Landscape Classification with Deep Neural Networks

Abstract

Abstract:The application of deep learning, specifically deep convolutional neural networks (DCNNs), to the classification of remotely-sensed imagery of natural landscapes has the potential to greatly assist in the analysis and interpretation of geomorphic processes. However, the general usefulness of deep learning applied to conventional photographic imagery at a landscape scale is, at yet, largely unproven. If DCNN-based image classification is to gain wider application and acceptance within the geoscience community, demonstrable successes need to be coupled with accessible tools to retrain deep neural networks to discriminate landforms and land uses in landscape imagery. Here, we present an efficient approach to train/apply DCNNs with/on sets of photographic images, using a powerful graphical method called a conditional random field (CRF), to generate DCNN training and testing data using minimal manual supervision. We apply the method to several sets of images of natural landscapes, acquired from satellites, aircraft, unmanned aerial vehicles, and fixed camera installations. We synthesize our findings to examine the general effectiveness of transfer learning to landscape-scale image classification. Finally, we show how DCNN predictions on small regions of images might be used in conjunction with a CRF for highly accurate pixel-level classification of images.

Quantifying Below-Water Fluvial Geomorphic Change: The Implications of Refraction Correction, Water Surface Elevations, and Spatially Variable Error

“…As such, it includes a broad range of algorithms, encompassing everything from simple linear regressions to deep learning-based neural networks [52]. The application of AI/ML for geomorphic error thresholding purposes is novel, with existing studies within freshwater settings applying it predominantly for classification of land cover types from image-derived parameters (e.g., [53][54][55][56]) or for the identification of other specific features of interest such as buildings (e.g., [57]) and invasive species (e.g., [58]). As such, our ultimate aim is to create the first high resolution, spatially continuous SfM-derived topographic change models in submerged fluvial environments constrained by spatially variable error estimates.…”

Assessment of a Smartphone-Based Camera System for Coastal Image Segmentation and Sargassum monitoring

“…Recently, deep learning has made a great deal of progress in natural image processing, as well as in remote-sensing image classification. Moreover, the performance of convolutional neural networks (CNNs) in scene classification or object detection [17,18] has been practically established. A CNN is a multi-layer artificial neural network with convolutional kernels, where each layer is a non-linear feature detector performing local processing of contiguous features within each layer, and it is developed by eliciting the function of the human brain [19].…”

“…Firstly, by sticky-edge adhesive superpixels partitioning, the original SolarCam images from the training data are over-segmented into several regions, which are used as the spatial processing units for CNN classification. The image is manually labelled by following a modified methodology from [18]. Next, transfer learning enables the retraining of the experimental network, based on MobileNet V2 convolutional neural network, described in Section 3.4.…”

Automated Discontinuity Detection and Reconstruction in Subsurface Environment of Mars Using Deep Learning: A Case Study of SHARAD Observation

“…With the advancement in powerful analytical approaches such as stereo topographic construction [5], the research communities would be benefited enormously by tracing the shape of and changes in the planetary surface. This enables the introduction of more sophisticated study tools such as virtual reality [6,7], numerical modeling [8,9], and surface dating [10,11].The recent developments in planetary surface research are moving towards the employment of high-end machine learning algorithms for many applications, such as the study of surface chronology based on automated crater counting [12], the classification of geomorphic features [13,14], and the detection of surface changes [15,16].The clues on planetary geological evolution can be traced by deep and shallow subsurface data, which are extracted either by gravitational measurement [17,18] or shallow surface electromagnetic scanning of orbital ground penetration radar (GPR) [19,20], as well as surface image analysis. Although the information achieved by subsurface sensing of the planetary mission is highly valuable, it should be noted that the interpretation of orbital GPR equipped in a planetary mission is usually more complicated compared to that of the surface imaging.…”

“…The recent developments in planetary surface research are moving towards the employment of high-end machine learning algorithms for many applications, such as the study of surface chronology based on automated crater counting [12], the classification of geomorphic features [13,14], and the detection of surface changes [15,16].…”