Patent · US Active

Regionlets with shift invariant neural patterns for object detection

US9202144B2 · kind B2 · utility

27Cited by

1References

19Claims

0Family size

Assignee

NEC Laboratories America, Inc. · US

Inventors

Xiaoyu Wang · Culver City, US
Yuanqing Lin · Sunnyvale, US
Will Zou · Princeton, US
Miao Sun · Dhahran, SA

Key dates

Filing date	Oct 17, 2014
Grant date	Dec 1, 2015
Priority date	—
Expiry date	Oct 17, 2034

Classification

Technology area (CPC G)Physics
CPC primaryG06V30/194
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Systems and methods are disclosed for detecting an object in an image by determining convolutional neural network responses on the image; mapping the responses back to their spatial locations in the image; and constructing features densely extract shift invariant activations of a convolutional neural network to produce dense features for the image.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.