Techniques for fast point cloud filtering using a parallel cascaded filter

A light detection and ranging (LiDAR) system, comprising:

• a processor;
• and
• a memory to store instructions that, when executed by the processor, cause the system to:
• receive, at a first filter, a set of points of interest (POIs) of a point cloud, wherein each POI of the set of POIs comprises one or more points;
• filter each POI of the set of POIs, wherein to filter, the system is to:
• at a second filter:
• select a first set of neighborhood points of a POI;
• compute a first metric for the first set of neighborhood points;
• and
• determine a first score of the POI based on the first metric;
• at the third filter:
• select a second set of neighborhood points of the POI;
• compute a second metric for the second set of neighborhood points;
• and
• determine a second score of the POI based on the second metric;
• and
• at the first filter:
• determine, based on the first score and the second score, whether to accept the POI, modify the POI, or reject the POI, to extract at least one of range or velocity information related to a target;
• provided the POI is accepted or modified, transmit the POI to a filtered point cloud to extract the at least one of range or velocity information related to the target;
• provided the POI is rejected, prevent the POI from reaching the filtered point cloud.

A light detection and ranging (LiDAR) system, comprising:

• an optical source to transmit a portion of a light signal towards a target;
• an optical receiver to receive a return beam from the target based on the light signal,
• a circuitry;
• and
• a memory to store instructions that, when executed by the circuitry, cause the system to:
• receive, at a first filter, a set of points of interest (POIs) of a point cloud, wherein each POI of the set of POIs comprises one or more points;
• filter each POI of the set of POIs, wherein to filter, the system is to:
• at a second filter:
• select a first set of neighborhood points of a POI;
• compute a first metric for the first set of neighborhood points;
• and
• determine a first score of the POI based on the first metric;
• at the third filter:
• select a second set of neighborhood points of the POI;
• compute a second metric for the second set of neighborhood points;
• and
• determine a second score of the POI based on the second metric;
• and
• at the first filter:
• determine, based on the first score and the second score, whether to accept the POI, modify the POI, or reject the POI, to extract at least one of range or velocity information related to a target;
• provided the POI is accepted or modified, transmit the POI to a filtered point cloud to extract the at least one of range or velocity information related to the target;
• provided the POI is rejected, prevent the POI from reaching the filtered point cloud.