Model Of Visual System Research Articles

Systematic Literature Review on the Fidelity of Maritime Simulator Training

The fidelity of a maritime simulator refers to how realistic the representation of a vessel and its environment look, behave, and feel in real life. Despite the benefits of using simulators in maritime training and education, there is a lack of understanding of different debates on whether higher levels of fidelity translate into better training outcomes. Therefore, to investigate and summarise what is known about maritime simulator fidelity, we conducted a systematic literature review on the maritime simulator-based training literature from 2005 to 2021. We performed bibliometric, authorship, and content analyses of thirty-six references, including white and grey literature. The results show that simulator fidelity is divided into physical and functional fidelity. While the former includes the ergonomics layout of the bridge, visual system, vessel manoeuvrability, and hydrographic modelling, the latter involves training program design, simulator session design, and the role of the instructor. The results reveal that there is no prevalent tradition in the literature, a low number of citations, and the references are dispersed among many publications, authors, and institutions. Despite the fact that the prevalence of studies employing high-fidelity simulators can positively impact training, most of the studies are based on subjective evaluation, if any evidence is provided, and were produced by Scandinavian and European institutions and researchers. To address these limitations, we propose a research agenda containing three recommendations.

Predicting Identity-Preserving Object Transformations in Human Posterior Parietal Cortex and Convolutional Neural Networks.

Previous research shows that, within human occipito-temporal cortex (OTC), we can use a general linear mapping function to link visual object responses across nonidentity feature changes, including Euclidean features (e.g., position and size) and non-Euclidean features (e.g., image statistics and spatial frequency). Although the learned mapping is capable of predicting responses of objects not included in training, these predictions are better for categories included than those not included in training. These findings demonstrate a near-orthogonal representation of object identity and nonidentity features throughout human OTC. Here, we extended these findings to examine the mapping across both Euclidean and non-Euclidean feature changes in human posterior parietal cortex (PPC), including functionally defined regions in inferior and superior intraparietal sulcus. We additionally examined responses in five convolutional neural networks (CNNs) pretrained with object classification, as CNNs are considered as the current best model of the primate ventral visual system. We separately compared results from PPC and CNNs with those of OTC. We found that a linear mapping function could successfully link object responses in different states of nonidentity transformations in human PPC and CNNs for both Euclidean and non-Euclidean features. Overall, we found that object identity and nonidentity features are represented in a near-orthogonal, rather than complete-orthogonal, manner in PPC and CNNs, just like they do in OTC. Meanwhile, some differences existed among OTC, PPC, and CNNs. These results demonstrate the similarities and differences in how visual object information across an identity-preserving image transformation may be represented in OTC, PPC, and CNNs.

Robustness in bio‐inspired visually guided multi‐agent flight and the gain modulation hypothesis

AbstractAerial swarm implementations often underperform their feedback design goals due to sensor noise, modeling errors, and external disturbances, each of which can often be mitigated by including robustness in the design approach. At the same time, gain modulation has been measured in numerous insect flight examples involving relative position regulation and tracking. Gains are often lower than what initially appears optimal, which is not fully explained by existing hypotheses. This article analyzes the robustness of a visual feedback control system modeling insect flight feedback paths by using optic flow to regulate an agent's motion relative to its neighbors. This study considers the system's robustness to sensor noise and configuration deviations, which appear as a nonlinearity in the observation equation often neglected in linear feedback. The analysis indicates robust performance can be attained by a static gain controller by appropriate choice of gain. Experimental results using an optic flow swarm implementation in robotic systems are used to quantify the actual system performance for static gain controllers. Performance is compared when the system responds to ideal optic flow (no sensor noise) and to camera‐based optic flow swarm implementation (sensor noise and configuration uncertainty). [Correction added on 10 November 2022, after first online publication: the underline in the word ‘compared’ of the preceding sentence has been removed in this version.] The analysis suggests neural gain modulation in insect feedback paths may support robust group motion stabilization.

Mathematical study of neural feedback roles in small target motion detection.

Building an efficient and reliable small target motion detection visual system is challenging for artificial intelligence robotics because a small target only occupies few pixels and hardly displays visual features in images. Biological visual systems that have evolved over millions of years could be ideal templates for designing artificial visual systems. Insects benefit from a class of specialized neurons, called small target motion detectors (STMDs), which endow them with an excellent ability to detect small moving targets against a cluttered dynamic environment. Some bio-inspired models featured in feed-forward information processing architectures have been proposed to imitate the functions of the STMD neurons. However, feedback, a crucial mechanism for visual system regulation, has not been investigated deeply in the STMD-based neural circuits and its roles in small target motion detection remain unclear. In this paper, we propose a time-delay feedback STMD model for small target motion detection in complex backgrounds. The main contributions of this study are as follows. First, a feedback pathway is designed by transmitting information from output-layer neurons to lower-layer interneurons in the STMD pathway and the role of the feedback is analyzed from the view of mathematical analysis. Second, to estimate the feedback constant, the existence and uniqueness of solutions for nonlinear dynamical systems formed by feedback loop are analyzed via Schauder's fixed point theorem and contraction mapping theorem. Finally, an iterative algorithm is designed to solve the nonlinear problem and the performance of the proposed model is tested by experiments. Experimental results demonstrate that the feedback is able to weaken background false positives while maintaining a minor effect on small targets. It outperforms existing STMD-based models regarding the accuracy of fast-moving small target detection in visual clutter. The proposed feedback approach could inspire the relevant modeling of robust motion perception robotics visual systems.

Can Sensory Drive Explain the Evolution of Visual Signal Diversity in Terrestrial Species? A Test with Anolis Lizards.

AbstractAnimal signal colors evolve to efficiently stimulate conspecific visual systems. The sensory drive hypothesis proposes that species differences in habitat light conditions favor the evolution of color diversity. The strongest support comes from aquatic systems, while terrestrial systems offer fewer convincing examples. Anolis lizards occupy diverse habitats and signal with a colorful dewlap. Dewlap visibility depends on perceived chromatic contrast with the background. Visual system modeling has shown that red dewlaps are most visible in most habitat types. However, a majority of species possess white or yellow dewlaps. In a recent behavioral study, we showed that low light conditions can sometimes make yellow and white colors more visible by altering chromatic contrast perception with the background. Using 17 Caribbean Anolis species, we showed that cut-on wavelength, a measure of dewlap color in a white to red continuum, correlates with habitat light intensity. Pairwise comparisons revealed that red dewlaps are most visible in bright habitats, whereas yellow and white are more visible in darker habitats. We conclude that sensory drive has contributed to the evolution of dewlap color differences through the interactive effects of total habitat light intensity and chromatic contrast perception and may provide a mechanism for speciation among anoles.

Arousal state affects perceptual decision-making by modulating hierarchical sensory processing in a large-scale visual system model.

Arousal levels strongly affect task performance. Yet, what arousal level is optimal for a task depends on its difficulty. Easy task performance peaks at higher arousal levels, whereas performance on difficult tasks displays an inverted U-shape relationship with arousal, peaking at medium arousal levels, an observation first made by Yerkes and Dodson in 1908. It is commonly proposed that the noradrenergic locus coeruleus system regulates these effects on performance through a widespread release of noradrenaline resulting in changes of cortical gain. This account, however, does not explain why performance decays with high arousal levels only in difficult, but not in simple tasks. Here, we present a mechanistic model that revisits the Yerkes-Dodson effect from a sensory perspective: a deep convolutional neural network augmented with a global gain mechanism reproduced the same interaction between arousal state and task difficulty in its performance. Investigating this model revealed that global gain states differentially modulated sensory information encoding across the processing hierarchy, which explained their differential effects on performance on simple versus difficult tasks. These findings offer a novel hierarchical sensory processing account of how, and why, arousal state affects task performance.

Biometric identification of sheep via a machine-vision system

This paper describes a sheep biometric identification system based on facial images. A machine vision system and deep learning model were developed and applied for animal identification. The system included two 8-MegaPixels cameras installed in a controlled water trough adapted to work with NVIDIA Jetson Nano-embedded system-on-module (SoM). Data from 81 Assaf breed sheep, aged two to three months, from two different groups of sheep, were collected over a period of two weeks. The biometric identification model included two steps: face detection and classification. In order to locate and localize the sheep's face in an image, the Faster R-CNN deep learning object detection algorithm was applied. The detected face was provided as input to seven different classification models. Different transfer learning methods were examined. The best performance was obtained using a ResNet50V2 model with the state-of-art ArcFace loss function. The identification system resulted in average accuracies of 95% for the two groups tested. When applying transfer learning methods, average identification accuracies improved to 97% in both groups, and the training process was accomplished in half the time. The newly developed system proves the feasibility of individual biometric identification of sheep on commercial farms.

SISTEM INFORMASI E-RAPORT MENGGUNAKAN EXPECTATION CONFIRMATION MODEL (ECM) PADA SMAN 1 PABUARAN

SMA Negeri 1 Pabuaran is one of the schools that has implemented the 2013 Curriculum. The change from the KTSP curriculum to the 2013 curriculum certainly changes the value management process. The process of managing report cards carried out is currently less effective and efficient because the process is carried out separately using Microsoft Excel. There is often a difference in the format of report values between subject teachers and homeroom teachers, so homeroom teachers need to change these scores to fit the proper format. The purpose of this study is to design and develop a value management information system using a web-based E-Report and to conduct quality testing using the Expectation Confirmation Model (ECM) method on the information system developed. The system design used in this research is using the Waterfall method so that it is easier to develop and use UML (Unified Modeling Language) for visual system modeling. The results achieved after the implementation of this application make it easier for users (teachers, homeroom teachers, and student parents) to do their work and overcome the difficulties of inputting report values that have been done in schools. The conclusion obtained is that using the e-rapport application can support improvements in work so that the process of inputting values ​​is more effective and efficient. The value of the report becomes more structured and well-documented. The results of the research on the level of user satisfaction with thee-rapport system are in the very good or very satisfied category.

Adaptive neural network control for image‐based visual servoing of robot manipulators

This paper presents a novel adaptive neural network control strategy for image-based visual servoing (IBVS) of robotic manipulators with both eye-in-hand and eye-to-hand camera configurations in the presence of unknown dynamics and external disturbances. The IBVS method is combined with the adaptive neural network to construct the proposed adaptive neural network controller to solve the visual servoing control problem of robots. The adaptive neural network based IBVS controller is designed based on the depth-independent interaction matrix, which can be trained on-line to identify the visual servoing robotic system modeling errors. Moreover, the proposed method can approach the unknown nonlinear dynamics for both eye-in-hand and eye-to-hand camera configurations without requiring the robot dynamics to be linearly parameterizable, and the exact knowledge of the robot structure is not needed. On the basis of the nonlinear robot dynamics, the Lyapunov stability analysis is given to prove the asymptotical convergence of the image position and velocity errors. Simulation results for both camera configurations are provided to demonstrate the performance of the proposed adaptive neural network based approach.

Uncalibrated visual positioning using adaptive Kalman Filter with dual rate structure for wafer chip in LED packaging

In the LED packaging, the changes of calibration parameters will affect the positioning effect of wafer chip and eventually result in the quality degradation of packaging process. Moreover, the frequent visual calibration processes will reduce the production efficiency. Accordingly, an uncalibrated visual positioning method for wafer chips is presented and applied for LED packaging in this paper. Firstly, the calibration model of LED chip visual positioning system is established. After sensitivity test based on calibration model, two typical cases of calibration parameters variation in LED packaging are given and analyzed. Then, the Kalman Filter is used to online estimate the variable calibration parameters, where two kinds of state vectors are designed for the two cases respectively. To accelerate the convergence and heighten the robustness, an adaptive design is introduced to improve the iterative process of Kalman Filter. Considering the influence of real time problems in visual signal, a dual rate structure is proposed to compensate the visual delay and realize the time synchronization for the multi-rate sensing. Based on the presented adaptive Kalman Filter with dual rate structure, an uncalibrated visual positioning control system is designed and verified by simulation. Finally, the chip positioning experimental results demonstrate that the proposed method can effectively improve the positioning effect of wafer chips and the working efficiency in LED packaging, which can be applied in practical production.

Real-Time CNN-based Computer Vision System for Open-Field Strawberry Harvesting Robot

Strawberry production in open-field conditions requires a lot of human labor, which is increasingly difficult to recruit. A robotic solution could potentially operate in the field around the clock with minimal supervision. For strawberry farmers, automation of harvesting would eliminate the personnel risk and provide security for operations in the long term. A robot which would be capable of replacing physical human labor in horticultural production requires an accurate and fast perception system. In this paper, we focus on the task of detecting of garden strawberries to guide the picking by a strawberry harvesting robot. We have developed a real-time implementation of strawberry and peduncle detection system that runs on an edge device. This paper outlines the vision system requirements, hardware selection, model selection, training process and results. After consideration of the overall requirements of the system, we decided to use YOLOv5 to detect both the berries and peduncles for the picking system. Training data was collected and annotated, and the detection model was trained. The network had 91.5% average precision (AP) for detecting strawberries and an 43.6% AP for detecting peduncles. One of the reasons for performance discrepancy was the difficulty to detect peduncles from afar. Overall, the vision algorithm reached the performance that was required to guide the robot to a strawberry and detect the corresponding strawberry-peduncle pairs. However, for densely clustered berries the method often failed to detect the correct peduncle and needs to be improved.

Matching of small packages of traditional Chinese medicine based on improved RANSAC algorithm

The vision system model of small package sorting of traditional Chinese medicine was constructed, and the chessboard calibration method was used to calibrate the binocular camera. Surf algorithm and orb algorithm are analyzed by experiments, and orb algorithm with high real-time performance is used to extract feature points. The fast nearest neighbor FLANN algorithm is used to quickly match the feature points, and the matched feature points are screened according to Lowe’s algorithm and v-axis coordinate consistency principle, to solve the problem of false matching points. The method of selecting feature points based on matching quality ranking to calculate the homography matrix is designed, which solves the random sampling problem of the RANSAC algorithm and effectively shortens the time of feature matching.

The visual ecology of selective predation: Are unhealthy hosts less stealthy hosts?

Predators can strongly influence disease transmission and evolution, particularly when they prey selectively on infected hosts. Although selective predation has been observed in numerous systems, why predators select infected prey remains poorly understood. Here, we use a mathematical model of predator vision to test a long‐standing hypothesis about the mechanistic basis of selective predation in a Daphnia–microparasite system, which serves as a model for the ecology and evolution of infectious diseases. Bluegill sunfish feed selectively on Daphnia infected by a variety of parasites, particularly in water uncolored by dissolved organic carbon. The leading hypothesis for selective predation in this system is that infection‐induced changes in the transparency of Daphnia render them more visible to bluegill. Rigorously evaluating this hypothesis requires that we quantify the effect of infection on the visibility of prey from the predator's perspective, rather than our own. Using a model of the bluegill visual system, we show that three common parasites, Metschnikowia bicuspidata, Pasteuria ramosa, and Spirobacillus cienkowskii, decrease the transparency of Daphnia, rendering infected Daphnia darker against a background of bright downwelling light. As a result of this increased brightness contrast, bluegill can see infected Daphnia at greater distances than uninfected Daphnia—between 19% and 33% further, depending on the parasite. Pasteuria and Spirobacillus also increase the chromatic contrast of Daphnia. These findings lend support to the hypothesis that selective predation by fish on infected Daphnia could result from the effects of infection on Daphnia's visibility. However, contrary to expectations, the visibility of Daphnia was not strongly impacted by water color in our model. Our work demonstrates that models of animal visual systems can be useful in understanding ecological interactions that impact disease transmission.

Visual Decision Support System Model for Managing Unemployment by Hybrid Education

Hybrid eeducation is an approach that helps in conducting face-to-face and online ddistance learning especially for formal education. However, during COVID-19 pandemic, formal education institutions including schools and universities as well as informal education tthrough the media for communities and industries are practiced by the lawmakers to manage workplace distancing. Food supply chain are experiencing unexpected disruptions due to interrelated activities that will determine supply chain performance and efficiency. This article explores the challenges faced by food industry and related sectors due to emergence impact of COVID-19 in Malaysia. Food supply chain management (FSCM) is a complex task involving interconnected activities and numerous stakeholders for a specific food product from raw materials to final product before it reaches the end customers. An overview of COVID-19 scenarios, followed by the impact of pandemic towards the activities in food supply chain, and the management issues that need to be addressed are presented. Several challenges identified are including the worldwide implication of the pandemic scenarios to food supply chain management and food supply chain activities, and indirect impact of supply chain disruption to labour force; unemployment and retrenchment. Finally, a visual decision support system (VDSS) model is developed to illustrate the main impacts of the pandemic scenario on food supply chain as well as addressing the labour management and opportunities. It has potential to provide general guidelines to educators, policy-makers, and decision-makers to deal with uncertainties after the pandemic.

A Model of the Early Visual System Based on Parallel Spike-Sequence Detection, Showing Orientation Selectivity.

Simple SummaryA computational model of primates’ early visual processing, showing orientation selectivity, is presented. The system importantly integrates two key elements: (1) a neuromorphic spike-decoding structure that considerably resembles the circuitry between layers IV and II/III of the primary visual cortex, both in topology and operation; (2) the plasticity of intrinsic excitability, to embed recent findings about the operation of the same area. The model is proposed as a tool for the analysis and reproduction of the orientation selectivity phenomenon, whose underlying neuronal-level computational mechanisms are today the subject of intense scrutiny. In response to rotated Gabor patches the model is able to exhibit realistic orientation tuning curves and to reproduce responses similar to those found in neurophysiological recordings from the primary visual cortex obtained under the same task, considering different stages of the network. This demonstrates its aptness to capture the mechanisms underlying the evoked response in the primary visual cortex. Our tool is available online, and can be expanded to other experiments using a dedicated software library developed by the authors, to elucidate the computational mechanisms underlying orientation selectivity.Since the first half of the twentieth century, numerous studies have been conducted on how the visual cortex encodes basic image features. One of the hallmarks of basic feature extraction is the phenomenon of orientation selectivity, of which the underlying neuronal-level computational mechanisms remain partially unclear despite being intensively investigated. In this work we present a reduced visual system model (RVSM) of the first level of scene analysis, involving the retina, the lateral geniculate nucleus and the primary visual cortex (V1), showing orientation selectivity. The detection core of the RVSM is the neuromorphic spike-decoding structure MNSD, which is able to learn and recognize parallel spike sequences and considerably resembles the neuronal microcircuits of V1 in both topology and operation. This structure is equipped with plasticity of intrinsic excitability to embed recent findings about V1 operation. The RVSM, which embeds 81 groups of MNSD arranged in 4 oriented columns, is tested using sets of rotated Gabor patches as input. Finally, synthetic visual evoked activity generated by the RVSM is compared with real neurophysiological signal from V1 area: (1) postsynaptic activity of human subjects obtained by magnetoencephalography and (2) spiking activity of macaques obtained by multi-tetrode arrays. The system is implemented using the NEST simulator. The results attest to a good level of resemblance between the model response and real neurophysiological recordings. As the RVSM is available online, and the model parameters can be customized by the user, we propose it as a tool to elucidate the computational mechanisms underlying orientation selectivity.

A test of Sensory Drive in plant-pollinator interactions: heterogeneity in the signalling environment shapes pollinator preference for a floral visual signal.

Sensory Drive predicts that habitat-dependent signal transmission and perception explain the diversification of communication signals. Whether Sensory Drive shapes floral evolution remains untested in nature. Pollinators of Argentina anserina prefer small ultraviolet (UV)-absorbing floral guides at low elevation but larger guides at high. However, mechanisms underlying differential preference are unclear. High elevation populations experience elevated UV irradiance and frequently flower against bare substrates rather than foliage, potentially impacting signal transmission and perception. At high and low elevation extremes, we experimentally tested the effects of UV light (ambient vs reduced) and floral backgrounds (foliage vs bare) on pollinator choice for UV guide size. We examined how different signalling environments shaped pollinator-perceived flower colour using visual system models. At high elevation, pollinators preferred locally common large UV guides under ambient UV, but lacked preference under reduced UV. Flies preferred large guides only against bare substrate, the common high elevation background. Ambient UV amplified contrast of large UV guides with floral backgrounds, and flowers contrasted more with bare ground than foliage. Results support that local signalling conditions contribute to pollinator preference for a floral visual signal, a key tenet of Sensory Drive. Components of Sensory Drive could shape floral signal evolution in other plants spanning heterogeneous signalling environments.

A Model of Visual Intelligent System for Genus Identification of Fish in the Siluriformes Order

Ambiguity in the fish naming is present in several fish species database, especially for fish in Siluformes order. To fix the ambiguity, a visual intelligent system is needed to automate the fish naming correction in the database. In this study, we developed a deep-learning-based model as the core of the intelligent system. The proposed model achieved 89% accuracy for the classification of three genera in Siluformes order: Mystus, Hemibagrus, and Glyptothorax.

Coordination of top-down influence on V1 responses by interneurons and brain rhythms

Top-down processing in neocortex underlies functions such as prediction, expectation, and attention. Visual systems have much feedback connection that carries information of behavioral context. Top-down signals along feedback pathways modulate the representation of visual information in early visual areas such as primary visual cortex (V1). Recent studies have shown further that beta rhythms are responsible for the transmission of behavioral-context information to lower visual areas. However, the mechanism underlying top-down influence and the role of brain rhythms in top-down processing are poorly understood. To address these issues, we focus on experimental studies on top-down influence in visual perceptual tasks. We develop a model of visual system, in which early visual areas are subjected to top-down influence from a recognition area. We show that task-relevant information in early visual areas is regulated by a push-pull effect, produced by somatostatin-expressing interneurons and top-down signal. We also show that task-context information is coordinated by the phase-phase coupling of beta rhythms, while the local, task-relevant stimulus features are enhanced by the phase-amplitude coupling of beta and gamma rhythms. Furthermore, the feedback from a higher visual area such as secondary visual area facilitates the gating of task-relevant information in V1. The results provide insights to understanding the roles of inhibitory interneurons and brain rhythms in top-down influence on information processing in early visual areas.

Natural environment statistics in the upper and lower visual field are reflected in mouse retinal specializations

Pressures for survival make sensory circuits adapted to a species' natural habitat and its behavioral challenges. Thus, to advance our understanding of the visual system, it is essential to consider an animal's specific visual environment by capturing natural scenes, characterizing their statistical regularities, and using them to probe visual computations. Mice, a prominent visual system model, have salient visual specializations, being dichromatic with enhanced sensitivity to green and UV in the dorsal and ventral retina, respectively. However, the characteristics of their visual environment that likely have driven these adaptations are rarely considered. Here, we built a UV-green-sensitive camera to record footage from mouse habitats. This footage is publicly available as a resource for mouse vision research. We found chromatic contrast to greatly diverge in the upper, but not the lower, visual field. Moreover, training a convolutional autoencoder on upper, but not lower, visual field scenes was sufficient for the emergence of color-opponent filters, suggesting that this environmental difference might have driven superior chromatic opponency in the ventral mouse retina, supporting color discrimination in the upper visual field. Furthermore, the upper visual field was biased toward dark UV contrasts, paralleled by more light-offset-sensitive ganglion cells in the ventral retina. Finally, footage recorded at twilight suggests that UV promotes aerial predator detection. Our findings support that natural scene statistics shaped early visual processing in evolution.

A Novel Fuzzy Inference System Based Robust Reversible Watermarking Technique provided with Six Layer Security

Digital Watermarking has evolved as one of the latest technologies for digital media copyright protection. Watermarking of images can be done in many ways and one of the proposed algorithms for image watermarking is by utilizing Fuzzy Logic. It is similar to the concept of a Fuzzy set, each element can be defined by an ordered pair, in which one is the value and other is the membership function value. Fuzzy logic systems can explain inaccurate information and explain their decisions. Fuzzy inference system is the simplest way of performing Fuzzy Logic. In the proposed method, three Fuzzy inference models are used to generate the weighing factor for embedding the watermark and input to the Fuzzy Inference System is taken from the Human Visual System model. The Performance measures used in the Process are Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM), Normalized Cross Correlation (NCC) and Bit Error Ratio (BER). The Proposed algorithm is immune to various Image Processing attacks.