发明名称 |
Method and system for wildfire detection using a visible range camera |
摘要 |
Wildfires are detected by controlling image scanning within the viewing range of a video camera to generate digital images that are analyzed to detect gray colored regions, and then to determine whether a detected gray colored region is smooth. Further analysis to determine movement in a gray colored smooth region uses a past image which is within a slow moving time range, as determined by a strategy for controlling the image scanning. Additional analysis connects a candidate region to a land portion of the image, and a support vector machine is applied to a covariance matrix of the candidate region to determine whether the region shows smoke from a wildfire. |
申请公布号 |
US9047515(B2) |
申请公布日期 |
2015.06.02 |
申请号 |
US201013825003 |
申请日期 |
2010.09.13 |
申请人 |
Delacom Detection Systems LLC |
发明人 |
Cetin Ahmet Enis;Gunay Osman |
分类号 |
G06K9/00;G06K9/40;G08B17/00;G08B17/12;G06T7/00;G06T7/20 |
主分类号 |
G06K9/00 |
代理机构 |
Whitham, Curtis, Christofferson & Cook, P.C. |
代理人 |
Whitham, Curtis, Christofferson & Cook, P.C. |
主权项 |
1. A computer implemented method for wildfire detection using a visible range video camera, the computer performing steps comprising:
generating sequential video images of a subject area; detecting gray colored regions in one of the video images; determining if a gray colored region is smooth; determining if a gray colored smooth region is slow moving by a frame difference comparison between a video image containing the gray colored smooth region and a past video image that is within a slow moving time range of the video image; determining if a slow moving gray colored smooth region is connected to a land portion of the subject area; constructing a covariance matrix of a land connected slow moving gray colored smooth region; and applying a trained support vector machine to the covariance matrix to determine if the land connected slow moving gray colored smooth region is smoke from a wildfire. |
地址 |
Sarasota FL US |