公开(公告)号：US20160260306A1

公开(公告)日：2016-09-08

申请号：US15030469

申请日：2014-10-18

Applicant: Klaus JÄCKEL ,  Andreas JOCK ,  Uwe KRANE ,  Azarm NOWZAD ,  Holger VOGEL ,  IQ WIRELESS GMBH ENTWICKLUNGSGESELLSCHAFT FÜR SYSTEME UND TECHNOLOGIEN DER TELEKOMMUNIKATION ,  DEUTSCHES ZENTRUN FÜR LUFT-UND RAUMFAHRT

Inventor： Klaus JÄCKEL ,  Andreas JOCK ,  Uwe KRANE ,  Azarm NOWZAD ,  Holger VOGEL

IPC: G08B17/12 ,  G06K9/32 ,  G08B29/18 ,  G06N7/02 ,  G08B17/00 ,  G06K9/00 ,  G06K9/62

CPC classification number: G08B17/125 ,  G06K9/00657 ,  G06K9/00771 ,  G06K9/3233 ,  G06K9/6277 ,  G06N7/02 ,  G06T7/90 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10032 ,  G06T2207/20036 ,  G06T2207/30188 ,  G08B17/005 ,  G08B29/186

Abstract: A method for the automated early detection of forest fires by means of the optical detection of clouds of smoke, includes the following steps: producing images by means of at least one digital color-image camera and transmitting said images to a digital data processing medium; defining membership functions in a fuzzy-logic system for the classes “smoke,” “forest,” and “dark surface” by evaluating a plurality of test images or test sequences recorded by the color-image camera with respect to the saturation value (S) of the image pixel.

Abstract translation: 通过烟雾的光学检测自动早期检测森林火灾的方法包括以下步骤：通过至少一个数字彩色图像相机产生图像并将所述图像发送到数字数据处理介质; 通过评估由彩色图像摄像机记录的多个测试图像或测试序列相对于饱和度值（S（S））来定义用于类“烟”，“森林”和“暗表面”的模糊逻辑系统中的隶属函数 ）的图像像素。

公开(公告)号：US20100194893A1

公开(公告)日：2010-08-05

申请号：US11791169

申请日：2005-10-20

Applicant: Guenter Graeser ,  Andreas Jock ,  Uwe Krane ,  Hartmut Neuss ,  Holger Vogel ,  Volker Mertens ,  Joerg Knollenberg ,  Thomas Behnke ,  Ekkehard Kuert

Inventor： Guenter Graeser ,  Andreas Jock ,  Uwe Krane ,  Hartmut Neuss ,  Holger Vogel ,  Volker Mertens ,  Joerg Knollenberg ,  Thomas Behnke ,  Ekkehard Kuert

IPC: H04N7/18 ,  G06T7/00

CPC classification number: G08B17/005 ,  A62C3/0271 ,  G08B17/125

Abstract: The monitoring of territories in order to recognize forest and surface fires requires complex automatic and human-assisted processes, which ultimately must include the control of intervention forces. Disclosed are processes for the centralised monitoring of territories. A swiveling and tiltable camera installed at a monitoring site supplies images of overlapping observation sectors. In each observation sector a sequence of images comprising a plurality of images is taken, at an interval which corresponds to fire and smoke dynamics. An on-site image-processing software supplies event warnings with indication of the position of the event site in the analysed image. A total image and an image sequence with image sections of the vent site are then transmitted to a central station and reproduced at the central station as an endless sequence in quick-motion mode. Event warnings with all relevant data can be blended into electronic maps at the central station. Cross-bearing is made possible by blending event warnings from adjacent monitoring sites. False alarms are minimized in that known false alarm sources are marked as exclusion zones in reference images.

Abstract translation: 监测领土以识别森林和地面火灾需要复杂的自动和人为辅助进程，最终必须包括对干预力的控制。 公开的是对领土进行集中监测的过程。 安装在监控点的可旋转和可倾斜的摄像机提供重叠观察部门的图像。 在每个观察扇区中，以对应于火和烟动力学的间隔拍摄包括多个图像的图像序列。 现场图像处理软件提供事件警告，指示分析图像中事件站点的位置。 然后将具有通气部位的图像部分的总图像和图像序列发送到中心站，并且在中心站处以快速运动模式中的循环序列再现。 有关所有相关数据的事件警告可以混合到中心站的电子地图中。 通过混合来自相邻监测点的事件警告，可以实现交叉轴承。 因为已知的假警报源在参考图像中被标记为排除区域，所以将最小化的错误警报最小化。

公开(公告)号：US08368757B2

公开(公告)日：2013-02-05

申请号：US11791169

申请日：2005-10-20

Applicant: Günter Gräser ,  Andreas Jock ,  Uwe Krane ,  Hartmut Neuss ,  Holger Vogel ,  Volker Mertens ,  Jorg Knollenberg ,  Thomas Behnke ,  Ekkehard Kürt

Inventor： Günter Gräser ,  Andreas Jock ,  Uwe Krane ,  Hartmut Neuss ,  Holger Vogel ,  Volker Mertens ,  Jorg Knollenberg ,  Thomas Behnke ,  Ekkehard Kürt

IPC: H04N7/18

CPC classification number: G08B17/005 ,  A62C3/0271 ,  G08B17/125

Abstract: Disclosed are processes for the centralised monitoring of territories to recognize forest and surface fires. A swiveling and tiltable camera installed at a monitoring site supplies images of overlapping observation sectors. In each observation sector a sequence of images includes a plurality of images is taken, at an interval which corresponds to fire and smoke dynamics. An on-site image-processing software supplies event warnings with indication of the position of the event site in the analysed image. A total image and an image sequence with image sections of the event site are then transmitted to a central station and reproduced at the central station as a continuous sequence in quick-motion mode. Event warnings with relevant data are blended into electronic maps at the central station. Cross-bearing is made possible by blending event warnings from adjacent monitoring sites. False alarms are minimized by marking known false alarm sources as exclusion zones.

Abstract translation: 公开的是集中监测领土以识别森林和地面火灾的过程。 安装在监控点的可旋转和可倾斜的摄像机提供重叠观察部门的图像。 在每个观察扇区中，以对应于火和烟气动力学的间隔拍摄多个图像序列。 现场图像处理软件提供事件警告，指示分析图像中事件站点的位置。 然后将具有事件站点的图像部分的总图像和图像序列作为快速运动模式中的连续序列发送到中心站并在中心站再现。 有关相关数据的事件警告会混合到中央电视台的电子地图中。 通过混合来自相邻监测点的事件警告，可以实现交叉轴承。 将已知的虚假警报源标记为排除区，可以最大限度地减少错误警报。