Enhancing the Performance of Vehicle Passenger Detection under Adverse Weather Conditions Using Augmented Reality-Based Machine Learning Approach

2021 ◽  
pp. 036119812110312
Author(s):  
Jaeyun Lee ◽  
Sangcheol Kang ◽  
Jaedeok Lim ◽  
Seong Geon Kim ◽  
Changmo Kim
Keyword(s):  
Augmented Reality ◽  
Traffic Congestion ◽  
Learning Algorithm ◽  
Weather Conditions ◽  
Training Data ◽  
Weather Data ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Adverse Weather Conditions ◽  
Adverse Weather

In response to extreme traffic congestion in metropolitan areas that causes unnecessarily long travel times, high fuel consumption, and excessive greenhouse gas emissions, transportation agencies have implemented various strategies to mitigate traffic congestion. Managed lanes—one of the measures applied worldwide—provide benefits to road users and operating agencies by integrating advanced technologies such as electronic and dynamic tolling systems. However, those agencies already implementing or considering implementing the managed lane strategy are seeking a solution to effectively and properly charge toll rates based on vehicle occupancy and penalize violating vehicles. Vehicle passenger detection systems (VPDSs) have been developed and evaluated worldwide, but limitations still inhibit their full implementation. This study confirms that the performance of the deep learning algorithm, a core VPDS technology, declines under certain adverse weather conditions because of lack of training data sets. The performance of the “you only look once” (YOLOv3) model trained with a normal weather data set decreased by as much as 8.5% when it was tested for adverse weather conditions. In this study, augmented reality (AR) models are developed to enhance the accuracy of vehicle passenger detection (VPDA) by the VPDS by training the algorithm with AR images representing virtual adverse weather conditions. Models trained with AR image sets of various weather categories (fog, rain, and snow) attained VPDA enhanced by up to 7.9%. The final model significantly improves VPDA under adverse weather conditions. The proposed models could be considered for implementation with road weather information systems under adverse weather conditions.

scholarly journals Seasonal changes in gravity wave activity measured by lidars at mid-latitudes

2008 ◽  
Vol 8 (22) ◽  
pp. 6775-6787 ◽  
Author(s):  
M. Rauthe ◽  
M. Gerding ◽  
F.-J. Lübken
Keyword(s):  
Gravity Wave ◽  
Gravity Waves ◽  
Low Frequency ◽  
Weather Conditions ◽  
Wave Activity ◽  
Data Set ◽  
Atmospheric Physics ◽  
Adverse Weather Conditions ◽  
Comprehensive Information ◽  
Adverse Weather

Abstract. More than 230 nights of temperature measurements between 1 and 105 km have been performed at the Leibniz-Institute of Atmospheric Physics in Kühlungsborn with a combination of two different lidars, i.e. a Rayleigh-Mie-Raman lidar and a potassium lidar. About 1700 h of measurements have been collected between 2002 and 2006. Apart from some gaps due to the adverse weather conditions the measurements are well distributed throughout the year. Comprehensive information about the activity of medium- and low-frequency gravity waves was extracted from this data set. The dominating vertical wavelengths found are between 10 and 20 km and do not show any seasonal variation. In contrast the temperature fluctuations due to gravity waves experience a clear annual cycle with a maximum in winter. The most significant differences exist around 60 km where the fluctuations in winter are more than two times larger than they are in summer. Only small seasonal differences are observed above 90 km and below 35 km. Generally, the fluctuations grow from about 0.5 K up to 8 K between 20 and 100 km. Damping of waves is observed at nearly all altitudes and in all seasons. The planetary wave activity shows a similar structure in altitude and season as the gravity wave activity which indicates that similar mechanisms influencing different scales. Combining the monthly mean temperatures and the fluctuations we show that the transition between winter and summer season and vice versa seems to start in the mesopause region and to penetrate downward.

scholarly journals Seasonal changes in gravity wave activity measured by lidars at mid-latitudes

2008 ◽  
Vol 8 (4) ◽  
pp. 13741-13773 ◽  
Author(s):  
M. Rauthe ◽  
M. Gerding ◽  
F.-J. Lübken
Keyword(s):  
Gravity Wave ◽  
Gravity Waves ◽  
Low Frequency ◽  
Weather Conditions ◽  
Wave Activity ◽  
Data Set ◽  
Atmospheric Physics ◽  
Adverse Weather Conditions ◽  
Comprehensive Information ◽  
Adverse Weather

Abstract. More than 230 nights of temperature measurements between 1 and 105 km have been performed at the Leibniz-Institute of Atmospheric Physics in Kühlungsborn with a combination of two different lidars, i.e. a Rayleigh-Mie-Raman lidar and a potassium lidar. About 1700 h of measurements have been collected between 2002 and 2006. Apart from some gaps due to the adverse weather conditions the measurements are well distributed throughout the year. Comprehensive information about the activity of medium- and low-frequency gravity waves was extracted from this data set. The dominating vertical wavelengths found are between 10 and 20 km and do not show any seasonal variation. In contrast the temperature fluctuations due to gravity waves experience a clear annual cycle with a maximum in winter. The most significant differences exist around 60 km where the fluctuations in winter are more than two times larger than they are in summer. Only small seasonal differences are observed above 90 km and below 35 km. Generally, the fluctuations grow from about 0.5 K up to 8 K between 20 and 100 km. Damping of waves is observed at nearly all altitudes and in all seasons. The planetary wave activity shows a similar structure in altitude and season as the gravity wave activity which indicates a strong coupling between the processes of the different scales. Combining the monthly mean temperatures and the fluctuations we show that the transition between winter and summer season and vice versa seems to start in the mesopause region and to penetrate downward.

Development of a Biologically-Based System for Detection and Tracking of Airborne Herbicides

1993 ◽  
Vol 7 (2) ◽  
pp. 404-410 ◽  
Author(s):  
Kassim Al-Khatib ◽  
Gaylord I. Mink ◽  
Guy Reisenauer ◽  
Robert Parker ◽  
Halvor Westberg ◽  
...  
Keyword(s):  
Computer Model ◽  
High Sensitivity ◽  
Weather Conditions ◽  
Weather Data ◽  
Indicator Plant ◽  
Field Exposure ◽  
Detection And Tracking ◽  
Adverse Weather Conditions ◽  
Adverse Weather ◽  
Herbicide Drift

This study was designed to develop a protocol for using a biologically-based system to detect and tract airborne herbicides. Common bean, lentil, and pea were selected for their quasi-diagnostic sensitivity to chlorsulfuron, thifensulfuron, metsulfuron, tribenuron, paraquat, glyphosate, bromoxynil, 2,4-D, and dicamba. Plants were grown in the greenhouse at Prosser, WA, and placed at 25 exposure sites at weekly intervals between Apr. 2 and Oct. 15, 1991. After 1 wk of field exposure plants were brought back and observed for herbicide symptoms over a 28-d period. Symptoms that developed were compared with symptoms caused by disease, insects, adverse weather conditions, and herbicides applied at different rates under controlled conditions on these species. In addition, if herbicide symptoms were observed, herbicide spray records and weather data in the area were used in a computer model to determine the source of potential herbicide drift. This study demonstrates that indicator plant species selected for high sensitivity to herbicides can be used to monitor the occurrence of herbicide movement.

scholarly journals Tomographic reconstruction with a generative adversarial network

2020 ◽  
Vol 27 (2) ◽  
pp. 486-493 ◽  
Author(s):  
Xiaogang Yang ◽  
Maik Kahnt ◽  
Dennis Brückner ◽  
Andreas Schropp ◽  
Yakub Fam ◽  
...  
Keyword(s):  
Phase Retrieval ◽  
Learning Algorithm ◽  
Tomographic Reconstruction ◽  
Training Data ◽  
Training Procedure ◽  
Contrast Imaging ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Deep Learning Algorithm

This paper presents a deep learning algorithm for tomographic reconstruction (GANrec). The algorithm uses a generative adversarial network (GAN) to solve the inverse of the Radon transform directly. It works for independent sinograms without additional training steps. The GAN has been developed to fit the input sinogram with the model sinogram generated from the predicted reconstruction. Good quality reconstructions can be obtained during the minimization of the fitting errors. The reconstruction is a self-training procedure based on the physics model, instead of on training data. The algorithm showed significant improvements in the reconstruction accuracy, especially for missing-wedge tomography acquired at less than 180° rotational range. It was also validated by reconstructing a missing-wedge X-ray ptychographic tomography (PXCT) data set of a macroporous zeolite particle, for which only 51 projections over 70° could be collected. The GANrec recovered the 3D pore structure with reasonable quality for further analysis. This reconstruction concept can work universally for most of the ill-posed inverse problems if the forward model is well defined, such as phase retrieval of in-line phase-contrast imaging.

scholarly journals Pill Detection Model for Medicine Inspection Based on Deep Learning

Chemosensors ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 4
Author(s):  
Hyuk-Ju Kwon ◽  
Hwi-Gang Kim ◽  
Sung-Hak Lee
Keyword(s):  
Deep Learning ◽  
Human Error ◽  
Learning Algorithm ◽  
Expansion Method ◽  
Training Data ◽  
Data Set ◽  
Learning Stage ◽  
Detection Model ◽  
Deep Learning Algorithm ◽  
Single Pill

This paper proposes a deep learning algorithm that can improve pill identification performance using limited training data. In general, when individual pills are detected in multiple pill images, the algorithm uses multiple pill images from the learning stage. However, when there is an increase in the number of pill types to be identified, the pill combinations in an image increase exponentially. To detect individual pills in an image that contains multiple pills, we first propose an effective database expansion method for a single pill. Then, the expanded training data are used to improve the detection performance. Our proposed method shows higher performance improvement than the existing algorithms despite the limited imaging and data set size. Our proposed method will help minimize problems, such as loss of productivity and human error, which occur while inspecting dispensed pills.

Impact of weather conditions on airport arrival delay and throughput

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Álvaro Rodríguez-Sanz ◽  
Javier Cano ◽  
Beatriz Rubio Fernández
Keyword(s):  
Decision Making ◽  
Weather Conditions ◽  
Weather Data ◽  
Arrival Process ◽  
Data Set ◽  
Content Type ◽  
Weather Events ◽  
Adverse Weather ◽  
Arrival Processes ◽  
The Impact

Purpose Weather events have a significant impact on airport arrival performance and may cause delays in operations and/or constraints in airport capacity. In Europe, almost half of all regulated airport traffic delay is due to adverse weather conditions. Moreover, the closer airports operate to their maximum capacity, the more severe is the impact of a capacity loss due to external events such as weather. Various weather uncertainties occurring during airport operations can significantly delay some arrival processes and cause network-wide effects on the overall air traffic management (ATM) system. Quantifying the impact of weather is, therefore, a key feature to improve the decision-making process that enhances airport performance. It would allow airport operators to identify the relevant weather information needed, and help them decide on the appropriate actions to mitigate the consequences of adverse weather events. Therefore, this research aims to understand and quantify the impact of weather conditions on airport arrival processes, so it can be properly predicted and managed. Design/methodology/approach This study presents a methodology to evaluate the impact of adverse weather events on airport arrival performance (delay and throughput) and to define operational thresholds for significant weather conditions. This study uses a Bayesian Network approach to relate weather data from meteorological reports and airport arrival performance data with scheduled and actual movements, as well as arrival delays. This allows us to understand the relationships between weather phenomena and their impacts on arrival delay and throughput. The proposed model also provides us with the values of the explanatory variables (weather events) that lead to certain operational thresholds in the target variables (arrival delay and throughput). This study then presents a quantification of the airport performance with regard to an aggregated weather-performance metric. Specific weather phenomena are categorized through a synthetic index, which aims to quantify weather conditions at a given airport, based on aviation routine meteorological reports. This helps us to manage uncertainty at airport arrival operations by relating index levels with airport performance results. Findings The results are computed from a data set of over 750,000 flights on a major European hub and from local weather data during the period 2015–2018. This study combines delay and capacity metrics at different airport operational stages for the arrival process (final approach, taxi-in and in-block). Therefore, the spatial boundary of this study is not only the airport but also its surrounding airspace, to take both the arrival sequencing and metering area and potential holding patterns into consideration. Originality/value This study introduces a new approach for modeling causal relationships between airport arrival performance indicators and meteorological events, which can be used to quantify the impact of weather in airport arrival conditions, predict the evolution of airport operational scenarios and support airport decision-making processes.

scholarly journals Application of Kalman Filter to Improve 3D LiDAR Signals of Autonomous Vehicles in Adverse Weather

2021 ◽  
Vol 11 (7) ◽  
pp. 3018
Author(s):  
Shih-Lin Lin ◽  
Bing-Han Wu
Keyword(s):  
Kalman Filter ◽  
Autonomous Vehicles ◽  
Traffic Accidents ◽  
Autonomous Vehicle ◽  
Weather Conditions ◽  
Weather Data ◽  
Stereo Images ◽  
Adverse Weather Conditions ◽  
Adverse Weather ◽  
On The Road

A worldwide increase in the number of vehicles on the road has led to an increase in the frequency of serious traffic accidents, causing loss of life and property. Autonomous vehicles could be part of the solution, but their safe operation is dependent on the onboard LiDAR (light detection and ranging) systems used for the detection of the environment outside the vehicle. Unfortunately, problems with the application of LiDAR in autonomous vehicles remain, for example, the weakening of the echo detection capability in adverse weather conditions. The signal is also affected, even drowned out, by sensory noise outside the vehicles, and the problem can become so severe that the autonomous vehicle cannot move. Clearly, the accuracy of the stereo images sensed by the LiDAR must be improved. In this study, we developed a method to improve the acquisition of LiDAR data in adverse weather by using a combination of a Kalman filter and nearby point cloud denoising. The overall LiDAR framework was tested in experiments in a space 2 m in length and width and 0.6 m high. Normal weather and three kinds of adverse weather conditions (rain, thick smoke, and rain and thick smoke) were simulated. The results show that this system can be used to recover normal weather data from data measured by LiDAR even in adverse weather conditions. The results showed an effective improvement of 10% to 30% in the LiDAR stereo images. This method can be developed and widely applied in the future.

scholarly journals HIGH-THROUGHPUT DEEP LEARNING ALGORITHM FOR DIAGNOSIS AND DEFECTS CLASSIFICATION OF WATERPROOFING MEMBRANES

2020 ◽  
Vol 16 (2) ◽  
pp. 26-38
Author(s):  
Darya Filatova ◽  
Charles El-Nouty ◽  
Uladzislau Punko
Keyword(s):  
Deep Learning ◽  
Building Materials ◽  
Learning Algorithm ◽  
Membrane Surface ◽  
Training Data ◽  
Water Repellent ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Defects Classification

The work is devoted to the development of a high-performance deep learning algorithm related to the diagnosis and classification of defects of water-repellent membranes. The mechanism of constructing visual models of the membrane surface is discussed. This allows to get the representative training data set. The proposed methodology consists in the sequent transformations of pixel-image intensities to find defected fragments on the membrane's surface. The computational algorithm is based on the architecture of convolution neural networks. To assess its effectiveness, the "confidence of confidence" criterion is proposed. The presented computations show that the methodology can be successfully applied in material sciences, for example, to study the properties of building materials, or in forensic science when examining the causes of construction catastrophes.

Music Emotion Recognition

2021 ◽  
Author(s):  
tejaswini kambaiahgari ◽  
Uma Rao K
Keyword(s):  
Deep Learning ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Ann Model ◽  
K Nearest Neighbor ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Present World

Abstract In the present world, there are many songs over the internet. But the information retrieval on these songs can be complicated. This paper intends to classify songs based on emotions using deep learning. We propose a strategy to recognize the emotion present in a song by classifying their spectrograms, which contains both time and frequency information. According to human psychology, neurons within a sub pop- ulation of our brain did not react the same way for all the emotions.So only specific neurons need to be triggered for identifying an emotion. Dif- ferent deep learning and machine learning algorithms are implemented to build music emotion recognizer. The main objective of this study is to study about the features which are important for audio file ,to de- velop a music emotion classifier using deep learning algorithm and also to validate the model.The datasets are split into training and testing sets, models are trained with training data set. The accuracy of Artifi- cial Neural Network (ANN) model is 79.7% ,K-Nearest Neighbor (KNN) model is 78.26% and logistic regression for gender classification is 81%.

Sign in / Sign up

Export Citation Format

Share Document