Multi-perspective detection of objects
First Claim
Patent Images
1. A method comprising:
- receiving, by an object detector, a first image from a first positional angle, wherein the first image is from a first perspective of a scene;
receiving, by the object detector, a second image from a second, different positional angle, wherein the second image is from a second perspective of the scene;
generating cross-referenced image data (i) for the first image from the first perspective by cross-referencing data related to the second image with data related to the first image and (ii) for the second image from the second perspective by cross-referencing data related to the first image with data related to the second image; and
performing, by the object detector, object detection on the first image from the first perspective and on the second image from the second perspective utilizing the generated cross-referenced image data.
2 Assignments
0 Petitions
Accused Products
Abstract
Various systems, methods and non-transitory computer-readable media are described, which may involve performing operations comprising: receiving, with an object detector, a first image from a first positional angle comprising a first perspective of a scene, receiving, with the object detector, a second image from a second, different positional angle comprising a second perspective of the scene, and performing, with the object detector, object detection on the first image from the first perspective and on the second image from the second perspective by cross-referencing data related to the first image and the second image within the object detector.
84 Citations
23 Claims
-
1. A method comprising:
-
receiving, by an object detector, a first image from a first positional angle, wherein the first image is from a first perspective of a scene; receiving, by the object detector, a second image from a second, different positional angle, wherein the second image is from a second perspective of the scene; generating cross-referenced image data (i) for the first image from the first perspective by cross-referencing data related to the second image with data related to the first image and (ii) for the second image from the second perspective by cross-referencing data related to the first image with data related to the second image; and performing, by the object detector, object detection on the first image from the first perspective and on the second image from the second perspective utilizing the generated cross-referenced image data. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computing device comprising:
-
at least one processor; and a non-transitory computer-readable storage medium comprising instructions that are executable by the at least one processor to cause the computing device to; receive a first image from a first positional angle, wherein the first image is from a first perspective of a scene; receive a second image from a second, different positional angle, wherein the second image is from a second perspective of the scene; generate cross-referenced image data (i) for the first image from the first perspective by cross-referencing data related to the second image with data related to the first image and (ii) for the second image from the second perspective by cross-referencing data related to the first image with data related to the second image; and perform object detection on the first image from the first perspective and on the second image from the second perspective utilizing the generated cross-referenced image data. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory computer-readable storage medium comprising instructions thereon that are executable by at least one processor to cause a computing system to:
-
receive a first image from a first positional angle, wherein the first image is from a first perspective of a scene; receive a second image from a second, different positional angle, wherein the second image is from a second perspective of the scene; generate cross-referenced image data (i) for the first image from the first perspective by cross-referencing data related to the second image with data related to the first image and (ii) for the second image from the second perspective by cross-referencing data related to the first image with data related to the second image; and perform object detection on the first image from the first perspective and on the second image from the second perspective utilizing the generated cross-referenced image data. - View Dependent Claims (18, 19, 20, 21, 22, 23)
-
Specification