The present disclosure relates to systems, devices and methods for identifying objects and scenarios that have not been trained or are unidentifiable to vehicle perception sensors or vehicle assistivedriving systems. Embodiments are directed to using a trained vehicle data set to identify target objects in vehicle sensor data. In one embodiment, a process is provided and includes running a scenedetection operation on a vehicle to derive a vector of the target object attributes of the vehicle sensor data and generating the vector representation for the scene detection operation and the attributes of the vehicle sensor data. The vector representation is compared to a familiarity vector to represent the effectiveness of the scene detection operation. In addition, the vector representation can be scored to identify one or more target objects or significant scenarios, including the unidentifiable objects and/or driving scenes, scenarios for reporting.
本公开涉及用于识别对象和情景的系统、装置和方法,所述对象和情景尚未经过训练或车辆感知传感器或车辆辅助驾驶系统无法识别。实施例涉及使用经训练的车辆数据集来识别车辆传感器数据中的目标对象。在一个实施例中,提供了一种过程,所述过程包括:对车辆运行场景检测操作以导出所述车辆传感器数据的目标对象属性的矢量;以及生成针对所述场景检测操作和所述车辆传感器数据的所述属性的矢量表示。将所述矢量表示与熟悉度矢量进行比较,以表示所述场景检测操作的有效性。另外,可以对所述矢量表示进行评分,以识别一个或多个目标对象或有效情景,包括无法识别的对象和/或驾驶场景、情景,以便进行报告。
System and method for determining vehicle data set familiarity
用于确定车辆数据集熟悉度的系统和方法
2020-04-17
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
System and method for determining vehicle data set familiarity
Europäisches Patentamt | 2021
|Vehicle Familiarity and Safety
NTIS | 1983
|Driving Performance Analysis of Driver Experience and Vehicle Familiarity Using Vehicle Dynamic Data
British Library Conference Proceedings | 2018
|Online Contents | 2008
British Library Online Contents | 2002