Urban tree generator: spatio-temporal and generative deep learning for urban tree localization and modeling
Urban tree generator: spatio-temporal and generative deep learning for urban tree localization and modeling
复制标题
DOI：
10.1007/s00371-022-02526-x
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
A. Firoze;Bedrich Benes;Daniel G. Aliaga
中科院分区：
文献类型：
--
作者：
A. Firoze;Bedrich Benes;Daniel G. Aliaga
我们提出了一种基于视觉的算法，该算法使用时空卫星图像、模式识别、过程建模和深度学习来在城市环境中执行树木定位。我们的方法解决了两个主要挑战。首先，高精度的自动化城市规模的树木定位通常需要大量的采集/用户干预。其次，来自卫星的植被指数分割方法需要手动阈值，这在不同的地理区域中是不同的，并且在具有不同地形、几何形状、海拔和树冠的城市中不稳定。在我们的工作中，我们通过使用12个月的卫星快照来弥补视觉细节的缺乏，并将城市划分为各种植被群。然后，我们使用多个基于GAN的网络通过程序化地识别分割区域内的放置模式来种植树木。我们提出了全面的实验在四个城市（芝加哥，奥斯汀，印第安纳波利斯，拉各斯），实现树木计数准确率为87- 97%。最后，我们证明了从每个模型（在特定城市训练）积累的知识可以转移到不同的城市。
We present a vision-based algorithm that uses spatio-temporal satellite imagery, pattern recognition, procedural modeling, and deep learning to perform tree localization in urban settings. Our method resolves two primary challenges. First, automated city-scale tree localization at high accuracy typically requires significant acquisition/user intervention. Second, vegetation-index segmentation methods from satellites require manual thresholding, which varies across geographic areas, and are not robust across cities with varying terrain, geometry, altitude, and canopy. In our work, we compensate for the lack of visual detail by using satellite snapshots across twelve months and segment cities into various vegetation clusters. Then, we use multiple GAN-based networks to plant trees by recognizing placement patterns inside segmented regions procedurally. We present comprehensive experiments over four cities (Chicago, Austin, Indianapolis, Lagos), achieving tree count accuracies of 87–97%. Finally, we show that the knowledge accumulated from each model (trained on a particular city) can be transferred to a different city.