Vision system for a motor vehicle and method of controlling a vision system

A vision system for a motor vehicle comprising, a pair of imaging devices forming a stereo imaging system and a data processing device establishing an object detector adapted to detect an object in a surrounding of the motor vehicle from one or more images captured by the imaging system, a tracker adapted to track over time the object by the object detector, wherein the data processing device is adapted to calculate a size related value and a disparity related value of the object, the data processing device comprises an analysis section adapted to perform an analysis on a group of at least five data points of the object corresponding to different times, wherein each data point comprises a size related value and a corresponding disparity related value of the object, wherein the analysis is a regression analysis using a predetermined regression function having at least one variable, wherein the regression analysis yields a best value for each of the at least one variable corresponding to a best match of the regression function to the group of data points, wherein the analysis section is adapted to calculate from the at least one best value a systematic error in the disparity related values or in the size related values, the data points used in the regression analysis span a distance range of at least 30 m or at least ten values in the distance range between 20 m and 100 m.

A vision system for a motor vehicle comprising, a pair of imaging devices forming a stereo imaging system and a data processing device establishing an object detector adapted to detect an object in a surrounding of the motor vehicle from one or more images captured by the imaging system, a tracker adapted to track over time the object by the object detector, wherein the data processing device is adapted to calculate a size related value and a disparity related value of the object, the data processing device comprises an analysis section adapted to perform an analysis on a group of at least five data points of the object corresponding to different times, wherein each data point comprises a size related value and a corresponding disparity related value of the object, wherein the analysis is a regression analysis using a predetermined regression function having at least one variable, wherein the regression analysis yields a best value for each of the at least one variable corresponding to a best match of the regression function to the group of data points, wherein the analysis section is adapted to calculate from the at least one best value a systematic error in the disparity related values or in the size related values, the data points corresponding to an object distance of less than a predetermined value are discarded in the regression analysis.

A vision system for a motor vehicle comprising, a pair of imaging devices forming a stereo imaging system and a data processing device establishing an object detector adapted to detect an object in a surrounding of the motor vehicle from one or more images captured by the imaging system, a tracker adapted to track over time the object by the object detector, wherein the data processing device is adapted to calculate a size related value and a disparity related value of the object, the data processing device comprises an analysis section adapted to perform an analysis on a group of at least five data points of the object corresponding to different times, wherein each data point comprises a size related value and a corresponding disparity related value of the object, wherein the analysis is a regression analysis using a predetermined regression function having at least one variable, wherein the regression analysis yields a best value for each of the at least one variable corresponding to a best match of the regression function to the group of data points, wherein the analysis section is adapted to calculate from the at least one best value a systematic error in the disparity related values or in the size related values, the data processing device is adapted to convert the systematic error in the disparity related values or the size related values into a squint angle error.

A vision system for a motor vehicle comprising, a pair of imaging devices forming a stereo imaging system and a data processing device establishing an object detector adapted to detect an object in a surrounding of the motor vehicle from one or more images captured by the imaging system, a tracker adapted to track over time the object detected by the object detector, wherein the data processing device is adapted to calculate a size related value and a disparity related value of the object, the data processing device comprises an analysis section adapted to perform an analysis on a group of at least five data points of the object corresponding to different times, wherein each data point comprises a size related value and a corresponding disparity related value of the object, wherein the analysis is a regression analysis using a predetermined regression function having at least one variable, wherein the regression analysis yields a best value for each of the at least one variable corresponding to a best match of the regression function to the group of data points, wherein the analysis section is adapted to calculate from the at least one best value a systematic error in the disparity related values or in the size related values, the regression analysis results from several of the objects are combined to yield a more accurate valve of the systematic error.