摄影测量与深度学习

Photogrammetry and Deep Learning

深度学习正逐渐占领与"学习"相关的诸多研究领域,也对摄影测量这门学科造成冲击和促进。根据摄影测量学的定义:"利用光学像片研究被摄物体的形状、位置、大小、特性及相互位置关系",其研究对象包括几何与语义。本文从这两个方面回顾和探讨深度学习目前的应用现状,并对其影响下的摄影测量的发展进行展望。在几何上,基于卷积神经元网络的学习架构已经广泛用于图像匹配、SLAM及三维重建,取得了较好的效果,但仍需进一步改进。在语义上,由于传统的手工设计方法未能将语义信息以工程化的形式确定并生成类似4D产品的各类语义"专题图",语义部分长期受到忽视。深度学习强大的泛化能力、对任意函数的拟合能力及极高的稳定性,正使得专题图的自动制作成为可能。笔者通过道路网、建筑物、作物分类等应用实例,回顾已经取得的研究成果,并预计:利用光学像片生成高精度的语义专题图,在不远的未来即将实现;并可能成为摄影测量的一类标准产品。最后,针对几何和语义,分别介绍了笔者的两个相关研究:基于深度学习的航空图像匹配以及基于3D卷积神经元网络的精细农作物分类专题图自动提取。

Deep learning has become popular and the mainstream in types of researches related to learning,and has shown its impact on photogrammetry.According to the definition of photogrammetry,a subject that researches shapes,locations,sizes,characteristics and inter-relationships of real objects from optical images,photogrammetry considers two aspects,geometry and semantics.From the two aspects,we review the history of deep learning and discuss its current applications on photogrammetry,and forecast the future development of photogrammetry.Ingeometry,the deep convolutional neural network（CNN）has been widely applied in stereo matching,SLAM and 3 Dreconstruction,and has made some effect but needs more improvement.In semantics,conventional empirical and handcrafted methods have failed to extract the semantic information accurately and failed to produce types of ＂semantic thematic map＂as 4 D productions（DEM,DOM,DLG,DRG）of photogrammetry,which causes the semantic part of photogrammetry be ignored for a long time.The powerful generalization capacity,ability to fit any functions and stability under types of situations of deep leaning is making the automated production of thematic maps possible.We review the achievements that have been obtained in road network extraction,building detection and crop classification,etc.,and forecast that producing high-accuracy semantic thematic maps directly from optical images will become reality and these maps will become a type of standard products of photogrammetry.At last,we introduce two current researches related to geometry and semantics respectively.One is stereo matching of aerial images based on deep learning and transfer learning;the other is fine crop classification from satellite special-temporal images based on 3 DCNN.