Traffic Surveillance with Precision: Deep CNN Model for Condition Monitoring (2023)
Kuppireddy Haripirya, Ch Swapna, Mounika Manchukonda
JCR. 2023: 231-239
Abstract
The traffic surveillance system is accumulated with an enormous amount of data regarding road traffic each second. Monitoring these data with the human eye is a tedious process and it also requires manpower for monitoring. Deep learning Convolutional Neural Network (DLCNN) can be utilized for traffic monitoring and control. The traffic surveillance data are pre-processed to construct the training dataset. The Traffic net is constructed by transferring the network to traffic applications and retraining it with self-established data set. This Traffic-net can be used for regional detection in large scale applications. Further, it can be implemented across-the-board. Further, DLCNN is used for prediction of traffic status i.e., dense traffic, low traffic, accident, and fire occurred from test sample. Finally, the simulations revealed that the proposed DLCNN resulted in superior performance as compared to existing model.
» PDF