Detecting Historical Terrain Anomalies With UAV-LiDAR Data Using Spline-Approximation and Support Vector Machines

Abstract

The documentation of historical remains and cultural heritage is of great importance to preserve historical knowledge. Many studies use low-resolution airplane-based laser scanning and manual interpretation for this purpose. In this study, a concept to automatically detect terrain anomalies in a historical conflict landscape using high-resolution UAV-LiDAR data was developed. We applied different ground filter algorithms and included a spline-based approximation step in order to improve the removal of low vegetation. Due to the absence of comprehensive labeled training data, a one-class support vector machine algorithm was used in an unsupervised manner in order to automatically detect the terrain anomalies. We applied our approach in a study site with different densities of low vegetation. The morphological ground filter was the most suitable when dense near-ground vegetation is present. However, with the use of the spline-based processing step, all filters used could be significantly improved in terms of the F1-score of the classification results. It increased by up to 42 percentage points in the area with dense low vegetation and by up to 14 percentage points in the area with sparse low vegetation. The completeness (recall) reached maximum values of 0.8 and 1.0, respectively, when taking into account the results leading to the highest F1score for each filter. Therefore, our concept can support on-site field prospection.

A Survey of Object Detection for UAVs Based on Deep Learning

“…Laser sensor: The principle of the laser sensor is basically the same as the ultrasonic sensor, except for the different emitted signal. A laser source is emitted by the laser ranging sensor at the speed of light, which makes the signal frequency much higher than the ultrasonic sensor [30]. Its disadvantages are high price, small measurement range, and the ability to scan.…”

Color-Based Point Cloud Classification Using a Novel Gaussian Mixed Modeling-Based Approach versus a Deep Neural Network

“…Many algorithms have been developed for point cloud segmentation, filtering, or classification. Especially where the acquisition of terrain data (ground filtering) is concerned, some special filters have been proposed, e.g., in [19][20][21][22][23]. However, as even the extensive literature review presented in [24] illustrates, RGB color is almost unused for landscape point cloud classification (only a single study with a highly specific purpose has been included in that review [25]).…”