This research developed a smart parking system through video data analysis using deep learning techniques that automatically determine the availability of vacant parking spaces. This system has two main stages. The first is the stage of marking the parking position on the image of a parking lot captured by the camera. This research proposes a Preprocessed Region-based Convolutional Neural Network (Mask R-CNN) to mark the parking position on the input image of a full parking lot. The preprocess that combining contrast enhancement using the Exposure Fusion framework, aims to overcome the problem of lighting variations in images taken in an open area. In the second stage, each parking position is examined whether the position is vacant or not using mAlexNet. A series of trials on images with varying light conditions indicate that the Preprocessed Mask R-CNN can improve marking the parking positions with an accuracy of Intersection over Union (IoU) reach 85.80%. The result of marking the parking position is then used in the trial of the availability of parking space on video data using mAlexNet, and achieving an accuracy of 73.73%.
A method to identify the type of insects with accurate and precise results is of importance. Nowadays, an automatic object identification system with increased accuracy, improved speed, and less cost have been developed. Convolutional Neural Network (CNN) implementation for image identification or classification can be done by collecting large-scale datasets containing hundreds to millions of images to study the many parameters involved in the network. This research was conducted to develop and apply the CNN model to identify eight species of insects in the sweet corn field in Thailand. Those insects were Calomycterus sp., Rhopalosiphum
maidis, Frankliniella
williamsi, Spodoptera
frugiperda, Spodoptera
litura, Ostrinia
furnacalis, Mythimna
separata, and Helicoverpa
armigera. The CNN model in this research was built with four convolutional layers, which consist of Conv2D, batch normalization, max pooling, dropout sublayer, and a fully-connected layer. in total, 5568 images were trained with 10 trials and different train attempts for each trial, were then tested with 40 images. The result shows that the CNN model has succeeded in identifying images of sweet corn insects with 80% up to 95% prediction accuracy for images with no background.
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.