Plane estimation for contextual awareness
Aspects of the disclosure relate to classifying the status of objects. For examples, one or more computing devices detect an object from an image of a vehicle's environment. The object is associated with a location. The one or more computing devices receive data corresponding to the surfaces of objects in the vehicle's environment and identifying data within a region around the location of the object. The one or more computing devices also determine whether the data within the region corresponds to a planar surface extending away from an edge of the object. Based on this determination, the one or more computing devices classify the status of the object.
1. A method comprising:
receiving, by one or more computing devices, sensor data of an autonomous vehicle corresponding to surfaces of objects in an environment of the autonomous vehicle, the surfaces of objects include a first surface of a first object identified as a sign at a location;
determining, by the one or more computing devices, whether there is a second surface of a second object included in the surfaces of objects based on the sensor data and a region around the location of the first object;
when there is determined to be a second surface of the second object included in the surfaces of objects, determining, by the one or more computing devices, whether the first surface is oriented closer to (1) parallel to the second surface or (2) perpendicular to the second surface;
when the first surface is determined to be oriented closer to perpendicular to the second surface, causing, by the one or more computing devices, the autonomous vehicle to react to the sign; and
when the first surface is determined to be oriented closer to parallel to the second surface, causing, by the one or more computing devices, the autonomous vehicle not to react to the sign.
2. The method of claim 1 , wherein the sign is a stop sign.
3. The method of claim 1 , wherein the second object is a vehicle in the environment of the autonomous vehicle.
4. The method of claim 3 , wherein the autonomous vehicle is a bus.
5. The method of claim 1 , wherein when there is determined to be no second surface of the second object included in the surfaces of objects, causing, by the one or more computing devices, the autonomous vehicle to react to the sign.
6. The method of claim 1 , wherein the sensor data includes a camera image, and the method further comprises identifying the sign using the camera image.
7. The method of claim 6 , wherein the sensor data includes laser data points identifying an intensity and location of surfaces of objects, and wherein the sensor data is processed by processing the laser data points.
8. The method of claim 7 , wherein processing the laser data points includes projecting the laser data points into a three-dimensional box that is larger than the sign.
9. A system comprising a vehicle having one or more computing devices configured to:
receive sensor data of an autonomous vehicle corresponding to surfaces of objects in an environment of the autonomous vehicle, the surfaces of objects include a first surface of a first object identified as a sign at a location;
determine whether there is a second surface of a second object included in the surfaces of objects based on the sensor data and a region around the location of the first object;
when there is determined to be a second surface of the second object included in the surfaces of objects, determine whether the first surface is oriented closer to (1) parallel to the second surface or (2) perpendicular to the second surface;
when the first surface is determined to be oriented closer to perpendicular to the second surface, causing the autonomous vehicle to react to the sign; and
when the first surface is determined to be oriented closer to parallel to the second surface, causing the autonomous vehicle to not react to the sign.
10. The system of claim 9 , wherein the sign is a stop sign.
11. The system of claim 9 , wherein the second object is a vehicle in the environment of the autonomous vehicle.
12. The system of claim 11 , wherein the autonomous vehicle is a bus.
13. The system of claim 9 , wherein the one or more computing devices are further configured to, when there is determined to be no second surface of the second object included in the surfaces of objects, cause the autonomous vehicle to react to the sign.
14. The system of claim 9 , wherein the sensor data includes a camera image, and the sign is identified using the camera image.
15. The system of claim 14 , wherein the sensor data includes laser data points identifying an intensity and location of surfaces of objects, and wherein the one or more computing devices are further configured to process the sensor data by processing the laser data points.
16. The system of claim 15 , wherein the one or more computing devices are further configured to process the laser data points by projecting the laser data points into a three-dimensional box that is larger than the sign.