Citywide reconstruction of traffic flow using the vehicle-mounted moving camera in the CARLA driving simulator

Kumar, Ashutosh; Kashiyama, Takehiro; Maeda, Hiroya; Omata, Hiroshi; Sekimoto, Yoshihide

doi:10.1109/itsc55140.2022.9921927

Cited by 7 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is done to improve the accuracy of the re-identification since the vehicle size would be larger compared to if it was re-identified at a farther distance. This consideration improves not only the re-identification but also the estimated position of the vehicles as they are much closer to the ego vehicle [6]. Further, it also reduces the tracking failure reducing the redundant images in the search space during re-identification.…”

Section: E Vehicle Re-identificationmentioning

confidence: 97%

“…We use the base model of YOLOv7 with pre-trained weights on the COCO dataset with an input size of 640×640. We first train with the real-world images from the vehicle orientation dataset [4] for 100 epochs with a learning rate of 0.001 on four Tesla A100 GPUs [16] and then use the synthetic vehicle orientation dataset [6] to fine-tune the next ten epochs with a reduced learning rate of 0.0001 to prevent large changes in the parameters. It should be noted that the vehicle orientation dataset contains 15 classes of vehicles, while the synthetic vehicle orientation dataset has 12 classes of vehicles due to the absence of bus class; thus, bus front, bus back, and bus side classes are not present.…”

Section: B Carla Reid Datasetmentioning

confidence: 99%

“…3 using 51 known ground truth distances of different vehicles. The average value of µ h from 51 observations is calculated to be 599.46-pixel units [6], which we use in Eq. 3 to calculate the distance of detected vehicles.…”

Section: Localization Of Detected Vehiclesmentioning

confidence: 99%

“…The authors suggest using crowd-sourcing for citywide traffic flow estimation, making the method highly scalable. Another study [6] Fig. 1.…”

Section: Introductionmentioning

confidence: 96%

“…Alternatively, a driving simulator such as CARLA provides a realistic virtual environment to conduct various experiments. Similar to the research conducted in [6] for traffic flow estimation using multiple moving cameras in a driving simulator, we use the CARLA driving simulator to develop a fully computer vision-based approach to reconstruct vehicle trajectory, as shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Vehicle re-identification and trajectory reconstruction using multiple moving cameras in the CARLA driving simulator

Kumar

Kashiyama

Maeda³

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

Self Cite

View full text Add to dashboard Cite

Analyzing vehicle movement trajectories is essential for understanding urban mobility and traffic flow patterns. Obtaining a reliable estimate of vehicle trajectory is challenging as it requires the vehicle to be observed and re-identified at different locations and times. Recently, a scalable citywide traffic flow estimation method has been proposed utilizing moving cameras on vehicle dashboards. As moving cameras constantly interact with their surroundings, they provide valuable information about the urban environment that can be used to estimate vehicle trajectories. This study extends the recently proposed method for traffic flow estimation by using cameras mounted on multiple moving observers to reconstruct the trajectory of detected vehicles. We develop the CARLA ReID dataset, which includes more than 50,000 images taken from 85 cameras for over 700 different vehicle models, and train a re-identification network to identify the same vehicle by multiple observers. Utilizing our proposed methodology, we conduct extensive research to estimate trajectories of vehicles in a driving simulator CARLA and evaluate the accuracy of reconstructed trajectories using Symmetrized Segment-Path Distance (SSPD) and Hausdorff Distance metrics. Our proposed method achieves a mean error of 5.13 meters evaluated using the SSPD metric for ten driving experiments in CARLA. Findings from this study will provide valuable insights for conducting traffic flow research in a simulation environment, which is otherwise challenging and costly in practice.

show abstract

Section: E Vehicle Re-identificationmentioning

confidence: 97%