Enhancing transportation network intelligence through visual scene feature clustering analysis with 3D sensors and adaptive fuzzy control

View article
PeerJ Computer Science

Main article text

 

Introduction

Visual scene feature aggregation analysis based on 3d sensor and adaptive fuzzy control algorithm

Feature extraction of visual scene based on 3D sensor

Data preprocessing

where focal length f and center distance B are both fixed camera parameters. Therefore, by obtaining parallax, which is XR-Xr, the distance can be calculated.

where 1i,j2k+1

Feature extraction

where i, j represent the order of geometric moments, and x, y represent pixels in the corresponding image. f(x, y) is the equivalent mass size corresponding to the point (x, y) in the image. Assuming f(x, y) is identical to a constant, then the centroid of the profile is the centroid of the profile, and the centroid coordinates are:

Feature clustering based on adaptive fuzzy control algorithm

Compute similarity for transportation environment

where n represents the number of different environments. Then Formula (11) can be amended to:

Experiment and analysis

Dataset and implement details

where pr refers to the predicted result and gt denotes the truth of the data set annotation.

Comparison of our method and other methods

The influence of visual scene feature processing

Discussion

Conclusion

Supplemental Information

Additional Information and Declarations

Competing Interests

The author declares that they have no competing interests.

Author Contributions

Jing Xu conceived and designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.

Data Availability

The following information was supplied regarding data availability:

The code is available in the Supplemental File.

The third-party dataset is available at Zenodo: Xinyu Chen, Yixian Chen, & Zhaocheng He. (2018). Urban Traffic Speed Dataset of Guangzhou, China [Data set]. Zenodo. https://doi.org/10.5281/zenodo.1205229.

Funding

The author received no funding for this work.

137 Visitors 129 Views 4 Downloads

MIT

Your institution may have Open Access funds available for qualifying authors. See if you qualify

Publish for free

Comment on Articles or Preprints and we'll waive your author fee
Learn more

Five new journals in Chemistry

Free to publish • Peer-reviewed • From PeerJ
Find out more