Time-Spatial Multiscale Net for Vehicle Counting and Traffic Volume Estimation

Road safety modelers frequently use average annual daily traffic (AADT) as a measure of exposure in regression models of expected crash frequency for road segments and intersections. Recorded AADT values at most locations are estimated by state and local transportation agencies with significant uncertainty, often by extrapolating short-term traffic counts over time and space. This uncertainty in the traffic volume estimates, often termed in a modeling context as measurement error in right-hand-side variables, can have serious effects on model estimation, including: 1) biased regression coefficient estimates; and 2) increases in dispersion. The structure and magnitude of measurement error in AADT estimates are not clearly understood by researchers or practitioners, leading to difficulties in explicitly accounting for this error in statistical road safety models, and ultimately in finding solutions for its correction. This study explores the impacts of measurement error in traffic volume estimates on statistical road safety models by employing measurement error correction approaches, including regression calibration and simulation extrapolation. The concept is demonstrated using crash, traffic, and roadway data from rural, two-lane horizontal curves in the State of Washington. The overall results show that the regression coefficient estimates with a positive coefficient were larger and those with a negative coefficient were smaller (i.e., more negative) when the measurement error correction methods were applied to the regression models of expected crash frequency. Future directions in applications of measurement error correction approaches to road safety research are provided.

Abstract: Estimating traffic volume at a link level is important to transportation planners, traffic engineers, and policy makers. More specifically, this vital parameter has been used in transportation planning, traffic operations, highway geometric design, pavement design, and resource allocation. However, traditional factor approach, regression-­‐based models, and artificial neural network models failed to present network-­‐wide traffic volume estimates because they rely on traffic counts for model development, and they all have inherent weaknesses. A review to previous research work and the state-­‐of-­‐practice clearly indicates that the Traditional Four-step Travel Demand Model (TFTDM) was generally based on large traffic analysis zones (TAZs) and networks consisting of high functional-class roads only. Consequently, this conventional modeling framework yielded a limited number of link traffic assignments with fairly high estimation errors. In the light of these facts and the obvious need of accurate network-wide traffic estimates, this review is conducted. In particular, this paper provides an extensive review of using traditional travel demand models for improved network-­‐wide traffic volume estimation. The paper then focuses on the challenges and opportunities in achieving high-fidelity travel demand model (HFTDM). This review has revealed that, opportunities in relation to both technological advances and intelligent data present a substantial potential in developing the proposed HFTDM for a much more accurate traffic estimation at a network-­‐wide level. Finally, the paper concludes with key findings from the review and provides a few recommendations for future research related to the topic.

There are various means of monitoring traffic situations on roads. Due to the rise of artificial intelligence (AI) based image processing technology, there is a growing interest in developing traffic monitoring systems using camera vision data. This study provides a method for deriving traffic information using a camera installed at an intersection to improve the monitoring system for roads. The method uses a deep-learning-based approach (YOLOv4) for image processing for vehicle detection and vehicle type classification. Lane-by-lane vehicle trajectories are estimated by matching the detected vehicle locations with the high-definition map (HD map). Based on the estimated vehicle trajectories, the traffic volumes of each lane-by-lane traveling direction and queue lengths of each lane are estimated. The performance of the proposed method was tested with thousands of samples according to five different evaluation criteria: vehicle detection rate, vehicle type classification, trajectory prediction, traffic volume estimation, and queue length estimation. The results show a 99% vehicle detection performance with less than 20% errors in classifying vehicle types and estimating the lane-by-lane travel volume, which is reasonable. Hence, the method proposed in this study shows the feasibility of collecting detailed traffic information using a camera installed at an intersection. The approach of combining AI and HD map techniques is the main contribution of this study, which shows a high chance of improving current traffic monitoring systems.

Vehicle counting in traffic videos plays an essential role in traffic sur- veillance system. It can provide some important traffic information such as con- gestion level and statistical analysis of traffic flow. In this paper, a novel vehicle counting strategy, which is based on foreground detection algorithm in videos, is proposed. Two advantages are contributed by our method. First, it is cost-saving as no additional hardware devices are required. Second, the influence to perfor- mance caused by weather variations is eliminated by the use of foreground detec- tion technique. Finally, We compare our method with the state-of-the-art methods, and the experimental results clearly demonstrate the effectiveness of our method on complex real world traffic videos.

Urban Arterial Traffic Volume and Travel Time Estimation with Use of Data Driven Models

Interpretable machine learning approach in estimating traffic volume on low-volume roadways

Towards improving quality of video-based vehicle counting method for traffic flow estimation

When main line roads are traffic jam, many vehicles move into residential areal roads. Using ETC2.0 data, the authors analyzed the increase or decrease in vehicle traffic volume and the frequency of sudden braking on residential roads. However, previous studies have not clarified the relationship between vehicle traffic volume and sudden braking. Therefore, in this study, the authors attempted to clarify the relationship between vehicle traffic volume on residential areal roads that increases during traffic jams on main line roads, vehicle speeds, and the occurrence of sudden braking through an analysis using ETC2.0 data. It was also revealed that an increase in vehicle traffic volume on residential areal roads was contributing to a decrease in their safety.

Separation effects in a microregion: traffic volume estimation between the settlements of Lake Velence

Video-based crowd counting and density estimation (CCDE) is vital for crowd monitoring. The existing solutions lack in addressing issues like cluttered background and scale variation in crowd videos. To this end, a multiscale head attention-guided multiscale density maps fusion for video-based CCDE via multi-attention Spatial-Temporal CNN (MHAMD-MST-CNN) is proposed. The MHAMD-MST-CNN has three modules: a multi attention spatial stream (MASS), a multi attention temporal stream (MATS), and a final density map generation (FDMG) module. The spatial head attention modules (SHAMs) and temporal head attention modules (THAMs) are designed to eliminate the background influence from the MASS and the MATS, respectively, by mapping the multiscale spatial or temporal features to head maps. The multiscale de-backgrounded features are utilised by the density map generation (DMG) modules to generate multiscale density maps to deal with scale variation due to perspective distortion. The multiscale density maps are fused and fed into the FDMG module to obtain the final crowd density map. The MHAMD-MST-CNN has been trained and validated on three publicly available benchmark datasets: the Venice, the Mall, and the UCSD. The MHAMD-MST-CNN provides competitive results as compared with the state-of-the-arts in terms of mean absolute error (MAE) and root mean squared error (RMSE).

Computer vision has many applications that were implemented to the existing advance technology. Vehicle tracking and counting in video surveillance is one of them. Vehicle tracking allow the computer to detect and tracking the vehicles that capture through the video surveillance. Afterwards vehicle counting allow to the computer to count all of the vehicles on video. Background Subtraction is one of the method to perform object tracking and counting process for the system. This research implements Pixel Based Adaptive Segmenter Model for Background Subtraction method to perform object tracking and counting. This research used video capture of visual surveillance and vehicles as object to track and count. Result of this research is the system can track and count all vehicles on videos.

Vehicle counting is a process to estimate traffic density on roads to assess the traffic conditions for intelligent transportation systems (ITS). Real-time traffic management systems have become popular recently due to the availability of high end cameras and technology. The present traffic management systems focus on speed detection, signal jumping, zebra crossing but not on traffic density estimation. Proposed video-based vehicle counting and tracking method using a video captured on CCTV and handheld mobile cameras. The system can be used in smart cities to create smart traffic light signals, in which duration of each signal depends on real time vehicle density in a particular lane of road. Vehicle counting is performed in two steps: the captured video is sent to You Only Look Once (YOLO) based deep learning framework to detect, count and classify the vehicles. Multi vehicular tracking is adopted using Deep SORTalgorithm to track the vehicles in video frames. Model was trained for six different classes, using Google Colaboratory. Datasets of vehicles specifically pertaining to Indian roads environment is considered for implementation. The performance of the model was analyzed, proposed model has tested and obtained an average counting accuracy of 86.56% while the average precision is 93.85%. The model can be implemented for ascertaining the traffic density on roads and this provides knowledge for infrastructural development to authorities. It can also be an integral part of smart city projects to develop intelligent and smart traffic surveillance system.

A methodology is described for estimating air passenger and visitor automobile traffic volumes at an airport as a function of an airline flight time. The methodology allows for the estimation of inbound and outbound traffic volumes for any desired time interval as a function of airline flight arrival and departure times and probability distributions for the times that passenger automobiles enter and leave the airport relative to flight times. The total expected number of air passenger vehicles using the access facilities in a given time period is obtained by superimposing these probability distributions over all airline flights. Previous methods of measuring airport trip generation are reviewed. This is followed by a description of a 2-day travel survey conducted at the Dallas/Fort Worth Regional Airport (DFW) to obtain data for the model. Model estimates are compared with measured traffic counts in preliminary model validation.

Abstract. High-resolution aerial imagery can provide detailed and in some cases even real-time information about traffic related objects. Vehicle localization and counting using aerial imagery play an important role in a broad range of applications. Recently, convolutional neural networks (CNNs) with atrous convolution layers have shown better performance for semantic segmentation compared to conventional convolutional aproaches. In this work, we propose a joint vehicle segmentation and counting method based on atrous convolutional layers. This method uses a multi-task loss function to simultaneously reduce pixel-wise segmentation and vehicle counting errors. In addition, the rectangular shapes of vehicle segmentations are refined using morphological operations. In order to evaluate the proposed methodology, we apply it to the public “DLR 3K” benchmark dataset which contains aerial images with a ground sampling distance of 13 cm. Results show that our proposed method reaches 81.58 % mean intersection over union in vehicle segmentation and shows an accuracy of 91.12 % in vehicle counting, outperforming the baselines.

Radio frequency identification technology (RFID) and time series forecasts are used to create a dependable IoT-based traffic system. The system regulates city traffic. The suggested method estimates junction traffic volume over time using LSTM neural networks. RFID technology improves data collection accuracy and reliability. Data preparation includes outlier identification to remove anomalies. Training the LSTM model on preprocessed data reveals traffic volume trends. The trained model predicts traffic volume using historical data. Prediction performance is quantified by MAE, MAPE, and R2. The proposed approach is tested using four intersection traffic data. Results indicate that LSTM-based traffic volume estimation works. The optimal design is determined by evaluating system performance for 12-to-168-time steps. The experimental findings suggest that the proposed method can accurately anticipate traffic volume, helping traffic managers enhance flow. RFID and time series projections bolster traffic system reliability.