This research focuses on the development of Smart Level Crossing for preventing the accidents in the level crossing by detecting train at a certain distance before reaching the train gate inside the level crossing area. In order to detect the train in the level crossing, sensors for detecting train and communication systems that sends data to the train gate must be determined. This research tries to utilize a radar-based sensor as main part for train detection. This system would communicate with the micro-controller to accordingly carry out the gate closing and opening operations. Warning lamp and warning light would be present to warn off pedestrians that use level area crossing. Manual back up system will replace the automatic system in the case of smart level crossing system sensor fail to trigger.
The problem of parking systems on the street is a classic problem that occurs from year to year, manysolutions are offered in solving the parking problem on the street. The problem is not only related to trafficjams due to in and out of vehicles from the parking spaces but also the parking management issues becomepolemic at this time. A prototype of parking management monitoring system tries to provide solution inmanaging parking by using image processing based smart camera. In a prototype the system test performedon day and night conditions, to anticipate the very contrast difference intensity of pixels during the day or night so as to develop vehicle detection program using adaptive brightness thresholding. The results showthat the program has been running quite well to identify vehicles during day and night timeframe
Automatic License Plate Recognition is related to the Intelligent Transportation System (ITS) that supports the road's e-law enforcement system. In the case of the Indonesian license plate, with various colour rules for font and background, and sometimes vehicle owners modify their license plate font format, this is a challenge in the image processing approach. This research utilizes pre-trained of AlexNet, VGGNet, and ResNet to determine the optimum model of Indonesian character license plate recognition. Three pre-trained approaches in CNN-based detection for reducing time for a build if model from scratch. The experiment shows that using the pre-trained ResNet model gives a better result than another two approaches. The optimum results were obtained at epoch 50 with an accuracy of 99.9% and computation time of 26 minutes. This experiment results fulfil the goal of this research.
Keywords : ALPR; ITS; CNN; AlexNet; VGGNet; ResNet
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.