Detection system for predicting pedestrian-related information

• Main Authors: HAHN LUKAS, HASEK FERENC, PAUS ANDRE, SCHAEFER MATTHIAS, ZHAO KUN, SCHNICKMANN YOSEF
• Format: Patent
• Language: Chinese; English
• Published: 02.08.2022
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; GYROSCOPIC INSTRUMENTS; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; MEASURING DISTANCES, LEVELS OR BEARINGS; NAVIGATION; PHOTOGRAMMETRY OR VIDEOGRAMMETRY; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; SURVEYING; TESTING

A detection system (100) for predicting pedestrian-related information has: a tracking module (110) that detects and tracks a pedestrian in an operating area in real time from sensor data; a machine learning prediction module (140) that uses a machine learning algorithm to predict information relating to the tracked pedestrian at a future time on the basis of input data including the data of the tracked pedestrian transmitted by the tracking module (110) and map data of the operation area; a pedestrian behavior evaluation module (130) determines additional data of the tracked pedestrian representing real-time behavior of the pedestrian, and the additional data of the tracked pedestrian is used by the machine learning prediction module (140) as another input data for the prediction. 一种用于预测与行人相关的信息的检测系统(100)，具有：追踪模块(110)，其从传感器数据实时检测和追踪操作区域中的行人；机器学习预测模块(140)，其使用机器学习算法根据包括由所述追踪模块(110)发送的被追踪行人的数据和所述操作区域的地图数据在内的输入数据来对与所述被追踪行人相关的在未来时间的信息进行预测；行人行为评估模块(130)，其确定所述被追踪行人的表示该行人的实时行为的附加数据，并且所述被追踪行人的所述附加数据被所述机器学习预测模块(140)用作