FAST-LIVO: Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry

FAST-LIVO is a fast LiDAR-Inertial-Visual odometry system, which builds on two tightly-coupled and direct odometry subsystems: a VIO subsystem and a LIO subsystem. The LIO subsystem registers raw points (instead of feature points on e.g., edges or planes) of a new scan to an incrementally-built point cloud map. The map points are additionally attached with image patches, which are then used in the VIO subsystem to align a new image by minimizing the direct photometric errors without extracting any visual features (e.g., ORB or FAST corner features). The details could be viewed in the associate paper: arxiv.org/abs/....

[@zaleliu7627]

Look forward to FAST-LIVO2🤓

[@andreuhuguetsegarra5788]

YES! Congrats guys, very excited to try it

[@francescoperasso]

Hi I see that you have implemented a new FastLIVo library that integrates the Avia lidar with images from a camera, all synchronized by a card that generates a very precise PPS clock. Will you publish detailed libraries? I am using MID40 with fast LIo connected with an external IMU of WITmotion, but since there is no synchro timer that tunes all the data, the cloud distorts, also because MID40 at a very narrow FOV. With an external card that generates a precise clock then how do you connect it to the lidar? via its supplied cable for the PPS signal? Can you give some details about the camera and how to merge images into the package? Thank you

[@trollenz]

Awesome !

[@francescoperasso]

please hardware list , pc , model camera, stm board sync schematic ect...

[@louisli1004]

looking forward the source code

[@juiceberber]

range yyds

[@hanjinlong9980]

期待源代码