Traffic sign classification method for automatic driver assistance system, involves simply developing optimal deep learning-based convolutional neural network to perform accurate classification and assessing through standard evaluation measures
	NEDUNCHELIYAN S; KUMAR M V; NAGA R S V; VULLI R; KUMAR S Y; SHAMLI R
	2023-10-16
专利权人	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
申请日期	2023-10-16
专利号	IN202341069651-A
成果简介	NOVELTY - The method involves combining the artificial intelligent technique with smart traffic control required as the categorization of traffic signs to directly affect autonomous driving behavior. The traditional image processing approaches and machine learning algorithms are employed to classify traffic signs. The performance is found effective only in the standard cases and suffered in the heterogeneous test cases. The most of the recent deep learning-based approaches have complex network structures. The optimal deep learning-based convolutional neural network is simply developed, to perform accurate classification and assessed through standard evaluation measures. USE - Traffic sign classification method for automatic driver assistance system used in smart homes, autonomous vehicles, internet of things (IoT) and smart traffic. ADVANTAGE - The method enables utilizing a convolutional neural network (CNN) to train an image classification and recognition model with high accuracy and precision. The optimal deep learning-based convolutional neural network is simply developed, which performs accurate classification and assessed through standard evaluation measures.
IPC 分类号	G06K-009/62 ; G06N-003/04 ; G06N-003/08 ; G08G-001/08 ; G08G-001/095
国家	印度
专业领域	信息技术
语种	英语
成果类型	专利
文献类型	科技成果
条目标识符	http://119.78.100.226:8889/handle/3KE4DYBR/19676
专题	中国科学院新疆生态与地理研究所
作者单位	BHARATH HIGHER EDUCATION & RES INST (BHAR-Non-standard)
推荐引用方式 GB/T 7714	NEDUNCHELIYAN S,KUMAR M V,NAGA R S V,et al. Traffic sign classification method for automatic driver assistance system, involves simply developing optimal deep learning-based convolutional neural network to perform accurate classification and assessing through standard evaluation measures. IN202341069651-A[P]. 2023.

条目包含的文件
条目无相关文件。

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。