Paper Title :CNN as Traffic Sings and Vehicle Classification Model: Model Analysis and Optimizing based on Tensorflow

Author :Malicehnkoviktor, Han Honggui

Article Citation :Malicehnkoviktor ,Han Honggui , (2021 ) " CNN as Traffic Sings and Vehicle Classification Model: Model Analysis and Optimizing based on Tensorflow " , International Journal of Advance Computational Engineering and Networking (IJACEN) , pp. 6-11, Volume-9,Issue-3

Abstract : Object detection and classification are among the most investigated types of projects and applicable in a wide range of jobs. One of the main goal is to create such a training model, which contains state-of-the-art technologies and methods with well-tuned parameters, and can be used to scale the project and implement it in real time. This will make it possible, with a luck of a big team, to create an unmanned vehicle that can recognize obstacles and take the necessary actions to avoid accidents. An essential criterion for creating such a model is to use approaches, with a clear analysis (using Tensorboard analysis) and understanding of the significance of each parameter. So we create a unique model that will be as stress-resistant as possible. Proposed article is a part of research of implementing artificial intelligence in different directions of the industry, developed in the laboratory of BJUT. Keywords - CNN, Object Classification, Tensorflow, Tensorboard, Traffic Sings - Vehicles

Type : Research paper

Published : Volume-9,Issue-3

	|		PDF	|	Viewed - 56	|	Published on 2021-07-21