Graphics Reference
In-Depth Information
Research on an Extracting Method to Assist Manual
Identification of Targets
Yue Shi and Guoying Zhang
School of Mechanical Electronic and Information Engineering, China University of Mining
and Technology, Beijing, China
{ shiyue1989 , zhangguoying1101}@163.com
Abstract. The interpretation of the target recognition in remote sensing image
is normally manually implemented by interpreters. In this essay, we propose to
analyze the method for rapid extraction of suspected targets (method that can be
used to assist manual interpretation) was proposed. The method is based on the
image gray-scale characteristics. First of all, resolution reduction and enhance-
ment should be used to preprocess the image. Then, through a series of means,
including binarization, erosion, big target extraction and dilation, suspected
targets are extracted. The experimental results show that the method can
effectively and quickly extract targets from the remote sensing image which
owns the features that the gray value of background area is mussy and the
object area is homogeneous.
Keywords: Remote sensing image, image processing and target extraction.
1 Introduction
The traditional ways to extract targets from remote sensing image mainly rely on the
manual operation of photographic interpreter. But manual methods have many defects
such as big workload and low efficiency. Furthermore, affected by the weather condi-
tion, quality of the camera equipments or visual angle, etc., the objects in remote
sensing image are different from the objects in the actual scene, which requires that
the photographic interpreter has a lot of skills and experience. Thus, training a profes-
sional photographic interpreter takes a lot of time and energy.
Since the 1970's, many countries around the world have heavily invested to the
study and the development of computer aided image interpretation system. Its
workflow is as the following: firstly, the image is processed by computer to exclude
the no value area and mark suspected objects. And then, the result image of the last
step is interpreted by photographic interpreter. The application of computer image
processing technology in remote sensing field greatly reduces the workload and im-
proves the working speed and the precision of the interpretation. With the rapid de-
velopment of the satellite remote sensing technology, satellites, the photos of which
have the resolution less than 1 mile, keep emerging. Those high resolution images
provide an objective foundation for object extraction method that is based on the gray
level characteristics.
 
Search WWH ::




Custom Search