Invention Grant
US09478038B2 Unsupervised spatio-temporal data mining framework for burned area mapping
有权
无监督的时空数据挖掘框架用于烧区映射
- Patent Title: Unsupervised spatio-temporal data mining framework for burned area mapping
- Patent Title (中): 无监督的时空数据挖掘框架用于烧区映射
-
Application No.: US14673018Application Date: 2015-03-30
-
Publication No.: US09478038B2Publication Date: 2016-10-25
- Inventor: Shyam Boriah , Vipin Kumar , Varun Mithal , Ankush Khandelwal
- Applicant: Shyam Boriah , Vipin Kumar , Varun Mithal , Ankush Khandelwal
- Applicant Address: US MN Minneapolis
- Assignee: Regents of the University of Minnesota
- Current Assignee: Regents of the University of Minnesota
- Current Assignee Address: US MN Minneapolis
- Agency: Westman, Champlin & Koehler, P.A.
- Agent Theodore M. Magee
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/00 ; G06K9/20 ; G06K9/46 ; G06K9/62

Abstract:
A method reduces processing time required to identify locations burned by fire by receiving a feature value for each pixel in an image, each pixel representing a sub-area of a location. Pixels are then grouped based on similarities of the feature values to form candidate burn events. For each candidate burn event, a probability that the candidate burn event is a true burn event is determined based on at least one further feature value for each pixel in the candidate burn event. Candidate burn events that have a probability below a threshold are removed from further consideration as burn events to produce a set of remaining candidate burn events.
Public/Granted literature
- US20150278603A1 UNSUPERVISED SPATIO-TEMPORAL DATA MINING FRAMEWORK FOR BURNED AREA MAPPING Public/Granted day:2015-10-01
Information query