Land Cover Classification Using SegNet with Slope, Aspect, and Multidirectional Shaded Relief Images Derived from Digital Surface Model

Abstract

Most object detection, recognition, and classification are performed using optical imagery. Images are unable to fully represent the real-world due to the limited range of the visible light spectrum reflected light from the surfaces of the objects. In this regard, physical and geometrical information from other data sources would compensate for the limitation of the optical imagery and bring a synergistic effect for training deep learning (DL) models. In this paper, we propose to classify terrain features using convolutional neural network (CNN) based SegNet model by utilizing 3D geospatial data including infrared (IR) orthoimages, digital surface model (DSM), and derived information. The slope, aspect, and shaded relief images (SRIs) were derived from the DSM and were used as training data for the DL model. The experiments were carried out using the Vaihingen and Potsdam dataset provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) through the International Society for Photogrammetry and Remote Sensing (ISPRS). The dataset includes IR orthoimages, DSM, airborne LiDAR data, and label data. The motivation of utilizing 3D data and derived information for training the DL model is that real-world objects are 3D features. The experimental results demonstrate that the proposed approach of utilizing and integrating various informative feature data could improve the performance of the DL for semantic segmentation. In particular, the accuracy of building classification is higher compared with other natural objects because derived information could provide geometric characteristics. Intersection-of-union (IoU) of the buildings for the test data and the new unseen data with combining all derived data were 84.90% and 52.45%, respectively.

Recognizing Zucchinis Intercropped with Sunflowers in UAV Visible Images Using an Improved Method Based on OCRNet

“…Therefore, the training dataset was generated by cropping the orthoimage line by line with a certain overlap rate. The way of making a dataset is also an effective data augmentation technique [42,43]. When cropping the orthoimage of the training area, an overlap area of 75% was set.…”

Semantic Segmentation and Building Extraction from Airborne LiDAR Data with Multiple Return Using PointNet++

“…The threshold to be considered accpetable prediction is 0.5. If IoU is larger than 0.5, it is normally considered a good prediction [15,31]. The results show that LiDAR data with two returns and appropriate point density could lead to improved results on the building boundaries.…”

“…Since each feature reflects the unique physical property of the objects, multi-dimensional features including entropy, height variation, intensity, normalized height, and standard deviation extracted from LiDAR data were utilized for building detection with convolutional neural network (CNN) model [14]. Combining slope, aspect, and shaded-relief generated from DSM with infrared (IR) images could improve semantic segmentation performance of the DL model [15].…”

A Convolutional Neural Network‐Based Classification and Decision‐Making Model for Visible Defect Identification of High‐Speed Train Images

“…CNNs, a family of algorithms especially suited to image analysis, have been applied in different ways, including image classification, object detection, and semantic image segmentation. Due to its strong ability of automatically learning high-level feature representations of images, CNNs can extract enough features for image classification [4][5][6][7] and perform better than traditional algorithms such as SIFT, HOG, and SURF. Moreover, it has the unique characteristic of preserving local image relations while performing dimensionality reduction.…”