Systems and methods for camera-LiDAR fused object detection with LiDAR-to-image detection matching

A method for controlling an autonomous vehicle, comprising:

• obtaining, by a computing device, a LiDAR dataset generated by a LiDAR system of the autonomous vehicle;
• using, by the computing device, the LiDAR dataset and at least one image to detect an object that is in proximity to the autonomous vehicle, the object being detected by
• matching points of the LiDAR dataset to pixels in the at least one image, and
• detecting the object in a point cloud defined by the LiDAR dataset based on the matching;
• using, by the computing device, the object detection to facilitate at least one autonomous driving operation,
• wherein the matching comprises determining a probability distribution of pixels of the at least one image to which a point of the LiDAR dataset may project taking into account a projection uncertainty in view of camera calibration uncertainties, and the probability distribution is determined by computing a probability distribution function over image space coordinates for a pixel to which a point of the LiDAR dataset would probably project and computed in accordance with following mathematical equation
• [
• x
• i
• y
• i
• 1
• ]
• =
• M
• int
• ⁢
• T
• Vehicle
• Camera
• ⁢
• T
• LiDAR
• Vechile
• [
• X
• Y
• Z
• 1
• ]
• where xi and yi represent image space coordinates for a pixel, and X, Y and Z represent LiDAR space coordinates for a point of the LiDAR dataset.