The invention discloses a radar and visual target matching fusion method of a roadside sensing system, which comprises the following steps of: S1, carrying out time and space alignment on a visual detection result and a radar detection result; S2, judging whether a target is in a high-confidence region; and S3, judging whether the visual detection result is matched with the radar detection result or not. According to the method, a common sensing area of different sensors is divided into a high-confidence area and a low-confidence area, then detection results of the different sensors are matched in the high-confidence area, association is kept all the time after matching is finished (leaving the high-confidence area), and therefore the high-precision and high-stability thundersight fusion effect is achieved. Compared with a data layer fusion algorithm and a feature layer fusion algorithm in the prior art, the method provided by the invention has the advantages of low complexity and higher efficiency. Moreover, according to the method provided by the invention, matching fusion is carried out based on a high-confidence region, so that the precision and the stability are better.
本发明公开了一种路侧感知系统的雷达与视觉目标匹配融合方法,包括以下步骤:步骤S1,将视觉检测结果和雷达检测结果进行时间以及空间对齐,步骤S2,判断目标是否在高置信度区域内;步骤S3,判断视觉检测结果和雷达检测结果是否已匹配。本发明通过将不同传感器的共同感知区域划分为高置信度区域和低置信度区域,然后在高置信度区域进行不同传感器的检测结果匹配并在匹配结束(离开高置信度区域)后一直保持关联,从而达到高精度,高稳定性的雷视融合效果。本发明中的方法,与现有技术中的数据层融合和特征层融合算法相比,具有复杂度低,效率更高的优点。并且,本发明中的方法,是基于高置信度区域进行匹配融合,精度和稳定性更好。
Radar and visual target matching fusion method of roadside sensing system
一种路侧感知系统的雷达与视觉目标匹配融合方法
2023-12-01
Patent
Elektronische Ressource
Chinesisch
Roadside laser radar and regional vehicle matching method based on Frechet distance
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2021
|