传统的像素级变化检测对辐射校正及阈值选择要求较高，因而在实际应用中受到诸多限制。在分析多尺度分割的基础上，提出了一种目标级的变化检测方法。分别利用粗、细尺度对各时相遥感图像的融合图像进行面向对象分割，以获取不同尺寸的目标区域，构造目标的特征进行向量分析得到差异图，并定义变化信息的强度，再利用多值逻辑理论将粗、细尺度下的检测结果进行决策级融合。实验结果表明，与传统的像素级检测方法相比，该方法受辐射差异影响小，检测精度更高，且检测结果对变化强度的衡量准确，能对应于有一定物理意义的目标变化。

The traditional pixellevel change detection algorithms have the disadvantage of high requirements for radiometric correction accuracy and threshold selectionwhich may limit their applications.An analysis was made to the multiscale segmentation methodand an objectlevel algorithm was proposed based on it.The fused image of the remote sensing images at different time phases was segmented by using objectoriented method in coarse and fine scales respectively to capture object areas of different sizes.Discrepancy image was obtained after analyzing of characteristics vectorsand the intensity of the changed information was defined.Thenthe decisionlevel fusion was implemented using the measurement results of the coarse and fine scales based on multivalued logic theory.Experiments indicate thatcompared with traditional pixellevel change detection algorithmsthe algorithm is less influenced by radiometric discrepancyhas higher detection accuracyand can evaluate the changed intensity accurately.