Paavo Nevalainen

Arctic Soil Hydraulic Conductivity and Soil Type Recognition Based on Aerial Gamma-Ray Spectroscopy and Topographical Data

A central characteristic of soil in the arctic is its load bearing capacity since that property influences forest harvester mobility, flooding dynamics and infrastructure potential. The hydraulic conductivity has the greatest dynamical influence to bearing capacity and hence is essential to measure or estimate. In addition, the arctic soil type information is needed in many cases, e.g. in roads and railways building planning. In this paper we propose a method for hydraulic conductivity estimation via linear regression on aerial gamma-ray spectroscopy and publicly available topographical data with derived elevation based features. The same data is also utilized for the arctic soil type recognition, both logistics regression and nearest neighbor classification results are reported. The classification results for logistic regression resulted in 44.5% prediction performance and 50.5% for 8-nearest neighbor classifier respectively. Linear regression results for estimating the hydraulic conductivity of the soil resulted in C-index value of 0.63. The hydraulic conductivity and soil type estimation results are promising and the proposed topographic elevation features are apparently new for remote sensing community and should also have a wider general interest.

Predicting Water Permeability of the Soil Based on Open Data

Water permeability is a key concept when estimating load bearing capacity, mobility and infrastructure potential of a terrain. Northern sub-arctic areas have rather similar dominant soil types and thus prediction methods successful at Northern Finland may generalize to other arctic areas. In this paper we have predicted water permeability using publicly available natural resource data with regression analysis. The data categories used for regression were: airborne electro-magnetic and radiation, topographic height, national forest inventory data, and peat bog thickness. Various additional features were derived from original data to enable better predictions. The regression performances indicate that the prediction capability exists up to 120 meters from the closest direct measurement points. The results were measured using leave-one-out cross-validation with a dead zone between the training and testing data sets.

Detecting Terrain Stoniness From Airborne Laser Scanning Data

Three methods to estimate the presence of ground surface stones from publicly available Airborne Laser Scanning (ALS) point clouds are presented. The first method approximates the local curvature by local linear multi-scale fitting, and the second method uses Discrete-Differential Gaussian curvature based on the ground surface triangulation. The third baseline method applies Laplace filtering to Digital Elevation Model (DEM) in a 2 m regular grid data. All methods produce an approximate Gaussian curvature distribution which is then vectorized and classified by logistic regression. Two training data sets consisted of 88 and 674 polygons of mass-flow deposits, respectively. The locality of the polygon samples is a sparse canopy boreal forest, where the density of ALS ground returns is sufficiently high to reveal information about terrain micro-topography. The surface stoniness of each polygon sample was categorized for supervised learning by expert observation on the site. The leave-pair-out (L2O) cross-validation of the local linear fit method results in the area under curve A U C = 0 . 74 and A U C = 0 . 85 on two data sets, respectively. This performance can be expected to suit real world applications such as detecting coarse-grained sediments for infrastructure construction. A wall-to-wall predictor based on the study was demonstrated.

Estimating the Rut Depth by UAV Photogrammetry

The rut formation during forest operations is an undesirable phenomenon. A methodology is being proposed to measure the rut depth distribution of a logging site by photogrammetric point clouds produced by unmanned aerial vehicles (UAV). The methodology includes five processing steps that aim at reducing the noise from the surrounding trees and undergrowth for identifying the trails. A canopy height model is produced to focus the point cloud on the open pathway around the forest machine trail. A triangularized ground model is formed by a point cloud filtering method. The ground model is vectorized using the histogram of directed curvatures (HOC) method to produce an overall ground visualization. Finally, a manual selection of the trails leads to an automated rut depth profile analysis. The bivariate correlation (Pearson’s r) between rut depths measured manually and by UAV photogrammetry is r = 0.67 . The two-class accuracy a of detecting the rut depth exceeding 20 cm is a = 0.65 . There is potential for enabling automated large-scale evaluation of the forestry areas by using autonomous drones and the process described.

Estimating the prediction performance of spatial models via spatial k-fold cross validation

ABSTRACT In machine learning, one often assumes the data are independent when evaluating model performance. However, this rarely holds in practice. Geographic information datasets are an example where the data points have stronger dependencies among each other the closer they are geographically. This phenomenon known as spatial autocorrelation (SAC) causes the standard cross validation (CV) methods to produce optimistically biased prediction performance estimates for spatial models, which can result in increased costs and accidents in practical applications. To overcome this problem, we propose a modified version of the CV method called spatial k-fold cross validation (SKCV), which provides a useful estimate for model prediction performance without optimistic bias due to SAC. We test SKCV with three real-world cases involving open natural data showing that the estimates produced by the ordinary CV are up to 40% more optimistic than those of SKCV. Both regression and classification cases are considered in our experiments. In addition, we will show how the SKCV method can be applied as a criterion for selecting data sampling density for new research area.

Video based Swimming Analysis for Fast Feedback

This paper proposes a digital camera based swimming analysis system for athletic use with a low budget. The recreational usage is possible during the analysis phase, and no alterations of the pool environment are needed. The system is of minimum complexity, has a real-time feedback mode, uses only underwater cameras, is flexible and can be installed in many types of public swimming pools. Possibly inaccurate camera placement poses no problem. Both commercially available and tailor made software were utilized for video signal collection and computational analysis and for providing a fast visual feedback for swimmers to improve the athletic performance. The small number of cameras with a narrow overlapping view makes the conventional stereo calibration inaccurate and a direct planar calibration method is proposed in this paper instead. The calibration method is presented and its accuracy is evaluated. The quick feedback is a key issue in improving the athletic performance. We have developed two indicators, which are easy to visualize. The first one is the swimming speed measured from the video signal by tracking a marker band at the waist of the swimmer, another one is the rudimentary swimming cycle analysis focusing to the regularity of the cycle.

Real-Time Swimmer Tracking on Sparse Camera Array

A swimmer detection and tracking is an essential first step in a video-based athletics performance analysis. A real-time algorithm is presented, with the following capabilities: performing the planar projection of the image, fading the background to protect the intimacy of other swimmers, framing the swimmer at a specific swimming lane, and eliminating the redundant video stream from idle cameras. The generated video stream is a basis for further analysis at the batch-mode. The geometric video transform accommodates a sparse camera array and enables geometric observations of swimmer silhouette. The tracking component allows real-time feedback and combination of different video streams to a single one. Swimming cycle registration algorithm based on markerless tracking is presented. The methodology allows unknown camera positions and can be installed in many types of public swimming pools.

Parallel applications and on-chip traffic distributions: Observation, implication and modelling

We study the traffic characteristics of parallel and high performance computing applications in this paper. Applications that utilize multiple cores are more and more common nowadays due to the emergence of multicore processors. However the design nature of single-threaded applications and multi-threaded applications can vary significantly. Furthermore the on-chip communication profile of multicore systems should be analysed and modelled for characterization and simulation purposes. We investigate several applications running on a full system simulation environment. The on-chip communication traces are gathered and analysed. We study the detailed low-level profiles of these applications. The applications are categorized into different groups according to various parallel programming paradigms. We discover that the trace data follow different parameters of power-law model. The problem is solved by applying least-squares linear regression. We propose a generic synthetic traffic model based on the analysis results.

Detecting stony areas based on ground surface curvature distribution

Presence of ground surface stones is one indicator of economically important landmass deposits in the Arctic. The other indicator is a geomorphological category of the area. This work shows that ground stoniness can be automatically predicted with practical accuracy. Northern forests have less biomass and foliage, thus direct analysis of stoniness is possible from airborne laser scanning (ALS) data. A test set of 88 polygons covering 3.3 km2 was human-classified and a method was developed to perform the stoniness classification over this set. The local curvature of the surface is approximated directly from the point cloud data without generating the Digital Terrain Model (DTM). The method performs well with area under curve AUC = 0.85 from Leave-Pair-Out cross-validation, and is rather insensitive to missing data, moderate forest cover and double-scanned areas.

Wheel rut measurements by forest machine-mounted LiDAR sensors – accuracy and potential for operational applications?

ABSTRACT Soil rutting caused by forest operations has negative economic and ecological effects and thus limits for rutting are set by forest laws and sustainability criteria. Extensive data on rut depths are necessary for post-harvest quality control and development of models that link environmental conditions to rut formation. This study explored the use of a Light Detection and Ranging (LiDAR) sensor mounted on a forest harvester and forwarder to measure rut depths in real harvesting conditions in Southern Finland. LiDAR-derived rut depths were compared to manually measured rut depths. The results showed that at 10–20 m spatial resolution, the LiDAR method can provide unbiased estimates of rut depth with root mean square error (RMSE) < 3.5 cm compared to the manual rut depth measurements. The results suggest that a LiDAR sensor mounted on a forest vehicle can in future provide a viable method for the large-scale collection of rut depth data as part of normal forestry operations.