Low-light sensor cleaning

Abstract

The disclosure provides a 'low-light sensor cleaning'. A system includes a camera having a field of view, a cleaning apparatus positioned to clean the camera, and a computer communicatively coupled tothe camera and the cleaning apparatus. The computer is programmed to detect an obstruction on the camera based on sensing a trajectory of an external light source relative to the field of view in data from the camera, and upon detecting the obstruction, activate the cleaning apparatus.

Description

technical field [0001] The present disclosure relates generally to vehicle sensors, and more particularly, to vehicle sensor cleaning. Background technique [0002] Vehicles often include sensors. The sensors may detect objects and / or features of the external world, such as the vehicle's surroundings, such as other vehicles, road lane markings, traffic lights and / or signs, pedestrians, and the like. For example, the sensor may be a radar sensor, a scanning laser range finder, a light detection and ranging (lidar) device and / or an image processing sensor such as a camera. [0003] Radar sensors and lidar units perform in roughly the same way during day and night because they generate their own radar waves or beams, while cameras, because they rely on light from the environment, perform better during day than night and / or in dark conditions Performed differently than. Nighttime imaging can be characterized by higher noise in the image due to lower light sensitivity at night...

AI Technical Summary

Problems solved by technology

Nighttime imaging can be characterized by higher noise in the image due to lower light sensitivity at night, under or overexposed parts of the image due to the higher dynamic range of the night scene, and can be used as ground truth Reduced number of known optical signatures of sources

These issues can make it more difficult to detect dust, raindrops, insect strikes, bird droppings, or other debris on the camera at night than during the day

Images