Rotation-and-scale-invariant airplane detection in high-resolution satellite images based on deep-Hough-forests
Rotation-and-scale-invariant airplane detection in high-resolution satellite images based on deep-Hough-forests
复制标题
DOI：
10.1016/j.isprsjprs.2015.04.014
复制
发表时间：
2016-02
影响因子：
12.7
通讯作者：
Yongtao Yu;H. Guan;D. Zai;Zheng Ji
中科院分区：
文献类型：
--
作者：
Yongtao Yu;H. Guan;D. Zai;Zheng Ji
提出了一种旋转和尺度不变性的高分辨率卫星图像飞机目标检测方法。为了提高特征表示能力，创建了多层特征生成模型，以通过深度学习技术为局部图像块生成高阶特征表示。为了有效地估计飞机质心，Hough森林模型被训练以学习从高阶补丁特征到飞机存在于特定位置的概率的映射。为了处理不同方向的飞机，补丁方向的定义和集成到霍夫森林，以增加霍夫投票。尺度不变性是通过使用一组嵌入在Hough森林中的尺度因子来实现的。对Google Earth服务中采集的图像进行定量评估表明，该方法在检测任意方向和大小的飞机时，其完整性、正确性、质量和F1测度分别达到0.968、0.972、0.942和0.970。对比研究表明，该方法优于其他三种现有的方法在准确和完整地检测飞机在高分辨率遥感图像。
This paper proposes a rotation-and-scale-invariant method for detecting airplanes from high-resolution satellite images. To improve feature representation capability, a multi-layer feature generation model is created to produce high-order feature representations for local image patches through deep learning techniques. To effectively estimate airplane centroids, a Hough forest model is trained to learn mappings from high-order patch features to the probabilities of an airplane being present at specific locations. To handle airplanes with varying orientations, patch orientation is defined and integrated into the Hough forest to augment Hough voting. The scale invariance is achieved by using a set of scale factors embedded in the Hough forest. Quantitative evaluations on the images collected from Google Earth service show that the proposed method achieves a completeness, correctness, quality, and F1-measure of 0.968, 0.972, 0.942, and 0.970, respectively, in detecting airplanes with arbitrary orientations and sizes. Comparative studies also demonstrate that the proposed method outperforms the other three existing methods in accurately and completely detecting airplanes in high-resolution remotely sensed images.