Evaluation of pollutants dispersion in an urban traffic scenario in Medellín

2018 ◽  
Author(s):  
C.A. Gómez-Pérez ◽  
J. Espinosa
Keyword(s):  
Urban Traffic ◽  
Traffic Scenario ◽  
Pollutants Dispersion

scholarly journals Vision-Based Bicycle Detection Using Multiscale Block Local Binary Pattern

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Hongyu Hu ◽  
Pengfei Tao ◽  
Zhenhai Gao ◽  
Qingnian Wang ◽  
Zhihui Li ◽  
...  
Keyword(s):  
Traffic Control ◽  
Local Binary Pattern ◽  
Detection Algorithm ◽  
Urban Traffic ◽  
Test Scenario ◽  
Adaboost Algorithm ◽  
Computation Efficiency ◽  
Traffic Scenario ◽  
Control And Management ◽  
Urban Traffic Control

Bicycle traffic has heavy proportion among all travel modes in some developing countries, which is crucial for urban traffic control and management as well as facility design. This paper proposes a real-time multiple bicycle detection algorithm based on video. At first, an effective feature called multiscale block local binary pattern (MBLBP) is extracted for representing the moving object, which is a well-classified feature to distinguish between bicycles and nonbicycles; then, a cascaded bicycle classifier trained by AdaBoost algorithm is proposed, which has a good computation efficiency. Finally, the method is tested with video sequence captured from the real-world traffic scenario. The bicycles in the test scenario are successfully detected.

scholarly journals Efficient Video-Based Vehicle Queue Length Estimation Using Computer Vision and Deep Learning for an Urban Traffic Scenario

Processes ◽  
2021 ◽  
Vol 9 (10) ◽  
pp. 1786
Author(s):  
Muhammad Umair ◽  
Muhammad Umar Farooq ◽  
Rana Hammad Raza ◽  
Qian Chen ◽  
Baher Abdulhai
Keyword(s):  
Traffic Engineering ◽  
Queue Length ◽  
Urban Traffic ◽  
Fine Tuning ◽  
Low Resolution ◽  
Vehicle Class ◽  
Traffic Lane ◽  
Length Estimation ◽  
Traffic Scenario ◽  
Queue Lengths

In the traffic engineering realm, queue length estimation is considered one of the most critical challenges in the Intelligent Transportation System (ITS). Queue lengths are important for determining traffic capacity and quality, such that the risk for blockage in any traffic lane could be minimized. The Vision-based sensors show huge potentials compared to fixed or moving sensors as they offer flexibility for data acquisition due to large-scale deployment at a huge pace. Compared to others, these sensors offer low installation/maintenance costs and also help with other traffic surveillance related tasks. In this research, a CNN-based approach for estimation of vehicle queue length in an urban traffic scenario using low-resolution traffic videos is proposed. The system calculates queue length without the knowledge of any camera parameter or onsite calibration information. The estimation in terms of the number of cars is considered a priority as compared to queue length in the number of meters since the vehicular delay is the number of waiting cars times the wait time. Therefore, this research estimates queue length based on total vehicle count. However, length in meters is also provided by approximating average vehicle size as 5 m. The CNN-based approach helps with accurate tracking of vehicles’ positions and computing queue lengths without the need for installation of any roadside or in-vehicle sensors. Using a pre-trained 80-classes YOLOv4 model, an overall accuracy of 73% and 88% was achieved for vehicle-based and pixel-based queue length estimation. After further fine-tuning of model on the low-resolution traffic images and narrowing down the output classes to vehicle class only, an average accuracy of 83% and 93%, respectively, was achieved which shows the efficiency and robustness of the proposed approach.

scholarly journals Urban Traffic Network Sustainability of One-Way and Two-Way Streets: A Case Study in Downtown Brickfields, Kuala Lumpur

2021 ◽  
Author(s):  
Yong Han Chow ◽  
Quan Ying Tan ◽  
Mohammad A. S. Bhuiyan ◽  
Burra V. D. Kumar ◽  
Mamun Bin Ibne Reaz ◽  
...  
Keyword(s):  
Socioeconomic Factors ◽  
Traffic Congestion ◽  
Travel Demand ◽  
Urban Traffic ◽  
Kuala Lumpur ◽  
Urban Street ◽  
Traffic Efficiency ◽  
Street Networks ◽  
Induced Travel ◽  
Traffic Scenario

The once-held wisdom of the supreme efficiency of one-way streets has been gradually sup-planted by the perceived sustainability of two-way streets in the design of livable cities that prioritizes the safety of pedestrians and thriving of local businesses. However, it is rarely dis-cussed on whether one-way street conversions have truly improved the long-term traffic effi-ciencies on urban street networks, as conflating socioeconomic factors such as vehicular popula-tion growth and induced travel demand may render empirical analysis inconclusive. In this study, microscopic traffic simulations implemented on SUMO platform was performed to ana-lyze the effect of street conversion in Downtown Brickfields, Kuala Lumpur. This approach can control and standardize travel demand in both one-way and two-way street networks, and would therefore give a fairer evaluation by precluding all socioeconomic factors. It was found that one-way streets do not necessarily improve the traffic efficiency of the network, as it is very dependent on the traffic scenario evolution over time. One-way streets perform better at the on-set of traffic congestion due to its higher capacity, but on average, the 4-fold longer travel times that made it harder to clear traffic by getting vehicles to their destinations compared to two-way streets. As time progresses, congestion in one-way streets may become twice as worse compared to two-way streets. This study may contribute to a more holistic assessment of traffic circulation plan designed for smart and livable cities

EGMM video surveillance for monitoring urban traffic scenario

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
A. Reyana ◽  
Sandeep Kautish ◽  
A.S. Vibith ◽  
S.B. Goyal
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Traffic Monitoring ◽  
Urban Traffic ◽  
Content Type ◽  
Proposed Model ◽  
Traffic Scenario ◽  
Slow Moving ◽  
Contamination Problem

PurposeIn the traffic monitoring system, the detection of stirring vehicles is monitored by fitting static cameras in the traffic scenarios. Background subtraction a commonly used method detaches poignant objects in the foreground from the background. The method applies a Gaussian Mixture Model, which can effortlessly be contaminated through slow-moving or momentarily stopped vehicles.Design/methodology/approachThis paper proposes the Enhanced Gaussian Mixture Model to overcome the addressed issue, efficiently detecting vehicles in complex traffic scenarios.FindingsThe model was evaluated with experiments conducted using real-world on-road travel videos. The evidence intimates that the proposed model excels with other approaches showing the accuracy of 0.9759 when compared with the existing Gaussian mixture model (GMM) model and avoids contamination of slow-moving or momentarily stopped vehicles.Originality/valueThe proposed method effectively combines, tracks and classifies the traffic vehicles, resolving the contamination problem that occurred by slow-moving or momentarily stopped vehicles.

EGMM Video Surveillance for Monitoring Urban Traffic Scenario

2020 ◽  
Vol 13 ◽  
Author(s):  
Reyana. A ◽  
Sandeep Kautish
Keyword(s):  
Monitoring System ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Traffic Monitoring ◽  
Processing Technique ◽  
Urban Traffic ◽  
Image Processing Technique ◽  
Traffic Scenario ◽  
Slow Moving

Objective: In the traffic monitoring system, the detection of stirring vehicles is monitored by fitting staticcameras in the traffic scenarios. The background subtraction, a commonly used method detaches poignant objects in the foreground from the background. The method applies a Gaussian Mixture Model, which can effortlessly be contaminated through slow-moving or momentarily stopped vehicles. For decades traffic vehicle-monitoring system follows fixedcamera surveillance for recording and extracting useful information. Calculating the number of Gaussian Models pixelwise the processing time of the observed scene can be calculated. However, an effective method to describe the smooth behavior of traffic scenes to handle critical situations is required. This paper proposes the method to effectively combine, track, and classify the traffic vehicles, resolving the contamination problem that occurred by slow-moving or momentarily stopped vehicles. Methods: The present study proposes an Enhanced Gaussian Mixture Model to overcome the addressed issue, efficiently detecting vehicles in complex traffic scenarios. The model was evaluated with experiments conducted using real-world on-road travel videos. Results: Compared with the existing GMM model to show contamination avoidance of vehicles that are motionless for a time gap. Conclusion: The findings present an improvement in the image processing technique for processing effective video scenes to eliminate frictional and noise variations. The Enhanced Gaussian Mixture Model shows a better accuracy of 0.9759 when compared with the existing state-of-the-art model and avoids contamination of slow-moving or momentarily stopped vehicles.

Sign in / Sign up

Export Citation Format

Share Document