pixels.

Enhancement-Registration-Homogenization (ERH): A Comprehensive Underwater Visual Reconstruction Paradigm

This paper presents a comprehensive underwater visual reconstruction paradigm that comprises three procedures, i.e., the E-procedure, the R-procedure, and the H-procedure. The E-procedure enhances original underwater images based on color compensation balance and weighted image fusion, yielding restored color, sharpened edges, and global contrast. The R-procedure registers multiple enhanced underwater images by exploiting global similarity and local deformation. The H-procedure homogenizes the registered underwater images by multi-scale composition strategy, which eliminates the inhomogeneous transition and brightness difference across overlapping regions, resulting in a reconstructed wide-field underwater image with comfortable and natural visibility. The three procedures operate in a cascade where the former procedure processes underwater images in a way that facilitates the latter one. We refer to the overall three procedures as the Enhancement-Registration-Homogenization (ERH) paradigm. Comprehensive qualitative and quantitative empirical evaluations reveal that our ERH paradigm outperforms state-of-the-art visual reconstruction methods, including the AutoStitch, APAP, SPHP, APNAP, and REW.

Simulation view of galaxy clusters with low X-ray surface brightness

Context. X-ray selected samples are known to miss galaxy clusters that are gas poor and have a low surface brightness. This is different for the optically selected samples such as the X-ray Unbiased Selected Sample (XUCS). Aims. We characterise the origin of galaxy clusters that are gas poor and have a low surface-brightness by studying covariances between various cluster properties at fixed mass using hydrodynamic cosmological simulations. Methods. We extracted ≈1800 galaxy clusters from a high-resolution Magneticum hydrodynamic cosmological simulation and computed covariances at fixed mass of the following properties: core-excised X-ray luminosity, gas fraction, hot gas temperature, formation redshift, matter density profile concentration, galaxy richness, fossilness parameter, and stellar mass of the bright central galaxy. We also compared the correlation between concentration and gas fractions in non-radiative simulations, and we followed the trajectories of particles inside galaxy clusters to assess the role of AGN depletion on the gas fraction. Results. In simulations and in observational data, differences in surface brightness are related to differences in gas fraction. Simulations show that the gas fraction strongly correlates with assembly time, in the sense that older clusters are gas poor. Clusters that formed earlier have lower gas fractions because the feedback of the active galactic nucleus ejected a significant amount of gas from the halo. When the X-ray luminosity is corrected for the gas fraction, it shows little or no covariance with other quantities. Conclusions. Older galaxy clusters tend to be gas poor and possess a low X-ray surface brightness because the feedback mechanism removes a significant fraction of gas from these objects. Moreover, we found that most of the LX covariance with the other quantities is explained by differences in the gas fraction.

Deep learning model for person identification and verification on low illumination images

Performances of the deep learning models for person identification and verification are degraded on low illumination images due to the generated facial embeddings being unable to be matched with the trained good illumination facial embeddings. Person verification on low illumination images is a challenging task. The existing techniques have adopted an approach of enhancing the low illumination images and performing the person verification in the enhanced images. But these techniques have not achieved satisfactory results, because the gamma value is kept constant in the power law intensity transformation function to enhance the images. To obtain better performance, we propose a deep learning-based framework that consists of a contrast enhancement module, called as contrast enhancement network (CENet); person identification; and person verification modules. The CENet is built based on the residual network, which predicts the gamma value based on the illumination of the input image. The predicted value is used to perform gamma correction on the image to improve the brightness difference between the faces and their background, whereas the existing techniques are keeping the gamma value as constant for image enhancement. After performing the image enhancement, the enhanced image is given as input to the person identification module. Then the detected faces are verified by the person verification module. Experimental results show that the proposed framework has achieved an improvement of 3.4% to 13% in person identification and verification accuracy on the extended yale face dataset to the existing methods.

Building Change Detection Based on an Edge-Guided Convolutional Neural Network Combined with a Transformer

Change detection extracts change areas in bitemporal remote sensing images, and plays an important role in urban construction and coordination. However, due to image offsets and brightness differences in bitemporal remote sensing images, traditional change detection algorithms often have reduced applicability and accuracy. The development of deep learning-based algorithms has improved their applicability and accuracy; however, existing models use either convolutions or transformers in the feature encoding stage. During feature extraction, local fine features and global features in images cannot always be obtained simultaneously. To address these issues, we propose a novel end-to-end change detection network (EGCTNet) with a fusion encoder (FE) that combines convolutional neural network (CNN) and transformer features. An intermediate decoder (IMD) eliminates global noise introduced during the encoding stage. We noted that ground objects have clearer semantic information and improved edge features. Therefore, we propose an edge detection branch (EDB) that uses object edges to guide mask features. We conducted extensive experiments on the LEVIR-CD and WHU-CD datasets, and EGCTNet exhibits good performance in detecting small and large building objects. On the LEVIR-CD dataset, we obtain F1 and IoU scores of 0.9008 and 0.8295. On the WHU-CD dataset, we obtain F1 and IoU scores of 0.9070 and 0.8298. Experimental results show that our model outperforms several previous change detection methods.

Mechanisms of spectral orientation in a diurnal dung beetle.

Ball rolling dung beetles use a wide range of cues to steer themselves along a fixed bearing, including the spectral gradient of scattered skylight that spans the sky. Here, we define the spectral sensitivity of the diurnal dung beetle Kheper lamarcki and use the information to explore the orientation performance under a range of spectral light combinations. We find that, when presented with spectrally diverse stimuli, the beetles primarily orient to the apparent brightness differences as perceived by their green photoreceptors. Under certain wavelength combinations, they also rely on spectral information to guide their movements, but the brightness and spectral directional information is never fully disentangled. Overall, our results suggest the use of a dichromatic, primitive colour vision system for the extraction of directional information from the celestial spectral gradient to support straight-line orientation.This article is part of the theme issue ‘Understanding colour vision: molecular, physiological, neuronal and behavioural studies in arthropods’.