公开(公告)号：US20160363653A1

公开(公告)日：2016-12-15

申请号：US15106700

申请日：2015-02-10

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Tianxu ZHANG ,  Heng YAO ,  Peng JIANG ,  Sufei FAN ,  Yimeng CHEN ,  Wenxuan MA ,  Longwei HAO ,  Zhihui YANG

IPC: G01S7/48 ,  G01S17/93 ,  G01S17/02 ,  G01S17/89

CPC classification number: G01S7/4802 ,  G01S17/023 ,  G01S17/107 ,  G01S17/89 ,  G01S17/933 ,  G06K9/0063 ,  G06K9/00637

Abstract: The present invention provides an above-ground building recognition method, including the following steps: (1) taking an infrared image of the ground from the air; (2) performing detection and positioning in the infrared image to determine a suspected target; (3) aiming at the suspected target to perform laser imaging; (4) performing range gating on a laser image to filter out foreground and background interference; and (5) extracting a shape feature of the suspected target from the laser image with interference filtered out, and taking the shape feature as a target matching element to perform matching with a target shape feature template, so as to recognize the target. In the method of the present invention, laser imaging is integrated into infrared imaging target positioning, so that an advantage of a large range of infrared imaging is utilized, and three-dimensional range information of laser imaging is also utilized, thereby effectively improving the precision of positioning a building.

Abstract translation: 本发明提供了一种地面建筑识别方法，包括以下步骤：（1）从空中拍摄地面的红外图像; （2）执行红外图像的检测和定位以确定可疑目标; （3）瞄准可疑目标进行激光成像; （4）对激光图像进行范围选通，滤除前景和背景干扰; 并且（5）从具有被滤除的干扰的激光图像中提取可疑目标的形状特征，并且将形状特征作为目标匹配元素来执行与目标形状特征模板的匹配，以便识别目标。 在本发明的方法中，激光成像被集成到红外成像目标定位中，因此利用了大范围的红外成像的优点，并且还利用了激光成像的三维范围信息，从而有效地提高了精度 定位建筑物。