CONTEXT-BASED PRIORS FOR OBJECT DETECTION IN IMAGES
First Claim
Patent Images
1. A method of object detection, comprising:
- identifying a context label of an entire image; and
selecting a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label.
1 Assignment
0 Petitions
Accused Products
Abstract
Context-based priors are utilized in machine learning networks (e.g., neural networks) for detecting objects in images. The likely locations of objects are estimated based on context labels. A machine learning network identifies a context label of an entire image. Based on the, the network selects a set of likely regions for detecting objects of interest in the image.
136 Citations
28 Claims
-
1. A method of object detection, comprising:
-
identifying a context label of an entire image; and selecting a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An apparatus for object detection, comprising:
-
a memory; and at least one processor coupled to the memory, the at least one processor configured; to identify a context label of an entire image; and to select a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A non-transitory computer-readable medium for object detection having non-transitory program code recorded thereon, the program code comprising:
-
program code to identify a context label of an entire image; and program code to select a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24)
-
-
25. An apparatus for wireless communication, comprising:
-
means for identifying a context label of an entire image; and means for selecting a set of likely regions for detecting objects of interest in the image based at least in part on an identified context label. - View Dependent Claims (26, 27, 28)
-
Specification