Search

BACKGROUND: The effects of traffic sign information volume (TSIV) on the visual characteristics and workload of novice and experienced drivers were investigated in this study. TSIV plays a crucial role in road traffic safety, and understanding its impact on drivers is essential for designing effective traffic sign systems. OBJECTIVE: This research aimed to compare the visual characteristics and workload of novice and experienced drivers under varying TSIV doses through simulated driving tests. The objective was to provide insights for optimizing the design of road TSIV. METHODS: Six TSIV levels were considered: S0, S1, S2, S3, S4, and S5, representing different workload levels. Participants, including both novice and experienced drivers, were involved in simulated driving scenarios with varying TSIV levels. Eye movement data was collected using an eye tracker device. The study was conducted in China, and appropriate driving simulators and equipment were utilized. RESULTS: The findings revealed several valuable results. Experienced drivers exhibited a higher proportion of saccade behavior in the 30–90 ms time period and did not show rapid saccade behavior during the 0–30 ms period, indicating superior visual search strategies. Both novice and experienced drivers demonstrated improved visual cognitive abilities at the S3 level of TSIV, which corresponds to normal and safe driving conditions. Furthermore, a majority of both groups had saccade amplitudes in the range of 0°–4°, with experienced drivers showing a slightly higher proportion. About 82% of experienced drivers had saccade behavior within the range of 0°–2°, compared to 75% of novice drivers. CONCLUSIONS: The study concludes that the S3 level of TSIV, corresponding to 30 bits/km, is optimal for both novice and experienced drivers. This level promotes better visual performance and reduces visual workload, indicating that drivers' information acquisition capacity and visual search strategies are maximized while keeping the workload associated with driving at a minimum. These findings have significant implications for enhancing driving safety. [ABSTRACT FROM AUTHOR]

More collisions occur at the exit ramps of expressways due to frequent lane-changing behavior and interweaving between vehicles. Young drivers with shorter driving mileage and driving experience, radical driving styles, and worse behavior prediction are likelier to be involved in collisions at the exit ramps. This paper focuses on the correlation analysis between young drivers' characteristics and their visual and physiological attributes at expressway exit ramps. First, the driver's gender, driving experience, and mileage are classified. Then, seven expressway exit models are established using the UC/Win road modeling software. The driver's driving plane vision is divided into four areas using the K-means clustering algorithm. In addition, the driver's visual and heart rate attributes were analyzed at 500 m, 300 m, 200 m, and 100 m away from an expressway exit. The results show that the visual attributes, gender, and driving mileage of young drivers strongly correlate with the fixation times and average saccade amplitude. In contrast, the driving experience has almost no correlation with the fixation behavior of young drivers. Young drivers' driving experience and mileage strongly correlate with cardiac physiological attributes, but there is virtually no correlation with gender. The practical implications of these results should be helpful to highway planners and designers. [ABSTRACT FROM AUTHOR]

(1) The early assessment of wood quality, even while trees are standing, provides significant benefits for forest management, sales efficiency, and market diversification. Its definition cannot be in absolute terms but must always be linked to the material's intended use. (2) In this contribution, a review of the scientific literature is given to discuss the visually evaluable attributes that define wood quality in standing trees, the applicability of the techniques used for their assessment, and the effectiveness of these attributes and technologies in predicting quality, to finally highlight future research needs. (3) The visual characteristics generally used to evaluate wood quality are linked to stem form and dimension, branchiness, and stem damage, but their assessment is challenging due to time and resource constraints. To address these challenges, laser-based and image-based techniques have been applied in field surveys. (4) Laser scanners offer detailed and accurate measurements. Photogrammetry, utilizing images to reconstruct 3D models, provides a cost-effective and user-friendly alternative. Studies have demonstrated the effectiveness of these tools in surveying the visible properties of stems and branches, but further development is necessary for widespread application, particularly in software development, with faster and more effective algorithmic advancements for automatic recognition and subsequent measurement of pertinent characteristics being critical for enhancing tool usability. (5) However, predicting wood quality from these surveys remains challenging, with a limited correlation between the visible tree characteristics assessed and the sawn product quality. Empirical studies evaluating products downstream in the forest-wood supply chain could provide valuable insights. In this sense, the implementation of traceability systems could facilitate the linkage between data on standing trees and the quality of the sawn product. Also, further research is needed to develop models that can accurately predict internal tree characteristics and their impact on product quality. [ABSTRACT FROM AUTHOR]

• Different visual environments at freeway tunnel entrance zones have varying effects on driver's visual attention, cognitive workload, and subjective mental workload. • The billboard condition attracts the highest level of visual attention from drivers, while the tip slogan condition results in the highest cognitive workload. • Evaluation using the NASA-TLX scale indicates that the tip slogan condition has the greatest impact on drivers' subjective mental workload. This study aims to evaluate the impact of different visual attraction environments at the entrance zone of freeway tunnels on drivers' visual performance and subjective mental workload. Through a naturalistic driving experiment conducted on actual roads, participants experienced various visual attraction environments at the entrance zones of freeway tunnels. The selected visual environments included baseline, landscape-style architecture, tip slogan, and billboard scenarios. Objective visual performance was assessed using eye-tracking devices to collect participants' eye movement data, while subjective mental workload was evaluated through the NASA-TLX measurement reports administered after the driving experiment. The results indicate that the visual attraction environments at the entrance zone of freeway tunnels have significant impacts on drivers' visual attention level, cognitive workload, and subjective mental workload. Under the billboard condition, participants exhibited the longest first fixation duration (FFD) and paid the earliest attention to visual attraction (reflected by participants positioned their initial fixation at the visual attraction farthest from the tunnel entrance zone (DFT)). Additionally, the tip slogan condition resulted in the highest mean fixation duration (MFD), the largest percentage of total fixation duration on the visual attraction (PTFD), and the highest cognitive workload (reflected in maximum pupil diameter (PD)). Billboard at the entrance zone of freeway tunnel had the greatest effect on attracting drivers' visual attention, while tip slogan resulted in the highest cognitive workload on drivers. The results of the subjective mental workload evaluation (NASA-TLX) also indicated that tip slogan had the greatest impact on drivers' subjective mental workload. This study provides valuable insights into the potential impact of different visual attraction environments at the entrance zone of freeway tunnels on drivers' eye-catching effect. The results contribute to both theoretical knowledge and practical applications in the field of transportation safety. [ABSTRACT FROM AUTHOR]

Safe driving depends on drivers' ability to rapidly and accurately process information in varying traffic conditions. The presence of central green landscapes on roads is a key factor in this context. However, there is a gap in current research, which tends to focus on qualitative aspects of landscape design while lacking quantitative data-driven analyses. In this study, we aim to address this gap by investigating the impact of road central greening configuration on the eye movements of young novice drivers, a population particularly sensitive to external environmental changes. Specifically, we explore the influence of central green landscapes on four visual parameters: driver gaze, saccade, blinking, and pupil behavior. Through real vehicle experiments conducted on different road sections, we collected visual feature data to comprehensively analyze the patterns of driver eye movements. Our findings reveal that the introduction of central green landscapes can exert cognitive pressure on drivers, leading to specific alterations in their visual parameters. These changes include dispersed gaze points, reduced effective gaze durations, increased gaze frequencies, extended saccade durations and angles, heightened blink durations and frequencies, and reduced pupil area. By shedding light on the intricate interplay between road central greenery and driver behavior, this study provides valuable insights for optimizing landscape design in transportation planning and enhancing road safety considerations. [ABSTRACT FROM AUTHOR]

In recent years, some expressway tunnels have started broadcasting warning sounds, such as fire alarms, to improve driver attention and traffic safety. However, there is few research on it, and in contrast to previous studies, we have considered different evaluation indices and through field measurement to determine the effectiveness of this practice. The characteristics of three warning sound signals, i.e., fire alarm, dynamic music, and voice command, in a tunnel were analyzed usingMATLAB. Considering pupil diameter and blink duration as evaluation indexes, the change in the mental state of the driver after hearing a warning sound was analyzed. Based on Markov chain theory, the change in the gaze region and gaze shift of the driver under the condition of a warning sound was analyzed. Results shows fire alarms and voice commands can increase the mental load of drivers, but the degree of impact was not determined. Dynamic music does not affect the mental load of the driver. The fire alarm and dynamic music attracted the attention of the driver; conversely, as the voice command warns the driver to focus on safety, it did not impact the attention of the driver. The research results provide a scientific reference for the selection of warning sounds in expressway tunnels and new research ideas for the prevention of traffic injuries in expressway tunnels.

• The driver's PRT was measured according to the visual fixation characteristics (using an eye-tracking device) and vehicle running data. • The PRT was measured in the interchange exit ramps. • These findings should serve as a valuable reference for refining the design of plateau expressway exit ramps and providing a theoretical basis for improving road safety in the plateau areas. The low-pressure (and low-oxygen) environment in plateau regions significantly impacts the driver's perception-reaction time (PRT) and, in turn, road safety. However, drivers faced increased workloads at interchange exit areas while the Tibet region experienced a significant improvement in high-grade highway construction. Therefore, this study aimed to quantitatively analyze the influence of the plateau environment on PRT. Using a UC/win-road simulator, 6 scenarios of expressway exit ramps were constructed. Then, a total of 50 participants (35 males, 15 females) in Nanjing (altitude of 50 m) and 50 participants (36 males, 14 females) in Lhasa (altitude of 3650 m) were recruited for the simulation experiments. The driver's PRT was measured according to the visual fixation characteristics (using an eye-tracking device) and vehicle running data. The no-difference in PRT for various scenarios was validated using the one-way-ANOVA test. Then, the Spearman bivariate correlation and generalized linear regression model were used to analyze the influence of driver's age, driving experience, gender, and acclimation period on PRT. In addition, the difference in PRT of different groups of plain and plateau drivers was further analyzed using the Mann-Whiteney U and Kruskal-Wallis tests. Although driving experience and gender affected the PRT of the plain and plateau drivers, the effect was greater in the plain areas. The low-pressure environment at high altitude had a more significant impact on young novice male drivers. These findings serve as valuable references for refining the design of expressway exit ramps and improving road safety in the plateau areas. [ABSTRACT FROM AUTHOR]

The common disorder, Keratoconus (KC), is distinguished by cumulative corneal slimming and steepening. The corneal ring implantation has become a successful surgical procedure to correct the KC patient’s vision. The determination of suitable patients for the surgery alternative is among the paramount concerns of ophthalmologists. To reduce the burden on them and enhance the treatment, this research aims to previse the ocular condition of KC patients after the corneal ring implantation. It focuses on predicting post-surgical corneal topographic indices and visual characteristics. This study applied an efficacious artificial neural network approach to foretell the aforementioned ocular features of KC subjects 6 and 12 months after implanting KeraRing and MyoRing based on the accumulated data. The datasets are composed of sufficient numbers of corneal topographic maps and visual characteristics recorded from KC patients before and after implanting the rings. The visual characteristics under study are uncorrected visual acuity (UCVA), sphere (SPH), astigmatism (Ast), astigmatism orientation (Axe), and best corrected visual acuity (BCVA). In addition, the statistical data of multiple KC subjects were registered, including three effective indices of corneal topography (i.e., Ast, K-reading, and pachymetry) pre- and post-ring embedding. The outcomes represent the contribution of practical training of the introduced models to the estimation of ocular features of KC subjects following the implantation. The corneal topographic indices and visual characteristics were estimated with mean errors of 7.29% and 8.60%, respectively. Further, the errors of 6.82% and 7.65% were respectively realized for the visual characteristics and corneal topographic indices while assessing the predictions by the leave-one-out cross-validation (LOOCV) procedure. The results confirm the great potential of neural networks to guide ophthalmologists in choosing appropriate surgical candidates and their specific intracorneal rings by predicting post-implantation ocular features.

Considerable evidence suggests that the decline in physiological abilities prevalent in older drivers leads to a reduction in the visual and psychomotor functions required for safe driving. The purpose of this study is to further investigate the differences in driving behavior between older and younger drivers and to describe the change process of driving behavior. In this study, 19 younger and older drivers each were recruited for a driving simulation experiment that included five scenarios. Driving operation data, eye movement data, and physiological data of drivers in five conflict scenarios were collected. The differences in driving behaviors between the two groups were also compared and analyzed, on which the thresholds of different driving behavior nodes were determined and driving behavior graphs were established. The results show that the eye movement nodes of older drivers appear later in five scenarios, the operational nodes of older people appear later in two steering scenarios, and are closer to those of younger drivers in three straight ahead scenarios, indicating that older drivers were later in observing and collecting traffic information, and later in applying brakes and steering to avoid conflicts when steering. The study provides a reference for the analysis of driving behavior and driving safety of older people.

This work proposes an augmented reality serious game (ARSG) for supporting individuals with motor disabilities while controlling robotic wheelchairs. A racing track was used as the game narrative; this included restriction areas, static and dynamic virtual objects, as well as obstacles and signs. To experience the game, a prior configuration of the environment, made through a smartphone or a computer, was required. Furthermore, a visualization tool was developed to exhibit user performance while using the ARSG. Two user studies were conducted with 10 and 20 participants, respectively, to compare (1) how different devices enable configuring the ARSG, and (2) different tracking capabilities, i.e., methods used to place virtual content on the real-world environment while the user interacts with the game and controls the wheelchair in the physical space: C1—motion tracking using cloud anchors; C2—offline motion tracking. Results suggest that configuring the environment with the computer is more efficient and accurate, in contrast to the smartphone, which is characterized as more engaging. In addition, condition C1 stood out as more accurate and robust, while condition C2 appeared to be easier to use. [ABSTRACT FROM AUTHOR]

Augmented Reality (AR) solutions are emerging in multiple scenarios of application as Industry 4.0 takes shape. In particular, for remote collaboration, flexible mechanisms such as authoring tools can be used to generate instructions and assist human operators as they experience increased complexity in their daily tasks. In addition to the traditional handicap of ensuring instructions can be intuitively created without having to understand complicated AR concepts, another relevant topic is the fact that the quality of said instructions is not properly analyzed prior to the tools being evaluated. This means that the characteristics of the visual content are not adequately assessed beforehand. Hence, it is essential to be aware of the cognitive workload associated with AR instructions to assert if they can be easily understood and accepted before being deployed in real-world scenarios. To address this, we focused on AR during sessions of remote guidance. Based on a participatory process with domain experts from the industry sector, a prototype for creating AR-based instructions was developed, and a user study with two parts was conducted: (1) first, a set of step-by-step instructions was produced, and their visual characteristics were evaluated by 129 participants based on a set of relevant dimensions; (2) afterward, these instructions were used by nine participants to understand if they could be used to assist on-site collaborators during real-life remote maintenance tasks. The results suggest that the AR instructions offer low visual complexity and considerable visual impact, clarity, and directed focus, thus improving situational understanding and promoting task resolution. [ABSTRACT FROM AUTHOR]

In order to improve the traffic safety at the entrance and exit of subsea tunnel, the variation law of driver􀆳s visual characteristics under different visual deceleration marking schemes at the entrance and exit of subsea tunnel was studied. Six visual deceleration marking schemes were set up, and the indoor driving simulation experiments were carried out on 26 drivers. The data such as vehicle speed, proportion of view points, pupil diameter and detection distance were collected. Through analyzing and processing the data to judge the effectiveness of visual deceleration marking, the regression models of vehicle speed and driver pupil diameter at the entrance and exit of subsea tunnel were established respectively, and the relationship between them was nonlinear at the entrance of subsea tunnel, the relationship between them was linear at the exit of subsea tunnel. The validity of visual deceleration marking was verified by driver questionnaire. The results show that the six visual deceleration marking schemes at the entrance and exit of subsea tunnel have a significant impact on the driver's visual characteristics. Compared with other marking schemes, the setting of white fishbone deceleration marking has the greatest impact on the driver's pupil diameter, the proportion of view points in area A, the detection distance and illusion influence, which helps the driver actively reduce the speed, take deceleration measures in advance and ensure driving safety. [ABSTRACT FROM AUTHOR]

The head-mounted eye-tracking technology is often used to manipulate the motion of servo platform in remote tasks, so as to achieve visual aiming of servo platform, which is a highly integrated human-computer interaction effect. However, it is difficult to achieve accurate manipulation for the uncertain meanings of gaze points in eye-tracking. To solve this problem, a method of classifying gaze points based on a conditional random field is proposed. It first describes the features of gaze points and gaze images, according to the eye visual characteristic. An LSTM model is then introduced to merge these two features. Afterwards, the merge features are learned by CRF model to obtain the classified gaze points. Finally, the meaning of gaze point is classified for target, in order to accurately manipulate the servo platform. The experimental results show that the proposed method can classify more accurate target gaze points for 100 images, the average evaluation values Precision = 86.81%, Recall = 86.79%, We = 86.79%, these are better than relevant methods. In addition, the isolated gaze points can be eliminated, and the meanings of gaze points can be classified to achieve the accuracy of servo platform visual aiming. [ABSTRACT FROM AUTHOR]

Connected vehicle technology relying on Human Machine Interface (HMI) achieve a dominant position in the overall safety improvement. However, the impact of HMI on the driver's visual attention cannot be ignored, especially on the accident-prone foggy freeway. The objective of this paper is to evaluate the level of distraction caused by HMI in data analysis of drivers' visual characteristics and to establish a generic evaluation methodology. A connected vehicle test platform has been established based on the driving simulator, in which visibility was set to the level of heavy fog and the technical condition was set in two conditions (with or without HMI). Measurement of driving behavior parameters include frequency of fixations and saccades and the proportion of fixation. The researchers compared and analyzed the driver's visual characteristics and the degree of distraction in a combination of indices based on the AttenD algorithm, setting two technical conditions in a heavy fog. Drivers suffering more visual distraction and interference with HMI may have an impact on the driver's driving safety. The results provide a generic approach to evaluate the HMI of a connected vehicle system and a safety assessment methodology for the connected vehicle system. [ABSTRACT FROM AUTHOR]

The lighting design of a road tunnel focuses on the setting of pavement luminance. As for the tunnel sidewall luminance, it simply follows the principle of no less than 60% of the pavement luminance. In fact, the sidewall is one of the important components of the tunnel lighting environment; however, the impact of the improvement of sidewall brightness on the LED lighting environment in a tunnel has not attracted enough attention. In this study, the impact of the improvement of tunnel sidewall brightness on the lighting environment and visual characteristics of human eyes were analyzed based on the lighting experiments when the tunnel sidewalls were decorated with two different types of materials and illuminated by LED lamps with five different color temperatures. The test results show that the tunnel sidewall luminance will increase if the energy-storage and luminescent coating with high reflectance is decorated on tunnel sidewalls, and the pavement luminance increases with the increasing sidewall luminance. After the improvement of the sidewall and pavement luminance, the visible distance for a small object in the tunnel will increase to a certain extent. Furthermore, there is no discomfort for drivers during driving, and the changing of eye pupil diameter is relatively stable, which indicates that the increase in tunnel sidewall luminance has a positive effect on the visual performance of drivers. [ABSTRACT FROM AUTHOR]

Although investigators are using data sources to describe the visual characteristics of streets, few researchers have linked human perceptions of the street environment with human activity density. This study proposes a conceptualized analytical framework that explains the relationship between human activity density and the visual characteristics of the streetscape. The image-segmentation model DeepLabv3+ automatically extracts each pixel's semantic information and classifies visual elements from 120,012 collected panoramic street view images of Zhengzhou, China, using the entropy weighting method and weighted superposition to calculate the street perception summary score. This deep learning approach can successfully describe the semantics of streets and the connection between population density and street perception. The study provides a new quantitative method for urban planning and the development of high-density cities. [ABSTRACT FROM AUTHOR]

Featured Application: The magnetic particle indication characteristics of bearing ring surfaces in the fluorescent magnetic particle inspection and crack detection method based on image processing were investigated, providing a valuable reference for automatic crack detection in magnetic particle inspection. Fluorescent magnetic particle inspection (MPI) is a conventional non-destructive testing process for railway bearing rings that still needs to be completed manually. Due to the complexity of bearing ring surfaces in inspection, automatic detection for bearing rings based on image processing is difficult to apply. Therefore, we proposed a bearing ring defect identification method based on visual characteristics and high-level features. Inspired by the mechanism of human visual perception, defects can be identified from the complex background conveniently by human eyes. According to the linear structure characteristics and greyscale distribution characteristics of cracks in the acquired images, we introduce the centerline extraction and Gaussian similarity measure to reduce background noise and obtain the crack candidate regions. Then, an improved MobileNetV3 is used to extract high-level features of the candidate regions and determine whether they are defective, which uses a new attention module, Coordinate Attention (CA), to substitute the Squeeze-and-Excitation (SE) attention to improve the performance. The experimental results show that the detection accuracy rate of the proposed method is 96.5%. Compared with traditional methods, the proposed method can efficiently extract crack defects in a complex textured background and shows high-quality performance in recall and precision. [ABSTRACT FROM AUTHOR]

Invasive pest fall armyworm (FAW) Spodoptera frugiperda is one of the serious threats to the food safety. Early warning and control plays a key role in FAW management. Nowadays, deep learning technology has been applied to recognize the image of FAW. However, there is a serious lack of training dataset in the current researches, which may mislead the model to learn features unrelated to the key visual characteristics (ring pattern, reniform pattern, etc.) of FAW adults and its close related species. Therefore, this research established a database of 10,177 images belonging to 7 species of noctuid adults, including FAW and 6 FAW close related species. Based on the small-scale dataset, transfer learning was used to build the recognition model of FAW adults by employing three deep learning models (VGG-16, ResNet-50 and DenseNet-121) pretrained on ImageNet. All of the models got more than 98% recognition accuracy on the same testing dataset. Moreover, by using feature visualization techniques, this research visualized the features learned by deep learning models and compared them to the related key visual characteristics recognized by human experts. The results showed that there was a high consistency between the two counterparts, i.e., the average feature recognition rate of ResNet-50 and DenseNet-121 was around 85%, which further demonstrated that it was possible to use the deep learning technology for the real-time monitoring of FAW adults. In addition, this study also found that the learning abilities of key visual characteristics among different models were different even though they have similar recognition accuracy. Herein, we suggest that when evaluating the model capacity, we should not only focus on the recognition rate, the ability of learning individual visual characteristics should be allocated importance for evaluating the model performance. For those important taxonomical traits, if the visualization results indicated that the model didn't learnt them, we should then modify our datasets or adjusting the training strategies to increase the learning ability. In conclusion, this study verified that visualizing the features learnt by the model is a good way to evaluate the learning ability of deep learning models, and to provide a possible way for other researchers in the field who want to understand the features learnt by deep learning models.

To explore the influence of color, texture and glossiness of wood surface visual characteristics on the evaluation of visual perception in different dimensions, and the evaluation difference of people with different gender and professional background on the evaluation of wood surface visual characteristics in different dimensions. The results showed that the characteristics of wood surface visual sensory evaluation of the main sources of color and glossiness, the influence of different color and glossiness of the surface of the wood characteristics brought people visual sensory evaluation of the differences in different dimensions, between designer and consumer characteristics of wood surface visual sensory evaluation is more significant difference. The results of this study provided designers with more detailed references for the evaluation of wood visual perception, and provided them with quantitative data support in the design practice of wood products. At the same time, the feasibility of the evaluation and analysis method of wood visual perception in semantic fractal was verified. [ABSTRACT FROM AUTHOR]

The penetration depth of welding seam can reflect welding quality fundamentally, during the gas metal arc welding (GMAW) process, the penetration depth of welding seam fluctuates over time. At present, it lacks of reliable sensing method to predict penetration depth fluctuation accurately in real time. To solve the above problem, in this paper, proposing a real-time prediction method for weld penetration mode and depth based on two-dimensional visual characteristics of weld pool, establishing a monocular vision sensing system, extracting the area, length and width of weld pool as key two-dimensional visual characteristics. Taking the extracted current frame characteristics of weld pool as the input, the weld penetration of welding seam corresponding to current frame as the output, based on support vector machine (SVM) and back propagation (BP) neural network respectively, the real-time prediction models for weld penetration mode and depth were established. The predicted results show that the established models can accurately predict the penetration mode and penetration depth of welding seam in real time.

Augmented Reality (AR) solutions are emerging in multiple scenarios of application as Industry 4.0 takes shape. In particular, for remote collaboration, flexible mechanisms such as authoring tools can be used to generate instructions and assist human operators as they experience increased complexity in their daily tasks. In addition to the traditional handicap of ensuring instructions can be intuitively created without having to understand complicated AR concepts, another relevant topic is the fact that the quality of said instructions is not properly analyzed prior to the tools being evaluated. This means that the characteristics of the visual content are not adequately assessed beforehand. Hence, it is essential to be aware of the cognitive workload associated with AR instructions to assert if they can be easily understood and accepted before being deployed in real-world scenarios. To address this, we focused on AR during sessions of remote guidance. Based on a participatory process with domain experts from the industry sector, a prototype for creating AR-based instructions was developed, and a user study with two parts was conducted: (1) first, a set of step-by-step instructions was produced, and their visual characteristics were evaluated by 129 participants based on a set of relevant dimensions; (2) afterward, these instructions were used by nine participants to understand if they could be used to assist on-site collaborators during real-life remote maintenance tasks. The results suggest that the AR instructions offer low visual complexity and considerable visual impact, clarity, and directed focus, thus improving situational understanding and promoting task resolution.

In order to explore the efficiency of drivers' visual recognition of traffic signs, an evaluation system of visual recognition efficiency of road signs in scenic spots was constructed. The field eye - tracking experiment was designed and data of drivers' visual recognition of traffic signs in scenic spots were collected. Based on the data variation rule and index characteristics, the optimal value and the critical value of the eye movement characteristic data were analyzed and the evaluation index set of traffic sign recognition efficiency was established. Then, support vector machine - recursive feature elimination was used to rank the significance of evaluation indexes to determine the degree of influence of each evaluation index on the evaluation system. In addition, the calibration index of efficacy coefficient method was adopted to establish the evaluation system of visual recognition efficiency. Finally, the system was used to evaluate the visual recognition in Nanjing Zhongshan Mountain National Park and some suggestions on improvement and optimization of traffic sign setting from the perspective of visual recognition efficiency were proposed. [ABSTRACT FROM AUTHOR]

Copyright of Ege Journal of Fisheries & Aquatic Sciences (EgeJFAS) / Su Ürünleri Dergisi is the property of Ege Journal of Fisheries & Aquatic Sciences (EgeJFAS) / Su Urunleri Dergisi and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The head-mounted eye-tracking technology is often used to manipulate the motion of servo platform in remote tasks, so as to achieve visual aiming of servo platform, which is a highly integrated human-computer interaction effect. However, it is difficult to achieve accurate manipulation for the uncertain meanings of gaze points in eye-tracking. To solve this problem, a method of classifying gaze points based on a conditional random field is proposed. It first describes the features of gaze points and gaze images, according to the eye visual characteristic. An LSTM model is then introduced to merge these two features. Afterwards, the merge features are learned by CRF model to obtain the classified gaze points. Finally, the meaning of gaze point is classified for target, in order to accurately manipulate the servo platform. The experimental results show that the proposed method can classify more accurate target gaze points for 100 images, the average evaluation values Precision = 86.81%, Recall = 86.79%, We = 86.79%, these are better than relevant methods. In addition, the isolated gaze points can be eliminated, and the meanings of gaze points can be classified to achieve the accuracy of servo platform visual aiming.

The lighting design of a road tunnel focuses on the setting of pavement luminance. As for the tunnel sidewall luminance, it simply follows the principle of no less than 60% of the pavement luminance. In fact, the sidewall is one of the important components of the tunnel lighting environment; however, the impact of the improvement of sidewall brightness on the LED lighting environment in a tunnel has not attracted enough attention. In this study, the impact of the improvement of tunnel sidewall brightness on the lighting environment and visual characteristics of human eyes were analyzed based on the lighting experiments when the tunnel sidewalls were decorated with two different types of materials and illuminated by LED lamps with five different color temperatures. The test results show that the tunnel sidewall luminance will increase if the energy-storage and luminescent coating with high reflectance is decorated on tunnel sidewalls, and the pavement luminance increases with the increasing sidewall luminance. After the improvement of the sidewall and pavement luminance, the visible distance for a small object in the tunnel will increase to a certain extent. Furthermore, there is no discomfort for drivers during driving, and the changing of eye pupil diameter is relatively stable, which indicates that the increase in tunnel sidewall luminance has a positive effect on the visual performance of drivers.

In highway traffic, different traffic signs have different influences on the driver's gaze behavior, affecting the safety of drivers and highway driving. To solve this matter, the research based on visual characteristic analysis aims to scientifically evaluate such influences, thereby indirectly reducing the occurrence of highway traffic accidents. Via designing tests to simulate the influence of highway traffic signs on curve highway sections on driver's visual system, our study adopted the eye tracking system as the visual characteristic acquisition device in the test; then this paper used gaze duration, gaze frequency, and average glance speed as the evaluation indicators of gaze behavior to compare the influence of different traffic signs on the gaze behavior and analyze the variation laws. Moreover, to further evaluate the influence of traffic signs on the safe driving behavior of drivers, based on the test results, this paper also gave a qualitative evaluation on the driver's visual load in highway road sections with different traffic signs. The test results in this paper provide scientific suggestions for the layout of highway traffic signs so as to effectively reduce the occurrence of highway traffic accidents, and this study is of important practical significance. [ABSTRACT FROM AUTHOR]

In order to further satisfy the needs of visual perception, a computer image segmentation algorithm based on visual characteristics is proposed. The computer image geometric features are linearly segmented to obtain multiple sub-panels and various geometric features of each sub-panel are extracted. The geometric features are input as low-level features into the deep neural network model to learn to generate high-level features. Finally, based on the high-level features, the clustering center is obtained by Gaussian mixture model, and the final segmentation result is obtained by using graph cut. The results of experiments on Princeton standard data set and COSEG dataset show that the rand index RI value is the best value for each 3D model, which shows that the proposed method is better than the traditional segmentation method. It has good consistent segmentation results. The research showed that using a variety of geometric features compared to a single geometric feature, the obtained features have a more comprehensive geometric meaning, which can effectively make image segmentation meet the visual characteristics requirements. [ABSTRACT FROM AUTHOR]

Although investigators are using data sources to describe the visual characteristics of streets, few researchers have linked human perceptions of the street environment with human activity density. This study proposes a conceptualized analytical framework that explains the relationship between human activity density and the visual characteristics of the streetscape. The image-segmentation model DeepLabv3+ automatically extracts each pixel’s semantic information and classifies visual elements from 120,012 collected panoramic street view images of Zhengzhou, China, using the entropy weighting method and weighted superposition to calculate the street perception summary score. This deep learning approach can successfully describe the semantics of streets and the connection between population density and street perception. The study provides a new quantitative method for urban planning and the development of high-density cities.

Abstract Extracting web content is to obtain the required data embedded in web pages, usually including structured records, such as product information, and text content, such as news. Web pages use a large number of HTML tags to organize and to present various information. Both knowing little about the structures of web pages and mixing kinds of information in web pages are making the extraction process very challenging to guarantee extraction performance and extraction adaptability. This study proposes a unified web content extraction framework that can be applied in various web environments to extract both structured records and text content. First, we construct a characteristic container to hold kinds of characteristics related with extraction objectives, including visual text information, content semantics(instead of HTML tag semantics), web page structures, etc. Second, the above characteristics are integrated into an extraction framework for extraction decisions on different web sites. Especially, we put forward different strategies, path aggregation for extracting text content and HMM model for structured records, to locate the extraction area by exploiting both those extraction characteristics. Comparative experiments on multiple web sites with popular extraction methods, including CETR, CETD and CNBE, show that our proposed extraction method can provide better extraction precision and extraction adaptability.

Introduction: According to previous research, locus of control (LOC) has a crucial role in an individual's psychological well-being. The purpose of this study was 3-fold: (1) comparing LOC of college students with and without visual impairments while controlling for gender, educational level, and age; (2) investigating the relationship between LOC and visual characteristics in college students with visual impairments; and (3) predicting LOC of these students using their visual characteristics. Methods: The design of this study was causal-comparative. The statistical population included a sample of college students with and without visual impairments who were enrolled at the University of Isfahan, Iran. Fifteen of the 20 college students with visual impairments were selected through convenience sampling and amongst sighted students, 15 individuals were selected in a way that they were matched with college students with visual impairment regarding gender, educational level, and age. The Rotter Locus of Control Scale was used to measure LOC. Also, visual impairment characteristics and demographic data were collected. The results were analyzed by t-test and stepwise regression analysis. Results: Results indicated no significant difference between LOC of college students with and without visual impairments (p > .05), and both groups tended to have internal LOC on average. The results indicated that adjustment to visual impairment and the recent status of visual impairment might predict the LOC of a college student who is visually impaired and explained 59.2% of its variance with this sample (p < .005). Discussion: LOC of college students with visual impairments was similar to their sighted counterparts. The better adjusted the person was to his or her visual impairment and the less worsening the status of visual impairment was, the higher internal LOC he or she had. Implications for practitioners: Families and society can help individuals with visual impairments build their internal LOC, by teaching them how to adjust to their disability and providing them the conditions to increase their independence. At the same time, preparing them for entering university may also help them develop their sense of internal LOC. [ABSTRACT FROM AUTHOR]

Fluorescent magnetic particle inspection (MPI) is a conventional non-destructive testing process for railway bearing rings that still needs to be completed manually. Due to the complexity of bearing ring surfaces in inspection, automatic detection for bearing rings based on image processing is difficult to apply. Therefore, we proposed a bearing ring defect identification method based on visual characteristics and high-level features. Inspired by the mechanism of human visual perception, defects can be identified from the complex background conveniently by human eyes. According to the linear structure characteristics and greyscale distribution characteristics of cracks in the acquired images, we introduce the centerline extraction and Gaussian similarity measure to reduce background noise and obtain the crack candidate regions. Then, an improved MobileNetV3 is used to extract high-level features of the candidate regions and determine whether they are defective, which uses a new attention module, Coordinate Attention (CA), to substitute the Squeeze-and-Excitation (SE) attention to improve the performance. The experimental results show that the detection accuracy rate of the proposed method is 96.5%. Compared with traditional methods, the proposed method can efficiently extract crack defects in a complex textured background and shows high-quality performance in recall and precision.

Copyright of Chinese Journal of Applied Ecology / Yingyong Shengtai Xuebao is the property of Chinese Journal of Applied Ecology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Highlights • We examined attitudes and purchase likelihood for visually sub-optimal apples. • Explicit and implicit measures had predictive validity regarding purchase decisions. • An implicit measure was better in predicting when consumers would reject apples. • An explicit measure was better in predicting when consumers would accept apples. Abstract Consumers are faced with daily choices on what foods to buy and eat. Visual characteristics of foods evoke in consumers both positive and negative attitudes, depending on the level of visual optimality or sub-optimality. These attitudes also play a critical role in purchase decision making. In this study we examined the food decision-making process and the extent to which explicit and implicit measures of visual optimality can predict purchase likelihood. In an online study with 608 Swedish consumers, we performed an implicit association test and used a questionnaire to measure consumers' explicit attitudes and purchase likelihood for optimal and sub-optimal apples. We also assessed the temporal stability of purchase likelihood in a re-test performed three weeks after the first test. The results showed that both explicit and implicit measures had predictive validity, but that the explicit measure was better in predicting when consumers would buy apples, while the implicit measure was better in predicting when consumers would reject apples. It was clear that consumers preferred visually optimal apples, but visually sub-optimal apples were not entirely rejected and the purchase likelihood remained stable throughout the experiment. We applied these results to draw up some recommendations on approaches to generate consumer acceptance and adoption of visually sub-optimal food products. [ABSTRACT FROM AUTHOR]

Image quality assessment plays an important role in remote sensing image fusion. Research on objective evaluation methods is of great value in this field. Because the fused images will be observed by human finally, the best objective evaluation index of image quality should be consistent with the subjective evaluation. After the human visual characteristics are introduced into, image quality e-valuation method can get better result. Therefore, based on the multi channels decomposition and contrast sensitivity characteristics of human visual system, this paper proposes a new method to evaluate the fusion quality of panchromatic image and multispectral image. Firstly, the color distortion and structural similarity are modified to evaluate the spectral information and spatial information respectively. Secondly, they are integrated as the overall evaluation of fused image. According to the experiment evaluating quality of different fused images by SPOT image data and GF-2 image data, it proves that the proposed method is in good agreement with the subjective evaluation when the remote sensing image is high resolution data. [ABSTRACT FROM AUTHOR]

Skin cancer is the second most common cancer affecting women younger than 39 years in the USA. As a female-oriented social media, Pinterest could be effectively used in reaching this particular demographic group for the purpose of skin cancer education. We analyze the visual characteristics of skin cancer pins, including use of human image, use of fear-invoking image, pin composition, color, and text legibility. We also explore how these visual characteristics as well as information richness predict Pinterest users' participative engagement. A combination of descriptive and predictive content analysis of 708 pins is conducted. The demographic characteristics of human models are consistent with epidemiology data. Text legibility in bodycopy is low. Information richness is a significant predictor of number of repins in all pins except pins on melanoma with human models. In the case of latter, pin composition, gender of human models, and fear-invoking images were associated with the number of repins. A number of visual characteristics as well as information richness significantly predict Pinterest users' participant engagement with pins on skin cancer. Public health professionals should consider these factors in creating effective prevention messages to be circulated on Pinterest. [ABSTRACT FROM AUTHOR]

This paper proposes a method for obtaining driver’s fixation points and establishing a preview model based on actual vehicle tests. Firstly, eight drivers were recruited to carry out the actual vehicle test on the actual straight and curved roads. The curvature radii of test curved roads were selected to be 200, 800, and 1500 m. Subjects were required to drive at a speed of 50, 70 and 90 km/h, respectively. During the driving process, eye movement data of drivers were collected using a head-mounted eye tracker, and road front scene images and vehicle statuses were collected simultaneously. An image-world coordinate mapping model of the visual information of drivers was constructed by performing an image distortion correction and matching the images from the driving recorder. Then, fixation point data for drivers were accordingly obtained using the Identification-Deviation Threshold (I-DT) algorithm. In addition, the Jarque–Bera test was used to verify the normal distribution characteristics of these data and to fit the distribution parameters of the normal function. Furthermore, the preview points were extracted accordingly and projected into the world coordinate. At last, the preview data obtained under these conditions are fit to build general preview time probability density maps for different driving speeds and road curvatures. This study extracts the preview characteristics of drivers through actual vehicle tests, which provides a visual behavior reference for the humanized vehicle control of an intelligent vehicle.

Extracting web content is to obtain the required data embedded in web pages, usually including structured records, such as product information, and text content, such as news. Web pages use a large number of HTML tags to organize and to present various information. Both knowing little about the structures of web pages and mixing kinds of information in web pages are making the extraction process very challenging to guarantee extraction performance and extraction adaptability. This study proposes a unified web content extraction framework that can be applied in various web environments to extract both structured records and text content. First, we construct a characteristic container to hold kinds of characteristics related with extraction objectives, including visual text information, content semantics(instead of HTML tag semantics), web page structures, etc. Second, the above characteristics are integrated into an extraction framework for extraction decisions on different web sites. Especially, we put forward different strategies, path aggregation for extracting text content and HMM model for structured records, to locate the extraction area by exploiting both those extraction characteristics. Comparative experiments on multiple web sites with popular extraction methods, including CETR, CETD and CNBE, show that our proposed extraction method can provide better extraction precision and extraction adaptability. [ABSTRACT FROM AUTHOR]