Visual recognition for urban traffic data retrieval and analysis in major events using convolutional neural networks

Accurate and prompt traffic data are necessary for the successful management of major events. Computer vision techniques, such as convolutional neural network (CNN) applied on video monitoring data, can provide a cost-efficient and timely alternative to traditional data collection and analysis methods. This paper presents a framework designed to take videos as input and output traffic volume counts and intersection turning patterns. This framework comprises a CNN model and an object tracking algorithm to detect and track vehicles in the camera’s pixel view first. Homographic projection then maps vehicle spatial-temporal information (including unique ID, location, and timestamp) onto an orthogonal real-scale map, from which the traffic counts and turns are computed. Several video data are manually labeled and compared with the framework output. The following results show a robust traffic volume count accuracy up to 96.91%. Moreover, this work investigates the performance influencing factors including lighting condition (over a 24-h-period), pixel size, and camera angle. Based on the analysis, it is suggested to place cameras such that detection pixel size is above 2343 and the view angle is below 22°, for more accurate counts. Next, previous and current traffic reports after Texas A&M home football games are compared with the framework output. Results suggest that the proposed framework is able to reproduce traffic volume change trends for different traffic directions. Lastly, this work also contributes a new intersection turning pattern, i.e., counts for each ingress-egress edge pair, with its optimization technique which result in an accuracy between 43% and 72%.

Changes in Electroencephalographic Results and Heart Rate Variability after Exposure to Green Landscape Photographs Correlated with Color Temperature and Illumination Level

Background and objective: Various images from visual display terminals (VDTs) as well as living lighting are important parts of our daily life; thus, properly controlling the lighting environment – that is, illuminance, color temperature and good images from VDTs – can have a substantial effect on improving the mental health and work efficiency in everyday life. We examined electroencephalography (EEG) and heart rate variability (HRV) responses to various lighting conditions in 25 university students as they viewed images of a green landscape or traffic congestion.Methods: EEG was performed in darkness and when the room was illuminated with 10 different light-emitting diode (LED) color temperatures, while the EEG and HRV responses to green landscape or traffic congestion image stimuli were measured in darkness and during room illumination with three different LED color temperatures.Results: We found a significant difference between darkness and high LED illumination (400 lx) at 7 (CZ, F4, FZ, O1, O2, OZ, and T6) of 30 channels, while the alpha wave activity increased during darkness. In the second experiment, the green landscape image stimuli in the 30 lx–2600 K lighting condition elicited theta wave activity on the EEG, whereas the traffic congestion image stimuli under high LED illumination elicited high beta and gamma wave activities. Moreover, the subjects exhibited better stress coping ability and heart rate stability in response to green landscape image stimuli under illuminated conditions, according to their HRV.Conclusion: These results suggest that lower color temperatures and illumination levels alleviate tension, and that viewing green landscape image stimuli at low illumination, or in darkness, is effective for reducing stress. Conversely, high illumination levels and color temperatures are likely to increase tension and stress in response to traffic congestion image stimuli.

Effect of Ambient Lighting on Frequency Dependence in Transcranial Electrical Stimulation-Induced Phosphenes

Inconsistencies have been found in the relationship between ambient lighting conditions and frequency-dependence in transcranial electric current stimulation (tECS) induced phosphenes. Using a within-subjects design across lighting condition (dark, mesopic [dim], photopic [bright]) and tECS stimulation frequency (10, 13, 16, 18, 20 Hz), this study determined phosphene detection thresholds in 24 subjects receiving tECS using an FPz-Cz montage. Minima phosphene thresholds were found at 16 Hz in mesopic, 10 Hz in dark and 20 Hz in photopic lighting conditions, with these thresholds being substantially lower for mesopic than both dark (60% reduction) and photopic (56% reduction), conditions. Further, whereas the phosphene threshold-stimulation frequency relation was linear in the dark (increasing with frequency) and photopic (decreasing with frequency) conditions, a quadratic function was found for the mesopic condition (where it followed the linear increase of the dark condition from 10-16 Hz, and the linear decrease of the photopic condition from 16-20 Hz). The results clearly demonstrate that ambient lighting is an important factor in the detection of tECS-induced phosphenes, and that mesopic conditions are most suitable for obtaining overall phosphene thresholds.

Lighting the Patient Room of the Future: Evaluating Different Lighting Conditions From the Patient Perspective

Objective: This study explores whether “future” lighting systems that provide greater control and opportunity for circadian synchronization are acceptable to participants in the role of patients. Background: Tunable, dimmable light emitting diode systems provide multiple potential benefits for healthcare. They can provide significant energy savings, support circadian synchronization by varying the spectrum and intensity of light over the course of the day, address nighttime navigation needs, and provide user-friendly control. There is an emerging understanding of the important visual and nonvisual effects of light; however, important questions remain about the experience and acceptability of this “future” lighting if we are to adopt it broadly. Methods: Volunteer participants (34) performed a series of tasks typical of patients, such as reading or watching a video, in a full-scale simulated inpatient room. Each participant conducted these tasks under 12 lighting conditions in a counterbalanced order that included varying illuminance levels, correlated color temperatures (CCTs), and in a few conditions, saturated colors. The participants rated each lighting condition on comfort, intensity, appropriateness, and naturalness. Results and Conclusions: The participants found that conditions with CCTs of 5,000 K and higher were significantly less comfortable and less natural than conditions with lower CCTs. Conditions with lighting distributed in multiple zones in the patient room were viewed more favorably than a traditional overbed configuration. The participants in this simulated patient study reacted negatively to colored lighting on the footwall of the room but found a mixture of warmer and cooler luminaire CCTs acceptable.

Use of Real-Time Traffic and Signal Timing Data in Modeling Occupant Injury Severity at Signalized Intersections

This study explored the use of real-time traffic events and signal timing data to determine the factors influencing the injury severity of vehicle occupants at intersections. The analysis was based on 3 years (2017–2019) of crash and high-resolution traffic data. The best fit regression was first identified by comparing the conventional regression model and logistic models with random effect. The logistic model with a heavy-tailed distribution random effect best fitted the data set, and it was used in the variable assessment. The model results revealed that about 13.6% of the unobserved heterogeneity comes from site-specific variations, which underlines the need to use the logistic model with a random effect. Among the real-time traffic events and signal-based variables, approach delay and platoon ratio significantly influenced the injury severity of vehicle occupants at 90% Bayesian credible interval. Additionally, the manner of a collision, occupant seat position, number of vehicles involved in a crash, gender, age, lighting condition, and day of the week significantly affected the vehicle occupant injury. The study findings are anticipated to provide valuable insights to transportation agencies for developing countermeasures to mitigate the crash severity risk proactively.

Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement

We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. While the input image can be of a smiling person or taken in extreme lighting conditions, our method can reliably produce a high-quality textured model of a person's face in neutral expression and skin textures under diffuse lighting condition. Cutting-edge 3D face reconstruction methods use non-linear morphable face models combined with GAN-based decoders to capture the likeness and details of a person but fail to produce neutral head models with unshaded albedo textures which is critical for creating relightable and animation-friendly avatars for integration in virtual environments. The key challenges for existing methods to work is the lack of training and ground truth data containing normalized 3D faces. We propose a two-stage approach to address this problem. First, we adopt a highly robust normalized 3D face generator by embedding a non-linear morphable face model into a StyleGAN2 network. This allows us to generate detailed but normalized facial assets. This inference is then followed by a perceptual refinement step that uses the generated assets as regularization to cope with the limited available training samples of normalized faces. We further introduce a Normalized Face Dataset, which consists of a combination photogrammetry scans, carefully selected photographs, and generated fake people with neutral expressions in diffuse lighting conditions. While our prepared dataset contains two orders of magnitude less subjects than cutting edge GAN-based 3D facial reconstruction methods, we show that it is possible to produce high-quality normalized face models for very challenging unconstrained input images, and demonstrate superior performance to the current state-of-the-art.

Development of models to study traffic accidents on the final sections of access roads to the cities: a case study of three major Iranian cities

The final sections of main access roads to the cities require especial attention as the frequency of accidents in these road sections are considerably higher than other parts of interurban roads. These road sections operate as an interface between the rural roads and urban streets. The previous researches available on this subject are limited and they have also mainly focused on a narrow range of factors contributing to the accidents in these areas. The main contribution of this research is to consider a relatively comprehensive range of potential factors , and to examine their impacts through the development and comparison of both conventional probabilistic models and Artificial Neural Network (ANN) models. For this purpose, information related to the main access roads of three major Iranian cities were collected. This information consisted of accident frequency data together with the field observations of traffic characteristics, road-way conditions and roadside features of these roads. Various ANN and probabilistic models were developed. The frequency of accidents, i.e. fatal, injured, or damaged accidents, was considered as the output of the developed models. The results indicated that a hybrid of ANN models, each comprised of 10 input variables representing traffic, roadway and roadside conditions, outperformed several probabilistic models, i.e. Poisson, Negative binomial, Zero-truncated Poisson, and Zero-truncated Negative Binomial models, also developed under similar conditions in this study. Moreo-ver, effective roadway width, roadway lighting condition, the standard deviation of vehicles speed, percentage of drivers violating the speed limit, average annual daily traffic, percentage of heavy goods vehicles, the density of road-side commercial and industrial landuses, the density of median U-turns, the density of local access roads, and the effective width of the left-side shoulder were identified as the most effective factors contributing to the accidents in these areas. The developed ANN model can be used as a tool to predict accident rates in these road sections, and to estimate a potential reduction in the accident rates, following any improvements in the major factors contributing to the traffic accidents in these areas.

A Novel Adversarial Relighting via Face Recognition

Deep facial recognition (FR) has reached very high accuracy on various demanding datasets and encourages successful real-world applications, even demonstrating strong tolerance to illumination change, which is commonly viewed as a major danger to FR systems. In the real world, however, illumination variance produced by a variety of lighting situations cannot be adequately captured by the limited facsimile. To this end, we first propose the physical model- based adversarial relighting attack (ARA) denoted as albedo- quotient-based adversarial relighting attack (AQ-ARA). It generates natural adversarial light under the physical lighting model and guidance of FR systems and synthesizes adversarially relighted face images. Moreover, we propose the auto-predictive adversarial relighting attack (AP-ARA) by training an adversarial relighting network (ARNet) to automatically predict the adversarial light in a one-step manner according to different input faces, allowing efficiency-sensitive applications . More importantly, we propose to transfer the above digital attacks to physical ARA (Phy- ARA) through a precise relighting device, making the estimated adversarial lighting condition reproducible in the real world. We validate our methods on three state-of-the-art deep FR methods, i.e., FaceNet, ArcFace, and CosFace, on two public datasets. The extensive and insightful results demonstrate our work can generate realistic adversarial relighted face images fooling FR easily, revealing the threat of specific light directions and strengths.

The Influence of Physical Environmental Factors on Older Adults in Residential Care Facilities in Northeast China

Objectives: To evaluate the aspects of the objective physical environments of five residential care facilities (RCFs) for older adults and the residents’ subjective perceptions of these aspects. Background: The physical environment in RCFs impacts the health and comfort of the residents. However, the design standards for RCFs lack details which can result in insufficient living conditions. Methods: Through questionnaire surveys, older adults’ satisfaction on the degree of the light, acoustic, and thermal environment in the facilities was obtained. Indoor lighting condition was measured by an illuminance meter in lux, sound pressure level (SPL) with sound level meters in dBA, and temperature in °C with a temperature data logger, and an audiometer was used to test the hearing of the older adults. Results: A total of 480 questionnaires were obtained. Results show that (a) older adults need an appropriate light environment to avoid the negative impact of limited light, (b) poor acoustic environment could affect their mood and health, and (c) when the room temperature is within the range of 20–26 °C (68–78.8 °F), they feel most comfortable. When the appropriate temperature and humidity, balanced illumination, and SPL meet the needs of older adults, it can provide a more comfortable physical environment for them. Conclusion: Examining the interaction between the physical environmental factors that affect older adults in RCFs is important for the design of residential housing and provides more theoretical support for research on the influence of the physical environment on the quality of life of older adults.

Analysis of Bicycle-Motor Vehicle Crashes in San Antonio, Texas

Bicycling is inexpensive, environmentally friendly, and healthful; however, bicyclist safety is a rising concern. This study investigates bicycle crash-related key variables that might substantially differ in terms of the party at fault and bicycle facility presence. Employing 5 year (2014–2018) data from the Texas Crash Record and Information System database, the effect of these variables on bicyclist injury severity was assessed for San Antonio, Texas, using bivariate analysis and binary logistic regression. Severe injury risk based on the party at fault and bicycle facility presence varied significantly for different crash-related variables. The strongest predictors of severe bicycle injury include bicyclist age and ethnicity, lighting condition, road class, time of occurrence, and period of week. Driver inattention and disregard of stop sign/light were the primary contributing factors to bicycle-vehicle crashes. Crash density heatmap and hotspot analyses were used to identify high-risk locations. The downtown area experienced the highest crash density, while severity hotspots were located at intersections outside of the downtown area. This study recommends the introduction of more dedicated/protected bicycle lanes, separation of bicycle lanes from the roadway, mandatory helmet use ordinance, reduction in speed limit, prioritization of resources at high-risk locations, and implementation of bike-activated signal detection at signalized intersections.