Gm Cruise Holdings LLC

Daniel Chou

Nigel Rodrigues

Yongjun Wang

Jordan Michael Croom

Zhi Yuan Sherwin Lau

Derek Wu

Marco Antonio Gaxiola Michel

Kayla Holman

A sensor calibration system periodically receives scene data from a detector in a calibration scene. The calibration scene includes calibration targets. The sensor calibration system generates a calibration map based on the scene data. The calibration map is a virtual representation of the calibration scene and includes features of the calibration targets that can be used as ground truth features for calibrating AV sensors. The sensor calibration system can periodically update the calibration map. For instance, the sensor calibration system receives the scene data at a predetermined frequency and updates the calibration map every time it receives new scene data. The predetermined frequency may be a frequency of the detector completing a full scan of the calibration scene. The sensor calibration system provides a latest version of the calibration map for being used by an AV to calibrate a sensor on the AV

Periodically mapping calibration scene for calibrating autonomous vehicle sensors

Apparatus and methods are provided for using a self-illuminating harp to calibrate for distortion. In particular, apparatus, methods and systems are provided for imaging and analyzing self-illuminated harp in order to correct for lens distortion. In various implementations, an array of media is strung plumb which resembles a harp. The media can be light fibers or other suitable material which can be strung in a straight line. The cores of translucent fibers are illuminated. These are configured to scatter light throughout their bulk which escapes the core by egressing along the length of fiber. This light produces plumb lines which can be imaged, analyzed and model. In some implementations, imaging is performed by rotation to include a full FOV.

Self-illuminating distortion harp

The present technology is directed to determining an accuracy of an infrared (IR) camera, and more particularly, validating a distortion accuracy of an IR camera. The present technology can receive one or more images of a calibration harp captured by the IR camera, wherein the one or more images include a plurality of lines corresponding to a plurality of strings of the calibration harp. The present technology can further determine a degree of distortion of the plurality of lines based on a distortion error coefficient, wherein the distortion error coefficient is computed based on edge points of the plurality of lines on the one or more images.

Validation of infrared (IR) camera distortion accuracy

An illuminated sensor target includes a light source. Actuating the light source illuminates the sensor target. The illuminated sensor target is recognized by one or more sensors of a vehicle during a calibration process, and is used to calibrate the one or more sensors of the vehicle during the calibration process. The illuminated sensor target is illuminated during at least part of the calibration process, which may involve rotation of the vehicle about a turntable, with the illuminated sensor target positioned within a range of the turntable along with other sensors targets, which may also be illuminated.

Illuminated vehicle sensor calibration target

A computer-implemented method for focal length validation may include receiving, by a computing system, initial image data for an optical target from a camera. The method may also include determining a distortion parameter associated with the camera, based on the initial image data. The method may also include receiving, by the computing system, a first image of the optical target, wherein the first image is associated with a first position of the camera. The method may also include receiving, by the computing system, a second image of the optical target, wherein the second image is associated with a second position of the camera. The method may also include determining an estimated displacement between the first position of the camera and the second position of the camera based on the first image and the second image. The method may further include determining a focal length based on the estimated displacement and a measured displacement of the camera between the first position and the second position.

Growing community of inventors

Sunnyvale, CA, United States of America

Daniel Chou