A longitudinal scanline based vehicle trajectory reconstruction method for high-angle traffic video

Tianya Zhang, Jing Jin

Research output: Contribution to journalArticle

Abstract

In this paper, a robust and efficient High-angle Spatial-Temporal Diagram Analysis (HASDA) model is built to reconstruct high-resolution vehicle trajectories from infrastructure traffic surveillance videos. A combined methodology was developed, comprising of scanline-based trajectory extraction and feature-matching coordinate transformation. A scanline-based trajectory extraction technique is introduced to separate vehicle strands from pavement background on the spatial-temporal diagram by considering color features, gradient features, and motion features. Particular cleaning algorithms for removing static object noises, shadows, and occlusions are also established. Feature-matching coordinate transformation converts the pixel coordinates to the real-world coordinates to generate the physical vehicle trajectory. To evaluate the algorithm, generated trajectory results were compared to the reconstructed version of the Next Generation Simulation (NGSIM) dataset. 15-min NGSIM video was divided into a 5-min dataset for the calibration and the remaining 10-min data for evaluation. Model parameters calibrated based on the 5-min video data are then applied to the 10-min testing data. Two levels of performance measurements are considered to evaluate both trajectory-level and point-level results. A reference algorithm based on mainstream motion-based detection and tracking methods are used as a baseline algorithm. Based on the evaluation results, the proposed method shows promising trajectory detection results, that on average more than 90% of vehicle trajectories are constructed by the proposed methods from the NGSIM videos. The HASDA model outperforms the reference algorithm and shows superior transferability in the training-testing experiment. Further work needs to be done to improve the algorithm performance against shadows and occlusions by incorporating more intelligent and advanced techniques.

Original languageEnglish (US)
Pages (from-to)104-128
Number of pages25
JournalTransportation Research Part C: Emerging Technologies
Volume103
DOIs
StatePublished - Jun 1 2019

Fingerprint

reconstruction
video
Trajectories
traffic
model analysis
simulation
traffic infrastructure
performance measurement
evaluation
surveillance
Testing
Pavements
Cleaning
Pixels
experiment
methodology
Calibration
Color
performance
Experiments

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Automotive Engineering
  • Transportation
  • Computer Science Applications

Cite this

@article{13660bd616b24cd1a687641936ad238d,
title = "A longitudinal scanline based vehicle trajectory reconstruction method for high-angle traffic video",
abstract = "In this paper, a robust and efficient High-angle Spatial-Temporal Diagram Analysis (HASDA) model is built to reconstruct high-resolution vehicle trajectories from infrastructure traffic surveillance videos. A combined methodology was developed, comprising of scanline-based trajectory extraction and feature-matching coordinate transformation. A scanline-based trajectory extraction technique is introduced to separate vehicle strands from pavement background on the spatial-temporal diagram by considering color features, gradient features, and motion features. Particular cleaning algorithms for removing static object noises, shadows, and occlusions are also established. Feature-matching coordinate transformation converts the pixel coordinates to the real-world coordinates to generate the physical vehicle trajectory. To evaluate the algorithm, generated trajectory results were compared to the reconstructed version of the Next Generation Simulation (NGSIM) dataset. 15-min NGSIM video was divided into a 5-min dataset for the calibration and the remaining 10-min data for evaluation. Model parameters calibrated based on the 5-min video data are then applied to the 10-min testing data. Two levels of performance measurements are considered to evaluate both trajectory-level and point-level results. A reference algorithm based on mainstream motion-based detection and tracking methods are used as a baseline algorithm. Based on the evaluation results, the proposed method shows promising trajectory detection results, that on average more than 90{\%} of vehicle trajectories are constructed by the proposed methods from the NGSIM videos. The HASDA model outperforms the reference algorithm and shows superior transferability in the training-testing experiment. Further work needs to be done to improve the algorithm performance against shadows and occlusions by incorporating more intelligent and advanced techniques.",
author = "Tianya Zhang and Jing Jin",
year = "2019",
month = "6",
day = "1",
doi = "10.1016/j.trc.2019.03.015",
language = "English (US)",
volume = "103",
pages = "104--128",
journal = "Transportation Research Part C: Emerging Technologies",
issn = "0968-090X",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A longitudinal scanline based vehicle trajectory reconstruction method for high-angle traffic video

AU - Zhang, Tianya

AU - Jin, Jing

PY - 2019/6/1

Y1 - 2019/6/1

N2 - In this paper, a robust and efficient High-angle Spatial-Temporal Diagram Analysis (HASDA) model is built to reconstruct high-resolution vehicle trajectories from infrastructure traffic surveillance videos. A combined methodology was developed, comprising of scanline-based trajectory extraction and feature-matching coordinate transformation. A scanline-based trajectory extraction technique is introduced to separate vehicle strands from pavement background on the spatial-temporal diagram by considering color features, gradient features, and motion features. Particular cleaning algorithms for removing static object noises, shadows, and occlusions are also established. Feature-matching coordinate transformation converts the pixel coordinates to the real-world coordinates to generate the physical vehicle trajectory. To evaluate the algorithm, generated trajectory results were compared to the reconstructed version of the Next Generation Simulation (NGSIM) dataset. 15-min NGSIM video was divided into a 5-min dataset for the calibration and the remaining 10-min data for evaluation. Model parameters calibrated based on the 5-min video data are then applied to the 10-min testing data. Two levels of performance measurements are considered to evaluate both trajectory-level and point-level results. A reference algorithm based on mainstream motion-based detection and tracking methods are used as a baseline algorithm. Based on the evaluation results, the proposed method shows promising trajectory detection results, that on average more than 90% of vehicle trajectories are constructed by the proposed methods from the NGSIM videos. The HASDA model outperforms the reference algorithm and shows superior transferability in the training-testing experiment. Further work needs to be done to improve the algorithm performance against shadows and occlusions by incorporating more intelligent and advanced techniques.

AB - In this paper, a robust and efficient High-angle Spatial-Temporal Diagram Analysis (HASDA) model is built to reconstruct high-resolution vehicle trajectories from infrastructure traffic surveillance videos. A combined methodology was developed, comprising of scanline-based trajectory extraction and feature-matching coordinate transformation. A scanline-based trajectory extraction technique is introduced to separate vehicle strands from pavement background on the spatial-temporal diagram by considering color features, gradient features, and motion features. Particular cleaning algorithms for removing static object noises, shadows, and occlusions are also established. Feature-matching coordinate transformation converts the pixel coordinates to the real-world coordinates to generate the physical vehicle trajectory. To evaluate the algorithm, generated trajectory results were compared to the reconstructed version of the Next Generation Simulation (NGSIM) dataset. 15-min NGSIM video was divided into a 5-min dataset for the calibration and the remaining 10-min data for evaluation. Model parameters calibrated based on the 5-min video data are then applied to the 10-min testing data. Two levels of performance measurements are considered to evaluate both trajectory-level and point-level results. A reference algorithm based on mainstream motion-based detection and tracking methods are used as a baseline algorithm. Based on the evaluation results, the proposed method shows promising trajectory detection results, that on average more than 90% of vehicle trajectories are constructed by the proposed methods from the NGSIM videos. The HASDA model outperforms the reference algorithm and shows superior transferability in the training-testing experiment. Further work needs to be done to improve the algorithm performance against shadows and occlusions by incorporating more intelligent and advanced techniques.

UR - http://www.scopus.com/inward/record.url?scp=85064193471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064193471&partnerID=8YFLogxK

U2 - 10.1016/j.trc.2019.03.015

DO - 10.1016/j.trc.2019.03.015

M3 - Article

VL - 103

SP - 104

EP - 128

JO - Transportation Research Part C: Emerging Technologies

JF - Transportation Research Part C: Emerging Technologies

SN - 0968-090X

ER -