.png){kind=icon}
返回
Modular input processing scheme for object detection using computer vision in intelligent transportations
.png){kind=icon}
PRE
AI
DOI：10.1007/s10479-021-04383-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Intelligent Transportation System (ITS) relies on communication and computer-aided technologies for reliable driving and roadside assistance. The vehicle recognizes input from the driving environment through parking and dashboard video recorders. Based on the input, decisions on driving direction, object detection, etc., are made with ease. This article introduces Modular Input Processing Scheme (MIPS) for roadside object detection and decision-making in ITS. The scheme operates over the different input segments and features for identifying the object pattern. In the identification process, the object's estimated distance and velocity is computed. Therefore, the textural and physical features of the objects are identified for smart detection and driving decisions. The feature analysis is aided by classification learning for adaptable and non-adaptable feature differentiation. The proposed scheme also relies on stored and iterated features for in-distance identifications. The classification improves the detection accuracy in less time, reducing complexity and cumulative analysis. Thus the proposed scheme's performance is verified using accuracy, detection time, and computation complexity.
Keyword:
Classification learning
Computer vision
Feature analysis
Intelligent transportation system
Object detection
期刊
IF:
4.5
论文数:
8.1K
被引数:
2.1W
机构
引用论文
分享收藏
分享收藏Pedestrian Support in Intelligent Transportation Systems: Challenges, Solutions and Open issues
PREAI
分享收藏Moroccan Video Intelligent Transport System: Vehicle Type Classification Based on Three-Dimensional and Two-Dimensional Features摩洛哥视频智能交通系统: 基于三维和二维特征的车型分类.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏Using Reinforcement Learning With Partial Vehicle Detection for Intelligent Traffic Signal ControlOAAI
OAAI分享收藏
查看更多内容