Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery
Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery
复制标题
DOI：
--
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
E. Guirado;S. Tabik;D. Alcaraz‐Segura;J. Cabello;Francisco Herrera
中科院分区：
文献类型：
--
作者：
E. Guirado;S. Tabik;D. Alcaraz‐Segura;J. Cabello;Francisco Herrera
在许多领域，例如在土地利用规划和生物多样性保护方面，对准确的高分辨率土地覆盖图的需求日益增长。开发这类地图是使用基于对象的图像分析(OBIA)方法进行的，这种方法通常可以达到很好的精度，但需要很高的人工监督，并且一幅图像的最佳配置很难外推到另一幅图像。近年来，深度学习卷积神经网络(CNN)在计算机视觉领域中的目标识别领域取得了令人瞩目的成果。然而，它们在土地覆盖制图中还没有得到充分的探索，以检测具有高度生物多样性保护价值的物种。本文利用免费的高分辨率Google Earth TM图像，分析了基于CNN的植物物种检测方法的潜力，并与最新的Obia方法进行了客观比较。我们把检测到的酸枣莲花灌木作为案例研究，根据欧盟生境指令，它们被列为优先栖息地。实验结果表明，与基于OBIA的检测方法相比，基于CNN的检测模型结合了数据扩充、迁移学习和预处理，在较少的人工干预下获得了更高的检测性能，并且它从第一幅图像中获得的知识可以转移到其他图像上，从而使得检测过程非常快。所提供的方法可系统地复制用于其他物种的检测。
There is a growing demand for accurate high-resolution land cover maps in many fields, e.g., in land-use planning and biodiversity conservation. Developing such maps has been performed using Object-Based Image Analysis (OBIA) methods, which usually reach good accuracies, but require a high human supervision and the best configuration for one image can hardly be extrapolated to a different image. Recently, the deep learning Convolutional Neural Networks (CNNs) have shown outstanding results in object recognition in the field of computer vision. However, they have not been fully explored yet in land cover mapping for detecting species of high biodiversity conservation interest. This paper analyzes the potential of CNNs-based methods for plant species detection using free high-resolution Google Earth T M images and provides an objective comparison with the state-of-the-art OBIA-methods. We consider as case study the detection of Ziziphus lotus shrubs, which are protected as a priority habitat under the European Union Habitats Directive. According to our results, compared to OBIA-based methods, the proposed CNN-based detection model, in combination with data-augmentation, transfer learning and pre-processing, achieves higher performance with less human intervention and the knowledge it acquires in the first image can be transferred to other images, which makes the detection process very fast. The provided methodology can be systematically reproduced for other species detection.