The detection of strategically important geospatial objects in remote sensing images is one of the important tasks for interpreting satellite images. Identification and mapping of objects such as tank, airplane, roads, buildings, etc. from remotely sensed images has gained much research and exploration in both defense and civilian applications. Detection and identification of buildings become more challenging when analyzed in forest neighborhood environment. The presence of dense trees in the surroundings increases the complexity and the rates of both false positives and false negatives. In the current study, an integration of image pan-sharpening (Gram-Schmidt) and sub-pixel image classification (Linear Mixture Model) algorithm is used for identification and mapping of building objects in two high resolution remote sensing satellite imagery (IKONOS and Worldview-2). Building objects having large, medium and small geometric size are selected from both the satellite imagery in strategically challenged forest neighborhood. The capability of pan-sharpening and sub-pixel classification techniques are jointly used for detection of building objects. The accuracy of target detection has been evaluated qualitatively (visual interpretation) and quantitatively (statistical analysis). Results on selected datasets show that the proposed combination of pan-sharpening and sub-pixel classification offers higher correctness in identification of building than other contemporary techniques. Although, significant improvement is noticed in results obtained for both the satellite imagery. Irrespective of having lower spatial resolution, after pan-sharpening, IKONOS datasets are found to be slightly more accurate in building identification in comparison to Worldview-2 datasets.

遥感影像中具有战略意义的地理空间目标的检测是解译卫星影像的重要任务之一。从遥感图像对坦克、飞机、道路、建筑物等物体进行识别和制图，在国防和民用领域都得到了大量的研究和探索。在森林社区环境中进行分析时，建筑物的检测和识别变得更具挑战性。周围茂密的树木增加了复杂性和误报率和误报率。在目前的研究中，图像泛锐化（Gram-Schmidt）和亚像素图像分类（线性混合模型）的集成算法用于识别和映射两个高分辨率遥感卫星图像（IKONOS 和 Worldview-2）中的建筑物对象。从具有战略挑战性的森林社区的卫星图像中选择具有大、中和小几何尺寸的建筑对象。全色锐化和亚像素分类技术的能力被联合用于建筑物体的检测。对目标检测的准确性进行了定性（视觉解释）和定量（统计分析）评估。选定数据集的结果表明，与其他当代技术相比，所提出的全色锐化和亚像素分类的组合在建筑物识别方面提供了更高的正确性。尽管如此，在为这两个卫星图像获得的结果中都注意到了显着的改进。无论空间分辨率较低，在全色锐化后，与 Worldview-2 数据集相比，IKONOS 数据集在建筑物识别方面的准确度略高。