Yin M Wang

US Patent:

20090258656, Oct 15, 2009

Filed:

Apr 13, 2008

Appl. No.:

12/101998

Inventors:

Yin Wang - Medford MA, US
Tao Jin - Medford MA, US

International Classification:

H04W 4/02

US Classification:

4554561

Abstract:

A method is disclosed for wirelessly providing easily accessed and comprehended location-relevant information to a mobile device or web browser by displaying a map showing locations of interest. Simply by touching the map, a user can specify locations and regions used for queries and for uploading peer-to-peer information such as blogs, reviews, items for sale, etc. The device can request information, receive synchronously or asynchronously pushed responses, and display them with symbols that indicate category, age, etc. Location-aware devices can automatically specify their locations and provide location histories. Regions of interest can be adjusted according to visitation frequency, or region boundaries can simply be traced on the map. Limits can be placed on requested information and on distribution of uploaded information. Queries can use fuzzy logic, transactions can be completed using the devices, and requested information can be delivered when battery charge level and wireless link quality are appropriate.

US Patent:

20210312783, Oct 7, 2021

Filed:

Apr 1, 2020

Appl. No.:

16/837781

Inventors:

- Chicago IL, US
YANYAN HU - Medford MA, US
QIFAN LIANG - Quincy MA, US
KANGYAN LIU - Revere MA, US
YIN WANG - Woburn MA, US
WEIJUAN WU - Winchester MA, US
CHIA YING LEE - Medford MA, US

International Classification:

G08B 21/18
G06Q 50/26
G06N 20/00
G06N 5/04

Abstract:

Methods for detecting anomalies in a geographic area include receiving, from an electronic computing device, expected relationship data indicating expected relationships between a plurality of entities within the geographic area; detecting the plurality of entities within the geographic area; generating observed relationship data indicating observed relationships between the plurality of entities; identifying the expected relationships between the plurality of entities based on the expected relationship data; determining that a given observed relationship between two entities of the plurality of entities is likely to represent an anomaly based on the expected relationship data; and providing an electronic notification to a safety officer, the electronic notification indicating that the given observed relationship is likely to represent the anomaly.

US Patent:

20200097769, Mar 26, 2020

Filed:

Sep 18, 2019

Appl. No.:

16/575297

Inventors:

- Vancouver, CA
Yin Wang - Malden MA, US
Xiao Xiao - Reading MA, US
Hao Zhang - Winchester MA, US
Chia Ying Lee - Medford MA, US

Assignee:

Avigilon Corporation - Vancouver

International Classification:

G06K 9/62
G06K 9/20
G06K 9/00

Abstract:

Methods, systems, and techniques for object detection and tracking are provided. A system may include a module configured to generate a plurality of region proposals, each region proposal comprising a part of a video frame, a CNN pre-trained for object detection, the plurality of region proposals being input to the CNN; a tracker for tracking one or more targets based on outputs from the CNN across the series of video frames and generating tracking information on the one or more targets; and a module further configured to refine the plurality of region proposals to be input to the CNN, based on the tracking information.

US Patent:

20200092463, Mar 19, 2020

Filed:

Jul 30, 2019

Appl. No.:

16/526711

Inventors:

- Vancouver, CA
Yin WANG - Malden MA, US

Assignee:

Avigilon Corporation - Vancouver BC

International Classification:

H04N 5/232
G06K 9/00
G06N 3/04
G06F 17/15

Abstract:

Methods, systems, and techniques for performing object detection using a convolutional neural network (CNN) involve obtaining an image and then processing the image using the CNN to generate a first feature pyramid and a second feature pyramid from the first pyramid. The second pyramid includes an enhanced feature map, which is generated by combining an upsampled feature map and a feature map of the first feature pyramid that has a corresponding or lower resolution of a resolution of the enhanced feature map. The upsampled feature map is generated by upsampling a feature map of the second feature pyramid that is at a shallower position in the CNN than the enhanced feature map. The enhanced feature map is split into channel feature maps of different resolutions, with each of the channel feature maps corresponding to channels of the enhanced feature map. Object detection is performed on the channel feature maps.

US Patent:

20190188524, Jun 20, 2019

Filed:

Dec 14, 2017

Appl. No.:

15/842605

Inventors:

- Vancouver, CA
Yin Wang - Malden MA, US
Aleksey Lipchin - Newton MA, US

Assignee:

Avigilon Corporation - Vancouver

International Classification:

G06K 9/62
G06K 9/00

Abstract:

Methods, systems, and techniques for classifying an object-of-interest using an artificial neural network, such as a convolutional neural network. An artificial neural network receives a sample image including the object-of-interest overlaying a background and a sample background image excluding the object-of-interest and corresponding to the background overlaid by the object-of-interest. The object-of-interest is classified using the artificial neural network. The artificial neural network classifies the object-of-interest using the sample background and sample images. Prior to receiving the sample background and sample images the artificial neural network has been trained to classify the object-of-interest using training image pairs. Each of at least some of the training image pairs includes a first training image that includes a training object-of-interest overlaying a training background and a training background image excluding the training object-of-interest and corresponding to the training background.

US Patent:

20180338009, Nov 22, 2018

Filed:

May 21, 2017

Appl. No.:

15/600736

Inventors:

- Menlo Park CA, US
Kevin Ventullo - Cambridge MA, US
Charles Joseph Hughes - San Francico CA, US
Yin Wang - Fremont CA, US

International Classification:

H04L 29/08
G06Q 50/00
H04W 4/02

Abstract:

An online system determines a polygon representing a physical location associated with a content item and indexes edges of the polygon based on their positions along an axis of a map. The index is used to retrieve edges spanning a point on the axis representing a location of a client device associated with an online system user. The online system compares the positions of the point and retrieved edges on an axis perpendicular to the axis and determines whether the user is at the physical location based on the comparison. If the user is not at the physical location, a boundary surrounding the point is compared with boundaries surrounding the indexed edges to determine whether the user is within a threshold distance of the physical location. If the user is at or within the threshold distance of the physical location, the user is determined eligible to receive the content item.