應用深度學習於空載光達及空載影像之地物分類

Deep Learning-Based Land Cover Classification Using Airborne Lidar and Aerial Imagery

楊筑鈞(Chu-Chun Yang)

指導教授 ： 張智安

國立交通大學/工學院/土木工程系所/碩士(2019年)

摘要

地物分類是一個重要的議題，可從地物分佈中萃取有助理解影響氣候、環境或社會結構的相關因子。地物類別可以從光譜、幾何或資料融合中獲得，其中光譜和幾何特徵可以從光達點雲及航測影像提供。本研究採用監督式深度學習方法進行地物分類，深度學習方法能夠透過非線性模型，將原始數據轉換為更抽象的層次來學習更複雜的模型。在傳統的分類算法中，分類過程包括數據輸入、特徵提取和分類器分類，在特徵提取的步驟需要透過預先已有的知識來定義適合特定分類任務的良好特徵。與傳統分類不同，深度學習算法將特徵視為未知數，並結合特徵提取和分類器分類的過程。本研究之目的為比較不同特徵組合與資料型態於深度學習之分類精度。研究的貢獻有二，一為分析及比較網格式資料及點資料對於深度學習用於地物分類之影響，二為分析及比較光譜資訊及形狀資訊對深度學習用於地物分類之影響。
本研究分別採用FCN-8s和PointNet兩個深度學習網絡，將兩個深度學習網絡分別應用於影像資料和點雲資料的分類。研究可以分為兩個實驗。在第一個實驗中，將4種資訊組合的影像資料於FCN-8s上進行訓練。在第二個實驗中，將4種資訊組合設定的點在PointNet上進行訓練用。影像資料有5種屬性，即顏色資訊（RGB），數值地表模型（DSM）和強度資訊（I）。點雲資料則有7個屬性，空間坐標（XYZ），顏色資訊（RGB）和強度資訊（I）。為了比較光譜資訊和形狀資訊對結果的影響。影像資料的4種資訊組合是RGB、RGBI、RGBDSM、RGBDSMI。 點雲資料的4種資訊組合則為XYZ、XYZI、XYZRGB、XYZRGBI。
此研究將主要地物類別分樹木、建築物和道路。實驗結果顯示，點雲式資料相較網格式資料能更完整的描述物體的三維形狀資訊，因此點雲式分類較網格式分類有更佳的精度。此外，光達強度資訊能有效地從其他類別中識別道路區域，而數值地表模型能夠克服影像中高樓層建築物高差位移之影響。

關鍵字

地物分類 ； 深度學習 ； 空載光達 ； 空載影像 ； 幾何資訊 ； 光譜資訊

並列摘要

Land cover classification has always been a critical issue. People tried to learn information from the distribution of land cover; as it may affect climate, environment or structure of society. Land cover information can be extracted from spectral feature, geometrical feature or data fusion approach. Spectral and geometrical features can be provided from airborne LiDAR and aerial imagery, respectively. The supervised deep learning method is applied to this research for land cover classification. Deep learning is able to learn more complex scenes by the means of converting the original observation (i.e. lidar or image) to higher abstract level (i.e., features) with a non-linear model. In traditional classification algorithm, the classification process includes data input, features extraction and classifier operation. A sufficient feature is defined to fit in a specific classification task by knowing the pre-knowledge. Unlike traditional classification, deep learning algorithm assumes that the features are unknown variables and combines the process of features extraction and classifier operation simultaneously. This research analyses the impact of different input datasets for classification and compares different deep learning algorithms. The contribution of the research is twofold. First, analyze and compare the influence on land cover classification using deep learning method by raster data and point cloud data. Second, analyze and compare the influence on land cover classification using deep learning method by spectral and shape features.
This research adopted two deep learning networks, FCN-8s (pixel-based classification) and PointNet (point-based classification). The FCN-8s utilized interpolated 2D grid while PointNet utilized a reshaped 2D matrix in classification. The input data set for FCN-8s were RGB color information (RGB), DSM information (DSM) and intensity map (I). The input data set for PointNet were XYZ coordinates (XYZ), RGB color information (RGB) and intensity value (I). In order to compare how spectral and shape features will effect on the result. Four combinations with different observations were designed to evaluate the impact of input dataset for classification. Four combinations for FCN-8s were RGB, RGBI, RGBDSM, RGBDSMI while the other four combinations for PointNet were XYZ, XYZI, XYZRGB, XYZRGBI.
The research classified landcovers into 3 main categories, including tree, building, and road. Two experiments were applied to two different deep learning networks using airborne images and lidar points. The results showed that shape information is more useful than spectral information in land cover classification. Since point-based classification is able to describe more complete shape information than pixel-based classification, point-based classification has better results than pixel-based classification. Moreover, the intensity information is more useful for recognizing the road from other categories, and DSM information is able to correct relief displacement caused by high buildings.

並列關鍵字

land cover classification ； deep learning ； airborne lidar ； aerial image ； shape information ； spectral information

參考文獻

Arief, H., Strand, G. H., Tveite, H., Indahl, U., 2018. Land Cover Segmentation of Airborne LiDAR Data Using Stochastic Atrous Network. Remote Sensing 10, 973.

Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., Nemani, R., 2015. DeepSat: a learning framework for satellite imagery. Proceedings of the 23rd International Conference on Advances in Geographic Information Systems. ACM, 37.

Bounoua, L., DeFries, R., Collatz, G. J., Sellers, P., Khan, H., 2002. Effects of land cover conversion on surface climate. Climatic Change 52, 29-64.

Conneau, A., Schwenk, H., Barrault, L., Lecun, Y., 2016. Very deep convolutional networks for natural language processing. arXiv preprint arXiv:1606.01781.

Eigen, D., Fergus, R., 2015. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2650-2658.