Smart Parking: Symbol Detection Using Haar Cascade Classifier Algorithm To Monitor Empty Parking Slots

Sendari, Siti; Buana, Fajar Kelana; Wirawan, I Made; Wibowo, Fauzy Satrio; Tibyani,

doi:10.1109/iceeie52663.2021.9616962

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, this study is still in the form of a prototype, not really implemented in the actual parking environment. Another study regarding symbol identification with haar cascade classifier algorithm to monitor parking space vacancies [11] shows that the system is able to give the best results with a total of 108 images and the number of stages is 15. This study was using blue-red circle symbol to detect the parking lot status.…”

Section: Introductionmentioning

confidence: 99%

Perspective Transformation Automation In Identification Of Parking Lot Status With Blob Detection

Mubin,

Kusuma,

Rivai

2023

JAREE

View full text Add to dashboard Cite

Implementation of automation greatly facilitates the work of a system. This research automates the search for perspective transformation coordinates. In previous study, the process was done manually and was considered time-consuming and costly. The search for these coordinates is carried out with the help of red circles at several points in the parking area to be identified. There are two cases of images to be automated, namely the image of the parking area without obstacles and with obstacles. In the unobstructed images, the identification of transformation coordinates is carried out by identifying the coordinates of the auxiliary circle. Whereas in the images with obstructions, the identification of the transformation coordinates also involves the intersection equations of lines. The process of identifying the coordinates is done with the condition of the parking lot without a single vehicle. Once the coordinates are obtained, all coordinates are stored and will be used in the perspective transformation process in status parking slot identification stage. The identification stage is same with previous study. The proposed system 100% able to identify the transformation coordinates and carry out the perspective transformation process as expected. Of the 900 samples in each case, we acquire 100% recall, and most of the parking slot identification status being above 85% precision and accuracy. Compared to previous studies, the proposed system is more effective, with recall, precision, and accuracy values at 100%. The effectiveness of the proposed system is even more evident with average data automation time is 31.689 seconds.

show abstract

Section: Introductionmentioning

confidence: 99%