高速道路下匝道分叉点确定方法、系统、设备及存储介质
By acquiring video of the vehicle lane using a visual sensor, calculating the tangent value of the vehicle lane, and fitting a polynomial equation, the accuracy and stability issues of highway ramp recognition are solved, and the reliability of ramp recognition is improved.
CN118887639BActive Publication Date: 2026-07-17WUHAN KOTEI INFORMATICS
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN KOTEI INFORMATICS
- Filing Date
- 2024-07-25
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing methods for identifying highway ramps rely on matching GPS data with map data, which leads to delays or failures in identification when GPS signals are weak, resulting in insufficient accuracy and stability in ramp identification.
Method used
By acquiring video of the vehicle lanes on the highway using a visual sensor, traversing the video frame by frame, selecting video segments with consecutive frames of vehicle lane difference, determining the vehicle lane tangent value, fitting a vehicle lane polynomial equation, and calculating the ramp bifurcation point.
Benefits of technology
It improves the accuracy and stability of ramp identification and reduces the risk of identification delay when GPS signal is weak.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN118887639B_ABST
Abstract
本发明公开了一种高速道路下匝道分叉点确定方法、系统、设备及存储介质，所述方法包括：根据预设车线横向阈值范围从车线视频中选取多段连续帧数车线差值视频片段；基于起始时间戳通过预设帧数滑动窗口确定各段连续帧数车线差值视频片段的车线正切值，从多段连续帧数车线差值视频片段中选取车线正切值大于预设正切值的多段目标车线视频片段；基于各预设前帧数车线差值片段对应的车线差值从多段目标车线视频片段中选取多段下匝道口车线视频片段；根据各段下匝道口车线视频片段对应的多个右一车线数据点及多个右二车线数据点确定下匝道分叉点。本发明基于对车道线的识别参数计算获取匝道口车道线分叉位置，提高了高速道路匝道口识别准确性与稳定性。
Need to check novelty before this filing date? Find Prior Art