Camera-gated lidar system
AssigneeLuminar Technologies, Inc.
InventorsRichmond Hicks, Matthew D. Weed, Jason M. Eichenholz
Life of this patent
Estimating the term…
Abstract
A machine vision system comprises a camera configured to generate one or more images of a field of regard of the camera, a lidar system, and a processor. The lidar system includes a laser configured to emit light, where the emitted light is directed toward a region within the field of regard of the camera and a receiver configured to detect light returned from the emitted light. The processor is configured to receive an indication of a location based on the returned light and determine whether a solid object is present at the location based on the one or more images.
Claims18
A machine vision system comprising:
- a camera configured to generate one or more images of a field of regard (FOR) of the camera;
- a lidar system including:
- a laser configured to emit light, wherein the lidar system directs the emitted light toward a region within the FOR of the camera, and
- a receiver configured to detect light returned from the emitted light;
- and
- a processor configured to:
- receive an indication of a location based on the returned light,
- determine whether a solid object is present at the location based on the one or more images by detecting an absence of targets along a path of the emitted light within a maximum range of the lidar system, using the one or more images, and
- discard the indication of the location based on the detection of the absence of targets.
A method for operating a machine vision system, the method comprising:
- receiving, from a camera, data descriptive of a scene within a field of regard (FOR) of the camera;
- emitting, by a laser operating in a lidar system, light;
- directing the emitted light toward a region within the FOR of the camera;
- detecting light returned from the emitted light;
- receiving an indication of a location based on the returned light;
- determining, by a processor, whether a solid object is present at the location, based on the data descriptive of the scene, including detecting an object in a path of the emitted light, at an approximate distance greater than a maximum range of the lidar system, using the data descriptive of the scene, wherein the object scatters the light corresponding to the indication of the location;
- and
- discarding the indication of the location in view of the object.
A machine vision system comprising:
- a camera configured to generate one or more images of a field of regard (FOR) of the camera;
- a lidar system including:
- a laser configured to emit light, wherein the lidar system directs the emitted light toward a region within the FOR of the camera, and
- a receiver configured to detect light returned from the emitted light;
- and
- a processor configured to:
- receive an indication of a location based on the returned light,
- determine whether a solid object is present at the location based on the one or more images by detecting an absence of targets along a path of the emitted light within a certain range of the lidar system, using the one or more images;
- detect an object in a path of the emitted light, at a distance greater than a maximum range of the lidar system, using the one or more images, and
- discard the indication of the location in response to detecting the absence of targets within the certain range and detecting the object at a distance greater than the maximum range.
A machine vision system comprising:
- a camera configured to generate one or more images of a field of regard (FOR) of the camera;
- a lidar system including:
- a laser configured to emit light, wherein the lidar system directs the emitted light toward a region within the FOR of the camera, and
- a receiver configured to detect light returned from the emitted light;
- and
- a processor configured to:
- receive an indication of a location based on the returned light,
- determine whether a solid object is present at the location based on the one or more images by detecting an absence of targets along a path of the emitted light within a certain range of the lidar system, using the one or more images,
- detect an object in a path of the emitted light, at a distance greater than a maximum range of the lidar system, using the one or more images, and
- generate a pixel that corresponds to the range of the object in response to detecting the absence of targets within the certain range and detecting the object at a distance greater than the maximum range.
A machine vision system comprising:
- a camera configured to generate one or more images of a field of regard (FOR) of the camera;
- a lidar system including:
- a laser configured to emit a pulse of light, wherein the lidar system directs the emitted light toward a region within the FOR of the camera, and
- a receiver configured to detect light returned from the emitted light;
- and
- a processor configured to:
- receive an indication of a location based on the returned light, wherein the indication of the location is one of a plurality of indications of location received by the processor, and each of the indications of location is based on a respective pulse of returned light,
- select, from among the pulses of returned light, a pulse to generate a lidar pixel value,
- assign a confidence tag to the generated lidar pixel value in view of a shape of the selected pulse, and
- determine whether a solid object is present at the location based on the one or more images.
A method for operating a machine vision system, the method comprising:
- receiving, from a camera, data descriptive of a scene within a field of regard (FOR) of the camera;
- emitting, by a laser operating in a lidar system, light;
- directing the emitted light toward a region within the FOR of the camera;
- detecting light returned from the emitted light;
- receiving an indication of a location based on the returned light;
- determining, by a processor, whether a solid object is present at the location, based on the data descriptive of the scene, including detecting an object in a path of the emitted light, at an approximate distance greater than a maximum range of the lidar system, using the data descriptive of the scene, wherein the object scatters the light corresponding to the indication of the location;
- and
- generating a pixel that corresponds to the range of the object in response to detecting the object at a distance greater than the maximum range.
A method for operating a machine vision system, the method comprising:
- receiving, from a camera, data descriptive of a scene within a field of regard (FOR) of the camera;
- emitting, by a laser operating in a lidar system, light;
- directing the emitted light toward a region within the FOR of the camera;
- detecting light returned from the emitted light;
- receiving an indication of a location based on the returned light;
- detecting, using the data descriptive of the scene, a presence of a specularly reflective surface in the path of the light;
- determining, by a processor, whether a solid object is present at the location, based on the data descriptive of the scene;
- and
- discarding the indication of the location in view of a multipath return due to the specularly reflective surface.
Dependencies are inferred from the claim text.