NEURAL NETWORK FOR OBJECT DETECTION IN IMAGES
First Claim
Patent Images
1. A device implemented method for image recognition, the method comprising:
- Accessing, using one or more processors of the device coupled to a memory of the device, an image depicting an object of interest and a background within a field of view;
generating, by the one or more processors configured by a multilayer object model, a set of bounding boxes within the image;
detecting, the one or more processors using a set of detection layers of the multilayer object model at least a portion of the object of interest within the image in two or more bounding boxes;
determining, by the one or more processors, context information by passing a layer output of a second detection layer to a first detection layer and incorporating the layer output of the second detection layer into the layer output of the first detection layer; and
based on detecting the portion of the object of interest and determining the context information, identifying, by the one or more processors, the object of interest from the portion of the object of interest included within the two or more bounding boxes, using a set of image representation layers of the multilayer object model.
1 Assignment
0 Petitions
Accused Products
Abstract
Systems, devices, media, and methods are presented for identifying and categorically labeling objects within a set of images. The systems and methods receive an image depicting an object of interest, detect at least a portion of the object of interest within the image using a multilayer object model, determine context information, and identify the object of interest included in two or more bounding boxes.
86 Citations
20 Claims
-
1. A device implemented method for image recognition, the method comprising:
-
Accessing, using one or more processors of the device coupled to a memory of the device, an image depicting an object of interest and a background within a field of view; generating, by the one or more processors configured by a multilayer object model, a set of bounding boxes within the image; detecting, the one or more processors using a set of detection layers of the multilayer object model at least a portion of the object of interest within the image in two or more bounding boxes; determining, by the one or more processors, context information by passing a layer output of a second detection layer to a first detection layer and incorporating the layer output of the second detection layer into the layer output of the first detection layer; and based on detecting the portion of the object of interest and determining the context information, identifying, by the one or more processors, the object of interest from the portion of the object of interest included within the two or more bounding boxes, using a set of image representation layers of the multilayer object model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A system comprising:
-
one or more processors; and a processor-readable storage device coupled to the one or more processors, the processor-readable storage device storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising; accessing an image depicting an object of interest and a background within a field of view; generating, by one or more processors configured by a multilayer object model, a set of bounding boxes within the image; detecting, using a set of detection layers of the multilayer object model, at least a portion of the object of interest within the image in two or more bounding boxes; determining context information by passing a layer output of a second detection layer to a first detection layer and incorporating the layer output of the second detection layer into the layer output of the first detection layer; and based on detecting the portion of the object of interest and determining the context information, identifying the object of interest from the portions of the object of interest included within the two or more bounding boxes, using a set of image representation layers of the multilayer object model. - View Dependent Claims (12, 13, 14, 15)
-
-
16. A processor-readable storage device storing processor-executable instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
-
accessing an image depicting an object of interest and a background within a field of view; generating, by a multilayer object model implemented using the one or more processors, a set of bounding boxes within the image; detecting, using a set of detection layers of the multilayer object model, at least a portion of the object of interest within the image in two or more bounding boxes; determining context information by passing a layer output of a second detection layer to a first detection layer and incorporating the layer output of the second detection layer into the layer output of the first detection layer; and based on detecting the portion of the object of interest and determining the context information, identifying the object of interest from the portions of the object of interest included within the two or more bounding boxes, using a set of image representation layers of the multilayer object model. - View Dependent Claims (17, 18, 19, 20)
-
Specification