Parking Slot Detection for Autonomous Parking System with Template Matching

In this paper, a parking slot detection algorithm based on a bird's eye view is proposed. A density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and template matching algorithm are fused to detect parking slots in a bird's eye view. Progressive probabil...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Chinese Control Conference s. 8038 - 8043
Hlavní autori: Wang, Yijing, Wang, Runpeng, Li, Zheng, Zuo, Zhiqiang, Yu, Baowei
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: Technical Committee on Control Theory, Chinese Association of Automation 24.07.2023
Predmet:
Bird's Eye View
Classification algorithms
Clustering algorithms
Costs
DBSCAN Clustering Algorithm
Hardware
Learning systems
Marking point
Probabilistic logic
Shape
Template Matching
ISSN:1934-1768
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, a parking slot detection algorithm based on a bird's eye view is proposed. A density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and template matching algorithm are fused to detect parking slots in a bird's eye view. Progressive probabilistic Hough line detection and an improved DBSCAN clustering algorithm is developed to locate the sidelines of parking slots. Then, template matching is provided to locate and classify the "T shape" and "L shape" marking points more accurately. Finally, the marking points and sidelines of parking slots are integrated to complete the parking slot detection. The recall rate and precision rate of experimental results are 74.4% and 92.0%.
ISSN:1934-1768
DOI:10.23919/CCC58697.2023.10241109