Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Crowdsense Roadside Parking Spaces with Dynamic Gap Reduction Algorithm

Wenjun Zheng, Zhan Shi, Qianyu Ou, Ruizhi Liao

TL;DR

The paper tackles the problem of accurate roadside parking occupancy detection using crowdsensing with moving sensors, addressing the inherent accuracy gap due to detection intervals. It proposes Dynamic Gap Reduction Algorithm (DGRA), comprising a predictive model that yields the conditional distribution $P_{y|x}$ for parking-duration variables $y_1$ and $y_2$ given features $x$, and a stochastic optimization that selects the predicted time point $z_1$ and state $z_2$ by maximizing $P_{y|x}(z_2|z_1)$ via Integrated Learning and Optimization (ILO). A Driver-Side and Traffic-Based Evaluation Model (DSTBM) is also introduced to incorporate drivers’ decisions and traffic conditions, improving realism and robustness. Across three evaluation streams—open data benchmarks, SFpark comparisons, and real drive tests—the DGRA approach reduces sensor requirements while achieving high detection and information accuracy (IA), with IA reaching around 88–90% under DGRA in high-quality GPS scenarios, signaling tangible benefits for cost-effective urban parking management. The work advances crowdsensing for urban parking by integrating probabilistic forecasting, optimization, and driver-traffic dynamics to deliver robust, scalable, and privacy-conscious parking information services.

Abstract

In the context of smart city development, mobile sensing emerges as a cost-effective alternative to fixed sensing for on-street parking detection. However, its practicality is often challenged by the inherent accuracy limitations arising from detection intervals. This paper introduces a novel Dynamic Gap Reduction Algorithm (DGRA), which is a crowdsensing-based approach aimed at addressing this question through parking detection data collected by sensors on moving vehicles. The algorithm's efficacy is validated through real drive tests and simulations. We also present a Driver-Side and Traffic-Based Model (DSTBM), which incorporates drivers' parking decisions and traffic conditions to evaluate DGRA's performance. Results highlight DGRA's significant potential in reducing the mobile sensing accuracy gap, marking a step forward in efficient urban parking management.

Crowdsense Roadside Parking Spaces with Dynamic Gap Reduction Algorithm

TL;DR

The paper tackles the problem of accurate roadside parking occupancy detection using crowdsensing with moving sensors, addressing the inherent accuracy gap due to detection intervals. It proposes Dynamic Gap Reduction Algorithm (DGRA), comprising a predictive model that yields the conditional distribution for parking-duration variables and given features , and a stochastic optimization that selects the predicted time point and state by maximizing via Integrated Learning and Optimization (ILO). A Driver-Side and Traffic-Based Evaluation Model (DSTBM) is also introduced to incorporate drivers’ decisions and traffic conditions, improving realism and robustness. Across three evaluation streams—open data benchmarks, SFpark comparisons, and real drive tests—the DGRA approach reduces sensor requirements while achieving high detection and information accuracy (IA), with IA reaching around 88–90% under DGRA in high-quality GPS scenarios, signaling tangible benefits for cost-effective urban parking management. The work advances crowdsensing for urban parking by integrating probabilistic forecasting, optimization, and driver-traffic dynamics to deliver robust, scalable, and privacy-conscious parking information services.

Abstract

In the context of smart city development, mobile sensing emerges as a cost-effective alternative to fixed sensing for on-street parking detection. However, its practicality is often challenged by the inherent accuracy limitations arising from detection intervals. This paper introduces a novel Dynamic Gap Reduction Algorithm (DGRA), which is a crowdsensing-based approach aimed at addressing this question through parking detection data collected by sensors on moving vehicles. The algorithm's efficacy is validated through real drive tests and simulations. We also present a Driver-Side and Traffic-Based Model (DSTBM), which incorporates drivers' parking decisions and traffic conditions to evaluate DGRA's performance. Results highlight DGRA's significant potential in reducing the mobile sensing accuracy gap, marking a step forward in efficient urban parking management.
Paper Structure (26 sections, 6 equations, 11 figures, 7 tables)

This paper contains 26 sections, 6 equations, 11 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Fixed sensing
  4. Mobile sensing
  5. Analytical modeling
  6. Dynamic Gap Reduction Algorithm for Crowdsensing Roadside Parking Spaces
  7. Example of detection error
  8. The framework of the Dynamic Gap Reduction Algorithm
  9. Kernel choice of random variable $y$
  10. The stochastic optimization problem
  11. Real-world deployment of DGRA
  12. Driver-Side and Traffic-Based Evaluation Model
  13. DSTBM Preliminary
  14. Drivers' decision tree
  15. Illustration of the whole process
  16. ...and 11 more sections

Figures (11)

  • Figure 1: Working scenarios of mobile sensing and fixed sensing techniques in monitoring parking status
  • Figure 2: Detection Error between two detections. (a) The process of entering or exiting a parking space, (b) The process of extra prediction between two detections, and (c) The benefit of DGRA prediction between two detections
  • Figure 3: The Framework of DGRA. (a) The process of DGRA in theory (b) The process of DGRA in practice
  • Figure 4: Flowchart of generating probability function P("1") for case 2
  • Figure 5: Drivers' decision model based on external factors
  • ...and 6 more figures