Multiple position rolling shutter imaging device
Provided are systems and methods related to a multiple position rolling shutter camera. A system can include an imaging device, an actuator, a processor, and a storage media. The imaging device can be configured to capture an image within a field of view using a rolling shutter that operates in a shutter direction. The actuator can be coupled to the imaging device and configured to rotate the imaging device between a first orientation, wherein the shutter direction comprises a first direction, and a second orientation, wherein the shutter direction comprises a second direction that is different than the first direction. The instructions can, when executed by the processor, cause the processor to cause the actuator to rotate the imaging device between the first orientation and the second orientation.
1 . A system, comprising:
an imaging device configured to be coupled to an autonomous vehicle, the imaging device configured to capture an image within a field of view using a rolling shutter that operates in a shutter direction;
a connector coupled to the imaging device;
an actuator coupled to the connector, the actuator configured to rotate the connector and the imaging device between:
a first orientation comprising one of a horizontal shutter direction and a vertical shutter direction, and
a second orientation comprising the other of the horizontal shutter direction and the vertical shutter direction;
a light detection and ranging (LiDAR) system configured to be coupled to the autonomous vehicle, the LiDAR system configured to capture a LiDAR image, wherein the image captured by the imaging device and the LiDAR image are captured at substantially the same point in time; and
at least one processor configured to compare the image captured by the imaging device and the LiDAR image and cause the actuator to rotate the imaging device between the first orientation and the second orientation based on determining that a difference between a shape of an object in the image captured by the imaging device and a shape of the object in the LiDAR image exceeds a pre-determined threshold value.
2 . The system of claim 1 , wherein the field of view of the imaging device is asymmetric.
3 . The system of claim 1 , wherein the at least one processor is configured to:
detect an object within the image; and
cause the actuator to rotate the imaging device between the first orientation and the second orientation based on determining that the object extends beyond the field of view of the imaging device.
4 . The system of claim 1 , wherein the pre-determined threshold value is a level of confidence.
5 . A method comprising:
receiving, using at least one processor, an image from an imaging device coupled to an autonomous vehicle, the imaging device configured to capture an image within a field of view using a rolling shutter that operates in a shutter direction, wherein the imaging device is coupled to an actuator configured to rotate the imaging device between a first orientation and a second orientation, the first orientation comprising one of a horizontal shutter direction and a vertical shutter direction and the second orientation comprising the other of the horizontal shutter direction and the vertical shutter direction;
receiving, using the at least one processor, a LiDAR image from a LiDAR system coupled to the autonomous vehicle, wherein the image captured by the imaging device and the LiDAR image are captured at substantially the same point in time;
comparing, using the at least one processor, the image from the imaging device and the LiDAR image to determine a difference between a shape of an object in the image from the imaging device and a shape of the object in the LiDAR image; and
causing, using the at least one processor, the actuator to rotate the imaging device between the first orientation and the second orientation when the difference exceeds a pre-determined threshold value.
6 . The method of claim 5 , wherein the pre-determined threshold value is a level of confidence.
7 . The method of claim 5 , further comprising:
detecting an object within the image; and
causing the actuator to rotate the imaging device between the first orientation and the second orientation based on determining that the object extends beyond a field of view of the imaging device.
8 . An apparatus, comprising:
a light detection and ranging (LiDAR) system configured to be coupled to an autonomous vehicle, the LiDAR system configured to capture a LiDAR image;
an imaging device configured to be coupled to the autonomous vehicle, the imaging device comprising a field of view that is asymmetric, the field of view comprising a first dimension that is less than and orthogonal to a second dimension, the imaging device configured to capture an image within the field of view, wherein the image captured by the imaging device and the LiDAR image are captured at substantially the same point in time;
a connector coupled to the imaging device; and
an actuator coupled to the connector, the actuator configured to rotate the connector and the imaging device between a first orientation and a second orientation based on an identified difference between a shape of an object in the image captured by the imaging device and a shape of the object in the LiDAR image exceeding a pre-determined threshold value, wherein:
the first orientation comprises one of a horizontal shutter direction and a vertical shutter direction, and
the second orientation comprises the other of the horizontal shutter direction and the vertical shutter direction.
9 . The apparatus of claim 8 , wherein the first orientation is about 90 degrees different than the second orientation.
10 . The apparatus of claim 8 , wherein the imaging device comprises a camera.
11 . The apparatus of claim 8 , wherein the actuator comprises an electric motor.
12 . The apparatus of claim 8 , wherein the pre-determined threshold value is a level of confidence.