A cleaning device includes a casing holding an image capturing device, a protective cover disposed in a visual field of the image capturing device, a vibrator to vibrate the protective cover, a controller to control the vibrator, a monitor to detect an electrical characteristic value associated with a vibration of the vibrator, and a storage to store determination criteria based on which the controller evaluates the electrical characteristic value detected by the monitor. The controller is configured to evaluate the electrical characteristic value based on the plurality of determination criteria stored in the storage and clean a surface of the translucent body by controlling the vibrator according to the determination.

A method for determining whether or not a transparent protective cover of a video camera comprising a lens-based optical imaging system is partly covered by a foreign object is disclosed. The method comprises: obtaining (402) a first captured image frame captured by the video camera with a first depth of field; obtaining (404) a second captured image frame captured by the video camera with a second depth of field which differs from the first depth of field; and determining (406) whether or not the protective cover is partly covered by the foreign object by analysing whether or not the first and second captured image frames are affected by presence of the foreign object on the protective cover such that the difference between the first depth of field and the second depth of field results in a difference in a luminance pattern of corresponding pixels of a first image frame and a second image frame. The first image frame is based on the first captured image frame and the second image frame is based on the second captured image frame.

A sensor lens assembly includes a cylindrical sensor body including a lower surface, a sensor lens surface, and a side surface extending between the lower surface and an outer edge of the sensor lens surface, a sensor enclosed within the cylindrical sensor body and adjacent to the sensor lens surface, and a nozzle configured to deliver a fluid near a center point of the sensor lens surface. The sensor lens surface is concave and rotates relative to the side surface of the cylindrical sensor body such that centrifugal force causes the fluid to form a film on the sensor lens surface that acts as a barrier, cushion, and particle collecting medium on the sensor lens surface.

The present teaching relates to method, system, and implementations for glare control. A sensor housing assembly is provided on an autonomous vehicle to house at least one sensor therein and protect the at least one sensor from negative impact from an environment including glare from the environment that prevents the at least one sensor from capturing accurate information regarding a field of view with respect to the environment to facilitate autonomous driving of the autonomous vehicle. The negative impact on the at least one sensor is determined by a controller, which then activates a glare blocking mechanism in response to the determined negative impact. The glare blocking mechanism being mounted on the sensor housing assembly and configured to assist in blocking glare with respect to the at least one sensor.

A fluid spray nozzle includes a first member that is configured to be fixed to a sensor or a mounted portion to which the sensor is mounted, and a second member that is fixed to the first member. The first member has a fluid inlet and a first fluid passage that is connected to the fluid inlet. The second member has a second fluid passage that is connected to the first fluid passage, and a spray port from which the fluid that has passed through the second fluid passage is sprayed onto a predetermined location of the sensor.

The present invention relates to a method for cleaning a protective device (3) for a drive assist system (1), comprising an optical sensor (13) having an optic (14), the protective device (3) having an optical element (9) arranged upstream of the optic (14) and having an inner surface (9a) and an outer surface (9b) and being movably mounted about an axis of rotation (A1), the method comprising the following steps: processing a succession of images acquired by the optical sensor (13) when the optical element (9) is rotating, so as to detect a generally circular or semi-circular shape which is centred on the axis of rotation (A1) of the optical element (9) and which is generated by dirt deposited on the outer surface (9b), and triggering at least one action for cleaning the outer surface (9b) of the optical element (9) if the shape is detected. The invention also relates to an associated drive assist system (1).

An image capture device may detect presence of drop of liquid on its optical element during capture of visual content. The image capture device may effectuate removal of the drop of liquid from the optical element.

A piezoelectric material including a perovskite-type metal oxide represented by the following general formula (1); Bi; and Mn, wherein the content of Bi is 0.1-0.5 mol % with respect to 1 mol of the metal oxide, the content of Mn is 0.3-1.5 mol % with respect to 1 mol of the metal oxide, and the piezoelectric material satisfies (L.sub.4−L.sub.5)/L.sub.5≧0.05 and (L.sub.8−L.sub.9)/L.sub.9≧0.05 when the lengths of twelve Bi—O bonds with Bi that is located at a 12-fold site with respect to O in a perovskite-type unit cell as a starting point are taken to be L.sub.1 to L.sub.12 in length order:

(Ba.sub.1-xM1.sub.x)(Ti.sub.1-yM2.sub.y)O.sub.3  (1)

wherein 0≦x≦0.2, 0≦y≦0.1, and M1 and M2 are mutually different metal elements which have a total valence of +6 and are selected from other elements than Ba, Ti, Bi and Mn.

A method for image capture using artificial intelligence (AI) techniques to generate a user-personalized and noise-corrected final image from a captured image, that includes classifying a noise associated with a lens of an imaging device, preprocessing the captured image based on the classified noise to determine an initial region of interest (ROI), generating a first processed image by inputting the initial ROI and the captured image to a deep learning network, receiving a passive user input corresponding to a portion of a first preview of the first processed image, determining an additional ROI based on the passive user input and the classified noise, generating a second processed image by inputting the second ROI and the captured image to the deep learning network, and generating a user-personalization based noise-corrected final image based on the second processed image.

A computer includes a processor and a memory, the memory storing instructions executable by the processor to collect first sensor data from a time-of-flight sensor, collect second sensor data from one or more sensors, generate a virtual map of at least one of a light reflectivity or a depth from the time-of-flight sensor from the collected first sensor data and the collected second sensor data, determine a difference between the light reflectivity or the depth of each pixel of the first sensor data from the light reflectivity or the depth of each corresponding pixel of the virtual map, determine an occlusion of the time-of-flight sensor as a number of pixels having respective differences of the light reflectivity or the depth exceeding an occlusion threshold, and actuate a component to clean the time-of-flight sensor when the occlusion exceeds an occlusion threshold.