变化检测是指针对不同时相的同一地区的两幅或者多幅遥感图像，进行对比分析，提取出该地区地物随时间发生的变化信息。在森林资源调查等多个领域中，遥感影像变化检测得到了越来越多的人重视。同时，2013年我国发射了GF-1卫星，其获取的多光谱遥感影像适用于林地变化检测。因此，本文在研究分析国内外在变化检测研究成果的基础上，选取了黑龙江省牡丹江市八面通林业局为研究区域，并收集了研究区域内两景不同时相高分1号影像数据进行面向对象的变化检测。本文具体开展了下面几方面的工作： （1）对传统基于像元的和面向对象的分类方法进行了全面的对比分析，阐述了各自的优缺点，并对面向对象分类的主要步骤如影像分割及影像对象分类等重要步骤进行了详细的论述说明。同时，通过实验对面向对象分析问题中的尺度选择进行了分析说明。 （2）对现有常见的变化检测方法进行了归纳和总结，并分析了多种方法进行变化检测的优劣性。 （3）通过对高分一号影像数据分别进行传统的基于像元的分类以及基于面向对象的分类的实验结果的分析，可以获得面向对象分类精度更高的结论。 （4）对前后两期高分一号影像数据进行面向对象的分类后，对分类结果进行变化检测。通过目视解译进行精度检验，发现检测结果良好。

Change detection means to extract features of changes over time by comparative analysis with multiple remote sensing images of the same area for a different time. Remote sensing image change detection has been paid more and more attention in many fields such as forest resources investigation. Meanwhile, China launched the GF-1 satellite in 2013, and its acquisition of multi spectral remote sensing image is suitable for forest change detection. Therefore, this paper through a comprehensive analysis and summarization of research achievements about change detection studied the information extraction of forest change information, and selected Bamiantong Forestry Bureau, Mudanjiang City, Heilongjiang Province as the research area, and collected two images of GF-1 in different times within the study region to change detection of the forest with object-oriented method. This paper carries out the following aspects of work: (1) Comprehensive comparative analysis of the advantages and disadvantages of the traditional pixel-based classification method and object-oriented classification method. Based on the inherent defects of the traditional classification methods, apply the object-oriented thinking into the extraction of target information, and elaborates some important parts such as image segmentation, feature extraction and image object classification in the object-oriented classification method. Experimental analysis and instructions are also conducted to solve scale effect problem in object-oriented information extraction. (2) Summarized the existing common change detection methods and analyzed the advantages and disadvantages of various methods. (3) Through the analysis of the experimental results by the traditional pixel based classification and based on the object-oriented classification methods, we can get the conclusion that the object-oriented classification accuracy is higher. (4) Detected the changes of the object-oriented classification results, and the detection result is relatively accurate by the analysis of visual interpretation.