Kalibr is a software suite for multi-camera calibration and visual-inertial parameter estimation. It provides a mathematical framework for determining intrinsic and extrinsic parameters across multiple cameras and calculating the spatio-temporal offsets between cameras and inertial measurement units. The project features a non-linear least-squares optimizer to minimize reprojection and inertial errors. It includes specialized tools for rolling-shutter camera calibration to estimate projection and distortion parameters for sensors that capture images row-by-row. The system covers a broad rang
Official PyTorch implementation of the paper “LCCNet: Lidar and Camera Self-Calibration Using Cost Volume Network”. A video of the demonstration of the method can be found on https://www.youtube.com/watch?v=UAAGjYT708A
A fully featured, pythonic library for representing and using quaternions
Extrinsic Calibration of LiDAR Camera given an RGB image and a projected Depth image. Implemented for learning purposes. Based on RegNet: Multimodal Sensor Registration Using Deep Neural Networks. Still playing around with it. This isn't intended to be a faithful implementation.