Apparatus and methods for atmospheric condition detection
Apparatus and methods for determining an atmospheric condition in an environment of a vehicle are described herein. A long wave infrared camera may be used to produce thermal image data from a field of view of the LWIR camera that includes an unknown atmospheric condition. The thermal image data may include a characteristic that may be compared to characteristic of thermal image data for a known atmospheric condition. A result of the comparison may be used to make a determination related to the unknown atmospheric condition which may be used in controlling the vehicle.
1. A vehicle comprising:
a long wave infrared (LWIR) sensor;
at least one processor; and
computer-readable instructions that, when executed by the at least one processor, cause the at least one processor to perform the operations comprising:
receiving thermal image data from the LWIR sensor, the thermal image data comprising a representation of an object in an environment with the vehicle
determining, based at least in part on the thermal image data, a thermal image data characteristic, the thermal image data characteristic comprising an intensity distribution associated with the thermal image data;
comparing the thermal image data characteristic to a previously determined thermal image data characteristic associated with a known atmospheric condition, the previously determined thermal image data characteristic comprising an additional intensity distribution associated with the known atmospheric condition;
determining, based at least in part on the comparison, an estimated atmospheric condition;
determining, based at least in part on the comparison, a confidence level associated with the estimated atmospheric condition; and
controlling the vehicle based at least in part on the confidence level.
2. The vehicle of claim 1 , wherein the vehicle further comprises a camera, and wherein the acts performed by the at least one processor includes:
receiving camera data from the camera; and
determining a camera data characteristic,
wherein determining the estimated atmospheric condition is further based at least in part on the camera data characteristic.
3. The vehicle system of claim 2 , wherein the camera data characteristic is indicative of water on a lens of the camera.
4. The vehicle system of claim 1 , wherein determining the thermal image data characteristic comprises:
inputting, into a machine learned model, the thermal image data; and
receiving, from the machine learned model, the thermal image data characteristic.
5. The vehicle system of claim 1 , wherein the thermal image data includes infrared radiation information and the thermal image data characteristic comprises a level of contrast in the thermal image data.
6. A method comprising:
receiving thermal image data from an infrared camera;
determining, based at least in part on the thermal image data, a thermal characteristic, the thermal characteristic comprising an intensity distribution associated with the thermal image data;
determining, based at least on the thermal characteristic and on a previously determined thermal characteristic associated with a known atmospheric condition, an estimated atmospheric condition, the previously determined thermal characteristic comprising an additional intensity distribution associated with the known atmospheric condition;
determining a confidence level associated with the estimated atmospheric condition; and
controlling a vehicle based at least in part on the estimated atmospheric condition and the confidence level.
7. The method of claim 6 , wherein:
determining the thermal characteristic comprises determining a level of contrast of the thermal image data,
determining the estimated atmospheric condition comprises comparing the level of contrast with a stored level of contrast associated with a known atmospheric condition, and
determining the confidence level comprises determining a similarity between the level of contrast and the stored level of contrast.
8. The method of claim 6 , wherein the estimated atmospheric condition comprises one or more of:
rain,
snow,
clouds,
ice, or
sunshine.
9. The method of claim 6 , wherein the thermal characteristic comprises an indication of a portion of the thermal image data being mirrored within the thermal image data.
10. The method of claim 6 , the method further comprising:
detecting, based at least in part on the thermal image data, an object represented in the thermal image data,
wherein determining one or more of the estimated atmospheric condition or the confidence level is based at least in part on the object.
11. The method of claim 10 , wherein the object comprises one or more of:
a person,
a raincoat,
a jacket, or
an umbrella.
12. The method of claim 10 , wherein determining the estimated atmospheric condition is based on the portion of the thermal image data associated with the object.
13. The method of claim 6 , comprising:
receiving image data from a camera; and
determining, based at least in part on the image data, an image data characteristic,
wherein determining one or more of the estimated atmospheric condition or the confidence level is further based at least in part on the image data characteristic.
14. The method of claim 13 , wherein the image data characteristic is indicative of rain on a lens of the camera.
15. The method of claim 13 , wherein determining one or more of the estimated atmospheric condition or the confidence level comprises:
inputting, into a machine learned model, the thermal data and the image data; and
receiving, from the machine learned model, one or more of the estimated atmospheric condition or the confidence level.
16. The method of claim 6 , wherein determining one or more of the thermal data characteristic, the estimated atmospheric condition, or the confidence level comprises:
inputting the thermal data into a machine learned model; and
receiving, from the machine learned model, one or more of the thermal data characteristic, the estimated atmospheric condition, or the confidence level.
17. A vehicle system comprising:
at least one processor; and
computer readable instructions that, when executed by the at least one processor, cause the at least one processor to perform the operations comprising:
receiving thermal image data from a long wave infrared (LWIR) sensor, the thermal image data comprising a representation of an object in an environment of a vehicle;
determining, based at least in part on the thermal image data, a thermal image data characteristic, the thermal image data characteristic comprising an intensity distribution associated with the thermal image data;
comparing the thermal image data characteristic to a previously determined thermal image data characteristic associated with a known atmospheric condition, the previously determined thermal image data characteristic comprising an additional intensity distribution associated with the known atmospheric condition;
determining, based at least on the comparison, an estimated atmospheric condition; and
controlling the vehicle based at least in part on the estimated atmospheric condition.
18. The vehicle system of claim 17 , wherein the thermal image data includes infrared radiation information and the thermal image data characteristic comprises a level of contrast in the thermal image data.
19. The vehicle system of claim 17 , wherein the thermal image data characteristic comprises an indication of a portion of the thermal image data being mirrored within the thermal image data.
20. The vehicle system of claim 17 , wherein the computer readable instruction cause the at least one processor to perform additional operations comprising:
receiving camera data from a camera;
determining a camera data characteristic; and
wherein determining the atmospheric condition is further based at least in part on the camera data characteristic.