Lidar noise removal using image pixel clusterings

A system comprising:

• a camera for obtaining a two-dimensional image;
• a light detector for obtaining a three-dimensional point cloud comprising a plurality of points;
• a memory;
• a processor coupled to the memory and configured to:
• perform semantic segmentation on the image to map objects with a discrete pixel color, and overlaying the semantic segmentation on the image to generate a semantic segmentation image;
• generate superpixel clusters from the semantic segmentation image to group like pixels together;
• project the point cloud onto the semantic segmentation image comprising the superpixel clusters;
• and
• remove points determined to be noise/errors from the point cloud based on determining noisy points within each superpixel cluster.

A non-transitory computer-readable storage medium containing executable computer program code, the code comprising instructions configured to cause a processor to:

• obtain a two-dimensional image;
• obtain a three-dimensional point cloud comprising a plurality of points;
• perform semantic segmentation on the image to map objects with a discrete pixel color, and overlaying the semantic segmentation on the image to generate a semantic segmentation image;
• generate superpixel clusters from the semantic segmentation image to group like pixels together;
• project the point cloud onto the semantic segmentation image comprising the superpixel clusters;
• and
• remove points determined to be noise/errors from the point cloud based on determining noisy points within each superpixel cluster.