Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal E-Komtek

Implementation of Convolutional Neural Network Algorithm for Detecting Empty Parking Area Based on Raspberry Pi Suhartono; Satria Gunawan Zain; Sadaruddin, Ayu Futri
Jurnal E-Komtek (Elektro-Komputer-Teknik) Vol 8 No 1 (2024)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/e-komtek.v8i1.1220

Abstract

This study aims to implement a convolution neural network algorithm to detect empty parking areas based on Raspberry Pi 4 and use the Convolutional Neural Network (CNN) method of the YOLO V5 model. This research consists of several stages, starting from the potential and problem stages, needs analysis, literacy studies, building prototypes, system design, and system testing. The datasets collected were taken using smartphone cameras and webcams with a total of 645 image datasets which were divided into two categories, namely training data and validation. System testing is carried out in two conditions, namely during the day and at night. The results of the detection test for observing variations in the position of filled and unfilled vehicles obtained the highest average accuracy during daytime conditions, while for observing cars entering and leaving the parking lot during day and night conditions, the results were the same percentage of success.
Vehicle Type Detection and Classification System To Determine Parking Rates Based On Image Recognition Suhartono; Satria Gunawan Zain; Nasir, Nuraeni
Jurnal E-Komtek (Elektro-Komputer-Teknik) Vol 7 No 2 (2023)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/e-komtek.v7i2.1221

Abstract

This study aims to develop a system for detecting and classifying vehicle types using the Convolutional Neural Network (CNN) model YOLO V5 based on image recognition. This research consists of several stages, from the potential and problem stages, needs analysis, literacy studies, prototyping, system design, and system testing. The collected datasets were taken using smartphone cameras and webcams with a total of 800 image datasets, divided into two categories: training data and validation data. System testing is carried out in day and night conditions. The classification test results in daytime conditions obtained an accuracy of 93, an accuracy of 80%. The system's design for detecting and classifying vehicle types for determining parking rates based on image recognition works well. Each type of vehicle can be seen and ranked by the system.