Search Results (213)

Oil palm fresh fruit bunch (FFB) ripeness classification is essential for improving the oil extraction rate, oil quality, and mill processing efficiency. However, RGB-based classification is often limited by insufficient colour information from dark unripe fruitlets and shadowed regions of the bunch surface. This study evaluated the effect of image input representation on convolutional neural network (CNN)-based FFB ripeness classification. Four models with the same CNN architecture were compared using RGB, RGB + infrared (IR), CIEL*a*b*, and CIEL*a*b* + IR inputs. RGB and IR images were acquired using a dual-camera setup positioned 3 m from the FFB sample. The CIEL*a*b* + IR model achieved the best overall performance, with weighted-average precision, recall, and F1-score values of 0.84, 0.81, and 0.81, respectively, compared with 0.79, 0.76, and 0.76 for RGB-only. The addition of IR improved model performance by providing complementary near-infrared reflectance information, while CIEL*a*b* colour-space transformation provided a more discriminative colour representation. Class activation heat maps showed that the models focused mainly on fruitlet regions, with the CIEL*a*b* + IR model producing more distinct activation over ripeness-relevant areas. These findings demonstrate that the proposed four-channel CIEL*a*b* + IR image representation improves CNN-based FFB ripeness classification by combining lightness-separated colour information with near-infrared reflectance features, although underripe FFB remains challenging, where it produced the highest rate of false positives because of its transitional and heterogeneous characteristics. Full article

Search-and-rescue (SAR) missions following earthquakes and other disasters require aerial video perception systems that do more than detect objects in isolated frames. Operators must maintain the identities of access points, vehicles, responders, hazards, and other mission-relevant targets despite UAV ego-motion, dust, debris, occlusion, scale variation, and abrupt scene transitions. This paper presents E’CHIT (Edge-Oriented Colour Histogram Instance-Guided Tracking), a deployment-oriented, operator-centric UAV tracking framework for real-world disaster-response applications. Its primary scientific contribution is an identity-stabilised, detector-assisted tracking methodology. YOLOv8-seg proposals trained on D’RespNeT initialise and refresh tracks; a Custom-RE3 recurrent module propagates target states through short detector dropouts; and a lightweight EOMC verifier, based on edge orientation, mean colour, and shape consistency, determines whether tracks should be accepted, refreshed, or reacquired. A scene-cut watchdog that combines luminance mean absolute difference (MAD) with HSV histogram divergence prevents stale identities from carrying over after hard edits or sudden feed changes. Custom-RE3 is the continuation module implemented and evaluated in this study. The surrounding E’CHIT wrapper follows an initialise–reseed–verify–reset cycle and is tracker-adaptable at the software-interface level: another compatible SOT or MOT continuation module can be integrated through adapter modifications, state and bounding-box conversion, and method-specific retuning, followed by independent validation. All reported quantitative results therefore apply to the Custom-RE3 implementation. D’RespNeT, the optional reinforcement learning (RL) warm start, the HUD, and the deployment stack support this central tracking contribution. D’RespNeT provides 28 polygon-annotated SAR classes. An author-developed PPO/SAC script is used only during offline detector training. In the reported runs, it produces different early optimisation trajectories for selected difficult or under-represented classes, while the default supervised schedule remains the strongest final global mAP reference. No RL policy runs during deployment; the detector architecture, parameter count, and inference graph remain unchanged. Evaluation on D’RespNeT and authentic disaster-response UAV footage shows that E’CHIT increases Success@IoU ≥ 0.5 from 0.62 to 0.79, reduces identity switches by approximately 71%, and maintains real-time 1080p performance, achieving 164–330 FPS for single-target tracking and 24–100+ FPS for end-to-end multi-target operation on an RTX-class GPU using FP16. The VOT2014, NT-VOT211, and VOTS2024 figures reproduce historical result spaces reported in the literature and include a clearly labelled, non-official E’CHIT operating-point marker solely for context. This marker was not produced using the corresponding official datasets, toolkits, reset rules, or submission routes; it is excluded from the primary quantitative claims and must not be interpreted as a leaderboard rank or a protocol-identical comparison. Overall, the system demonstrates how identity-stable UAV tracks can provide actionable operator cues for target monitoring, entry-point assessment, and UAV–UGV/ground-team coordination in cluttered disaster scenes. Full article

South African cities are marked by deepening social and spatial inequalities that produce exclusion, vulnerability, and contested forms of belonging. In this article, these inequalities are understood as the result of historically entrenched processes of colonialism, apartheid spatial planning, and contemporary economic exclusion that continue to shape urban life. These realities not only shape the socio-historical context of Christian mission but also expose the inadequacy of specific ecclesial forms—such as racially and linguistically differentiated synodical structures, centralised theological training institutions, and the historical distinction between “kerk” (church) and “sending” (mission), including mission paradigms characterised by a movement from institutional centers to marginalised communities under paternalistic control. This article argues that faithful participation in the missio Dei, understood here as the Triune God’s redemptive and transformative activity in the world, into which the church is called to participate rather than initiate, requires a reimagined missional ecclesiology shaped in, with, and from the margins. Framed by a broader transforming missiological paradigm and drawing on qualitative literature, this article critically engages key streams within African urban theology, missional ecclesiology, and discourses of power and marginalisation, patriarchy, and ecclesial control to interrogate how churches often reproduce dependency, paternalism, and unequal agency in urban spaces. Using the Reformed Churches in South Africa (RCSAs) as an illustrative case, this article demonstrates how inherited missionary structures have constrained the theological and missional agency of so-called mission churches—that is, churches established among Black and Coloured communities under conditions of financial, administrative, and theological dependence on historically white “mother churches”. Full article

Modern non-stationary signal denoisers increasingly replace a global wavelet threshold by a detect-then-act (gated) rule that first localises an artefact in the time–scale plane and then suppresses it selectively. Such gates couple sub-bands, and it has been unclear how to quantify, in a basis-intrinsic and interpretable way, how much of the denoising performance is produced by that coupling. We introduce the interaction budget $I=1-{\sum }_j{S}_j$ and prove that it equals the normalised $L^2$-distance of the performance functional to the space of band-additive functions; hence, $I=0$ for any band-diagonal operator and $I>0$ exactly when the gate couples bands. We then (i) give an exact pairwise identity for a binary gate, a two-point lower bound, and a sharp if-and-only-if condition on the gate; (ii) identify a coupling-strength functional with the leading-order law $I\left(\kappa \right)=(\mathcal{C}/V_0){\kappa }^2+o\left({\kappa }^2\right)$; and (iii) bound the second-order HDMR/EMPR truncation error, which vanishes for single-trigger gates. Finally, for coloured noise—where the sub-band factors are correlated, and I alone conflates the two effects—an EMPR product-support decomposition separates operator-induced from correlation-induced interaction, with a correlation-invariant operator signature and a permutation-based estimator. Controlled experiments confirm all results. Full article

Bacterial fluorescence generated by endogenous fluorophores may provide an optical approach for monitoring microbial fluorescence responses. The aim of this study was to analyse temporal changes in the Hue parameter, defined as an image-derived component of the HSB colour space representing the dominant colour tone, and to characterize strain-associated fluorescence response profiles under 405 nm violet-light excitation. A total of 28 reference bacterial strains were examined. Each strain was inoculated at eight distinct locations on a separate BHI agar plate, yielding eight colonies per strain. At 24, 48, 72, 96, and 168 h of incubation, the same colonies were repeatedly exposed for 45 s to a 405 nm continuous-wave diode laser operating at 200 mW and imaged in a completely darkened room using an iPhone 14, a yellow emission filter, and fixed acquisition geometry. The JPEG images were converted to the HSB colour space in ImageJ software (version 1.54), and background-corrected Hue values were calculated for each colony as ΔHue = Hmean − Hmean_BG using the corresponding colony and agar-background regions of interest. A complementary qualitative visual assessment was performed, and aligned rank transform ANOVA was used to evaluate the effects of bacterial strain, incubation time, and their interaction. ΔHue values differed significantly between strains and across incubation time points, with significant strain × time interactions observed in both rod-shaped and coccal bacteria (all p < 0.001). Exploratory planned contrasts also showed differences between the predefined Gram-staining groups (p = 0.0002) and between rod-shaped and coccal bacteria (p < 0.0001); however, these comparisons do not establish independent effects of Gram status or cellular morphology. The recorded fluorescence signal was generally weak, although visible temporal changes occurred in selected strains, including Staphylococcus aureus ATCC 6538P and Proteus mirabilis PCM 543. Overlap between ΔHue distributions limited separation of some strains. Background-corrected Hue analysis enabled exploratory within-dataset monitoring of temporal fluorescence colour changes under the applied in vitro imaging protocol. However, the overlap between ΔHue distributions and the technical limitations of the imaging system preclude the use of ΔHue as a standalone bacterial identification or diagnostic parameter. Full article

In the restoration of mural images with rich colour information and complex texture structures, existing techniques typically extract the spatial-domain features in the Red–Green–Blue (RGB) colour space. However, the three RGB channels are physically decoupled without unified perceptual colour correlation constraints, which often leads to noticeable colour deviation in damaged regions with large colour variations. In addition, restoring both high-frequency texture details and low-frequency global structures in a mixed-frequency spatial domain can create conflicts between frequencies, making it difficult to generate realistic high-frequency details. To address these issues, we propose the laboratory frequency network (LABFNet), a restoration network guided by the laboratory (LAB) colour space and frequency-domain constraints. Our model has two key improvements: (1) it incorporates colour parameters from the LAB space to model colour loss in murals, and (2) it decomposes the image into low- and high-frequency components and enforces frequency consistency during restoration. In the Dunhuang 20–40% mask-ratio setting, the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) improved by 1.58% and 0.27%, respectively, while the Mean Absolute Error (MAE), Learned Perceptual Image Patch Similarity (LPIPS) and CIEDE2000 decreased by 5.87%, 6.5%, and 21.65%, respectively. Experimental results on benchmark datasets show that LABFNet reduces colour deviation and structural defects. Full article

With an ever-growing recognition of Land Surface Temperature (LST) as a key Essential Climate Variable (ECV), it becomes utmost important to have such a variable at the fine spatial and temporal scales of urban spaces and dynamics. Sentinel-3 provides coarse LST (1 km, daily) based on thermal imagery acquired by its Sea and Land Surface Temperature Radiometer (SLSTR) as well as fine Spectral Directional Reflectances (SDRs, 300 m, every two days) synergically inferred from both SLSTR and the Ocean and Land Colour Instrument (OLCI), which gives the opportunity for using the latter as a predictor in the downscaling of the former. Herein, two scale-invariance-based architectures were developed: a single-timestamp (STS) model, trained with coarse data of the timestamp whose fine target it infers; and a multi-timestamp (MTS) one, trained with multiple timestamps. Note that while several Machine Learning (ML) models besides Linear Regression (LR) were considered for the MTS architecture, only LR was used for the STS one due to the limited amount of available data which the former require for hyperparameter tuning. The models were developed over four Danish Functional Urban Areas (FUAs) using SRD-derived indices and seasonal and geospatial predictors and validated against Landsat data. While Gradient Boosting (GB) achieved the best coarse-scale performance it corresponded to the worst fine-scale performer together with Random Forest (RF), indicating scale invariance breakdown. Tree-based models performed poorly due to extrapolation limitations, whereas Neural Net (NN) and LR proved more robust. After residual correction, single-timestamp LR achieved the best fine-scale performance, making it the most reliable and recommended architecture for operations. The overall results showed that, although ML models may better predict the target at their training scale, their performance may not significantly generalise at others, therefore revealing scale specificity. Furthermore, the results suggested that usage of the more general multi-timestamp architecture instead of the single one may deteriorate performance. Full article

The growing need for secure image transmission across public networks requires robust encryption algorithms. Traditional chaos-based image ciphers typically have a small key space, weak avalanche behavior, or are susceptible to differential cryptanalysis. To overcome such inadequacies, this paper suggests a new adaptive image cryptosystem that combines a fractional-order memristive chaotic engine and a non-linear hybrid encryption kernel. The system uses piano-inspired feedback; the keystream generator dynamically adapts to the previously encrypted pixel, enabling powerful Cipher Block Chaining (CBC)-style chaining and content-dependent diffusion. A four-dimensional memristive system is solved by the use of fractional-order calculus, which gives an ultra-large key space (>10⁸⁰) and very high sensitivity to initial conditions—confirmed by a positive largest Lyapunov exponent (1.7199). The encryption kernel maps the traditional Exclusive OR (XOR) with the reversible two-step operation: the modular addition of the plaintext with the first keystream byte and the XOR with the second keystream one, both of which increase non-linearity and confusion. Large-scale experiments with six standard 256 × 256 colour images indicate almost ideal entropy (7.9994), Number of Pixel Change Rate (NPCR) which is 99.62, Unified Average Changing Intensity (UACI) which is 33.43, correlation coefficients are near to zero, very low Gray-Level Co-occurrence Matrix (GLCM) homogeneity (≈0.017) and high contrast (≈4843) and low energy (≈0.006 The ciphertext passes seven National Institute of Standards and Technology (NIST) SP-800-22 statistical tests, is extremely sensitive to keys (a perturbation of 1 × 10⁻¹⁴ alters >99.6% of ciphertext) and resists chosen-plaintext and known-plaintext attacks. Decryption has linear time complexity O(N), and average encryption and decryption times are 3.40 s and 2.75 s for 256 × 256 images. The proposed cryptosystem provides an attractive security–performance trade-off that can be used in high-security systems like medical image protection, privacy-preserving multimedia transmission, and secure cloud storage. Full article

The history of pictorial space can be understood as a history of visual artifice, perceptual constructions, and material illusions inscribed on the painted surface. This article examines some fundamental milestones in the relationship between pictorial surface and space through a comparative analysis spanning from the modern tradition to contemporary painting, with special attention to the work of Claude Monet and Mark Rothko. It studies those pictorial strategies capable of generating perceptual ambiguity and uncertainty in the observer as a source of aesthetic and emotional experience. Starting from the conical perspective as a historical device for representing space on a two-dimensional surface, the work analyses its progressive dissolution at the end of the 19th century and the emergence of new spatial resources based on colour, matter and the organisation of the pictorial surface. In this context, painting abandons traditional optical illusion to explore forms of perceptual spatiality that can be as tangible as constructed architecture. Taking an interdisciplinary approach that links art theory, the history of painting and visual analysis, the article contributes to our understanding of the ways in which materials, pictorial methods and compositional strategies shape spatial experiences in modern and contemporary painting. Full article

Magic lantern slides are fragile objects consisting of transparent images depicted on thin glass plates to be projected by magic lanterns. Despite their widespread presence in archives and museums, these collections are often undervalued and understudied. The Portuguese Cinematheque holds the most extensive collection of slides in Portugal. This article presents the first preventive conservation case study focused on the collection of painted slides, reflecting on the general origins of this collection, examining the challenges faced by caretakers when adapting historical buildings to accommodate collections of this nature. Environmental monitoring of light and radiation, temperature, and relative humidity in storage and exhibition rooms was combined with ultraviolet-visible spectroscopy to measure the fading of one of the most light-sensitive colours identified in these slides in previous studies, the pink eosin-based lake, by comparing a slide exhibited under the measured light conditions with one kept in storage during the same period. The results identified damaging light exposure in display areas with illuminance values far above the recommended levels for these materials, and significant RH fluctuations in both spaces. These conditions are consistent with deterioration factors known to affect the material that composes these fragile media (e.g., light-sensitive painting materials and organic frames, and unstable glass). This study also showcases how raising awareness on the fragility of this heritage stimulated discussions and encouraged small and feasible changes that can positively impact its preservation. Full article

Lighting quality in interior spaces is not determined solely by horizontal illuminance at the workplace, but to a large extent by the spatial distribution of light, in particular by the luminance of ceilings and walls. Building on classical principles of lighting technology and visual perception, this article examines the influence of the ratio of indirect to direct lighting on the perception of room brightness, the spatial impression, and overall preference. To this end, two complementary studies were conducted: a visual assessment of realistic room simulations and a user study in a real meeting room with variable illuminance levels and systematically varied proportions of indirect and direct lighting. The results consistently show that perceived room brightness and user preference correlate much more strongly with the illumination of ceilings and walls than with the horizontally measured illuminance on the table, which was kept constant. A balanced ratio of indirect to direct light—typically in the range of approximately 35% to 65% indirect lighting—is preferred by users, whereas predominantly direct or nearly purely indirect lighting is associated with lower acceptance. The study clearly demonstrates that existing standards, which primarily focus on horizontal illuminance, neglect essential aspects of lighting quality. The findings highlight the need to systematically integrate light distribution, vertical illuminance, and spatial–psychological effects into lighting design, evaluation, and standardization in order to achieve visually comfortable, widely accepted, and spatially appropriate lighting solutions. Full article

People spend most of their time indoors, highlighting the importance of indoor environmental quality for health and wellbeing. While previous studies have shown that exposure to nature can benefit wellbeing, much of this research has focused on outdoor environments, and less is known about how indoor plants and their spatial characteristics influence human perceptions and experiences. This paper reports on a survey study exploring how perceived health and wellbeing are influenced by indoor plants and human preferences for their characteristics, spatial arrangement, and other features within indoor environments. Indoor plants serve as visual and multisensory environmental stimuli. By examining the relationship between indoor plants, preferences, perceptions, visual comfort, multisensory experiences, and wellbeing, the study aims to understand these influences. The questionnaires include multiple-choice questions, yes-no questions, and open-ended questions, allowing the collection of both quantitative and qualitative data. The survey findings highlight the unique benefits of indoor plants, emphasising their potential to enhance wellbeing in ways that outdoor nature may not fully replicate in indoor settings. One significant finding of this study is that scattering indoor plants throughout a space can enhance the connection to nature through three-dimensional spatial interaction, potentially improving wellbeing. This arrangement may serve as a bridge to the outdoors, providing a psychological link to the natural environment. Crucial preference factors also include the complexity and coherence of indoor plants’ appearance, such as colour, shape, and size. The results further indicate that students prefer indoor plants over other elements such as cut flowers, fake plants, or artificial plant representations. The findings indicate that caring for indoor plants may foster emotional engagement, a sense of fulfilment, and place attachment through everyday interaction. In public spaces, plants may also enhance feelings of refuge and perceived security. These findings provide practical recommendations for designing indoor environments that enhance student wellbeing and human–environment interaction. Full article

Skin pigmentation is a crucial factor influencing the market value of gilthead seabream. A three-month feeding trial evaluated the effects of dietary inclusion of Rhodotorula mucilaginosa on skin and fillet pigmentation of gilthead seabream (Sparus aurata). Four diets containing yeast were tested in triplicate tanks using 120 fish in total. Skin and fillet colours were assessed via computer-based image analysis in CIELAB, RGB and HSB spaces. Analysis of total carotenoids was also performed. Yeast inclusion increased L* and Whiteness values in the operculum and enhanced lightness in ventral skin regions. In the abdominal area, RGB values decreased, particularly in the 3% diet. Fillet responses were limited to the red muscle, where the 3% diet significantly increased a* and Chroma values. Overall, inclusion of R. mucilaginosa exceeding 2% influenced seabream skin brightness and total carotenoid content, while 3% inclusion enhanced red muscle pigmentation, suggesting potential as a natural pigment source in seabream feeds. Full article

Given China’s increasingly severe population ageing, urban comprehensive parks are important places for older adults’ daily activities. Improving their quality directly affects the physical and mental health of older adults. Most previous studies have explored spatial optimisation strategies from a single dimension, focusing either on behaviour or on perception; studies on simultaneous improvements in behavioural and perceptual levels across functional space types remain limited. This study selects 40 activity spaces from four urban comprehensive parks in Shenzhen as samples. It systematically analyses differences in older adults’ behavioural patterns and perceptual experiences across six types of functional spaces. Based on the results, a comprehensive behaviour–perception evaluation model is developed to identify optimisation priorities for different space types. Furthermore, generalised linear regression models are employed to explore the relationships between environmental elements and older adults’ behaviours and perceptions, from which targeted optimisation strategies are derived. First, significant differences are observed among six functional space types in older adults’ concentrated leisure behaviour, dispersed exercise behaviour, concentrated exercise behaviour, and safety, while the remaining indicators are relatively balanced. Second, the evaluation model classifies the 40 samples into four space types, including high behavioural level–high perceptual level, high behavioural level–low perceptual level, low behavioural level–high perceptual level, and low behavioural level–low perceptual level. Third, 12 environmental elements, including area, degree of greenery, and leisure facilities, are associated with older adults’ behavioural and perceptual levels in urban comprehensive parks. Fourth, optimisation strategies are proposed for problem spaces with low behavioural or perceptual levels across the six functional space types, including behavioural strategies such as expanding activity spaces and avoiding excessive plant density, as well as perceptual strategies such as improving plant landscape layering and balancing spatial colour combinations. This study develops a quantitative evaluation and spatial optimisation framework guided by older adults’ behaviour and perception, providing theoretical support and practical insights for the sustainable improvement of urban comprehensive park quality. Full article

The issue of children’s mental health is becoming increasingly prominent worldwide. Research indicates that insufficient physical activity constitutes a significant risk factor for various health issues. As primary school campuses serve as the primary setting for children’s physical activities, their spatial design currently fails to adequately support children’s psychological needs, thereby hindering improvements in mental well-being. This study, grounded in the theory of basic psychological needs, employs a combined approach of quantitative bibliometric analysis and qualitative content analysis to systematically investigate the relationship between children’s psychological needs and the design of physical activity spaces within school environments. The study identified six major research clusters: children’s health, self-determination theory, evaluation, physical education, user-centred design, and physical health. These reveal the multidimensional relationship between spatial design and children’s well-being. The key findings suggest that optimising facility diversity, designing progressively challenging activity zones, and implementing function-oriented colour coding can fulfil children’s fundamental psychological needs for autonomy, competence, and relatedness. These measures significantly enhance their mental well-being and overall happiness. This study extends the application of basic psychological needs theory to the field of campus spatial design, providing practical guidance for designers, educators, and policymakers. It aims to collectively advance the continuous optimisation of school sports facilities, thereby creating more favourable conditions for children’s healthy development. Full article