CPC G01S 17/86 (2020.01) [G01S 17/00 (2013.01); G01S 17/894 (2020.01); G06T 7/521 (2017.01); G06V 10/776 (2022.01); G06V 10/809 (2022.01); G06V 20/10 (2022.01); G06V 20/56 (2022.01); B60W 60/001 (2020.02); B60W 2420/42 (2013.01); B60W 2420/52 (2013.01)] | 20 Claims |
1. A method, comprising:
obtaining, by a processor, an image of a real-world scene with respect to a first viewpoint of an image sensor, wherein an object is identified in the image and is associated with a first annotation which represents a portion of the image which depicts the object;
obtaining, by the processor, sensor measurements representing the real-world scene in a three-dimensional space captured by a sensor, wherein the sensor is an active sensor which emits sound and/or light;
determining, by the processor, a spatial region in the three-dimensional space which is indicative of the viewpoint of the image sensor with respect to the first annotation which is extended in three-dimensional space, wherein the spatial region represents a subset of the three-dimensional space; and
annotating, by the processor, the second set of sensor measurements with a second annotation which represents a portion of the spatial region which includes the object, wherein the second annotation is identified via searching within the subset of the three-dimensional space.
|