scholarly journals FEASIBILITY OF MULTISPECTRAL AIRBORNE LASER SCANNING FOR LAND COVER CLASSIFICATION, ROAD MAPPING AND MAP UPDATING

2017 ◽  
Vol XLII-3/W3 ◽  
pp. 119-122 ◽  
Author(s):  
L. Matikainen ◽  
K. Karila ◽  
J. Hyyppä ◽  
E. Puttonen ◽  
P. Litkey ◽  
...  
Keyword(s):  
Land Cover ◽  
Change Detection ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Land Cover Classification ◽  
Aerial Images ◽  
Multispectral Data ◽  
Airborne Laser ◽  
First Results ◽  
Road Mapping

This article summarises our first results and experiences on the use of multispectral airborne laser scanner (ALS) data. Optech Titan multispectral ALS data over a large suburban area in Finland were acquired on three different dates in 2015–2016. We investigated the feasibility of the data from the first date for land cover classification and road mapping. Object-based analyses with segmentation and random forests classification were used. The potential of the data for change detection of buildings and roads was also demonstrated. The overall accuracy of land cover classification results with six classes was 96 % compared with validation points. The data also showed high potential for road detection, road surface classification and change detection. The multispectral intensity information appeared to be very important for automated classifications. Compared to passive aerial images, the intensity images have interesting advantages, such as the lack of shadows. Currently, we focus on analyses and applications with the multitemporal multispectral data. Important questions include, for example, the potential and challenges of the multitemporal data for change detection.

scholarly journals MULTISPECTRAL AIRBORNE LASER SCANNING FOR AUTOMATED MAP UPDATING

2016 ◽  
Vol XLI-B3 ◽  
pp. 323-330 ◽  
Author(s):  
Leena Matikainen ◽  
Juha Hyyppä ◽  
Paula Litkey
Keyword(s):  
Change Detection ◽  
Laser Scanning ◽  
Point Clouds ◽  
Airborne Laser Scanning ◽  
Aerial Images ◽  
Sensor Technology ◽  
Classification Error ◽  
Surface Model ◽  
Airborne Laser ◽  
Map Updating

During the last 20 years, airborne laser scanning (ALS), often combined with multispectral information from aerial images, has shown its high feasibility for automated mapping processes. Recently, the first multispectral airborne laser scanners have been launched, and multispectral information is for the first time directly available for 3D ALS point clouds. This article discusses the potential of this new single-sensor technology in map updating, especially in automated object detection and change detection. For our study, Optech Titan multispectral ALS data over a suburban area in Finland were acquired. Results from a random forests analysis suggest that the multispectral intensity information is useful for land cover classification, also when considering ground surface objects and classes, such as roads. An out-of-bag estimate for classification error was about 3% for separating classes asphalt, gravel, rocky areas and low vegetation from each other. For buildings and trees, it was under 1%. According to feature importance analyses, multispectral features based on several channels were more useful that those based on one channel. Automatic change detection utilizing the new multispectral ALS data, an old digital surface model (DSM) and old building vectors was also demonstrated. Overall, our first analyses suggest that the new data are very promising for further increasing the automation level in mapping. The multispectral ALS technology is independent of external illumination conditions, and intensity images produced from the data do not include shadows. These are significant advantages when the development of automated classification and change detection procedures is considered.

scholarly journals MULTISPECTRAL AIRBORNE LASER SCANNING FOR AUTOMATED MAP UPDATING

2016 ◽  
Vol XLI-B3 ◽  
pp. 323-330 ◽  
Author(s):  
Leena Matikainen ◽  
Juha Hyyppä ◽  
Paula Litkey
Keyword(s):  
Change Detection ◽  
Laser Scanning ◽  
Point Clouds ◽  
Airborne Laser Scanning ◽  
Aerial Images ◽  
Sensor Technology ◽  
Classification Error ◽  
Surface Model ◽  
Airborne Laser ◽  
Map Updating

During the last 20 years, airborne laser scanning (ALS), often combined with multispectral information from aerial images, has shown its high feasibility for automated mapping processes. Recently, the first multispectral airborne laser scanners have been launched, and multispectral information is for the first time directly available for 3D ALS point clouds. This article discusses the potential of this new single-sensor technology in map updating, especially in automated object detection and change detection. For our study, Optech Titan multispectral ALS data over a suburban area in Finland were acquired. Results from a random forests analysis suggest that the multispectral intensity information is useful for land cover classification, also when considering ground surface objects and classes, such as roads. An out-of-bag estimate for classification error was about 3% for separating classes asphalt, gravel, rocky areas and low vegetation from each other. For buildings and trees, it was under 1%. According to feature importance analyses, multispectral features based on several channels were more useful that those based on one channel. Automatic change detection utilizing the new multispectral ALS data, an old digital surface model (DSM) and old building vectors was also demonstrated. Overall, our first analyses suggest that the new data are very promising for further increasing the automation level in mapping. The multispectral ALS technology is independent of external illumination conditions, and intensity images produced from the data do not include shadows. These are significant advantages when the development of automated classification and change detection procedures is considered.

scholarly journals TOWARDS AUTOMATIC SINGLE-SENSOR MAPPING BY MULTISPECTRAL AIRBORNE LASER SCANNING

2016 ◽  
Vol XLI-B3 ◽  
pp. 155-162 ◽  
Author(s):  
E. Ahokas ◽  
J. Hyyppä ◽  
X. Yu ◽  
X. Liang ◽  
L. Matikainen ◽  
...  
Keyword(s):  
Land Cover ◽  
Tree Species ◽  
Forest Inventory ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Ground Surface ◽  
Airborne Laser Scanning ◽  
Forest Mapping ◽  
Airborne Laser Scanner ◽  
Airborne Laser

This paper describes the possibilities of the Optech Titan multispectral airborne laser scanner in the fields of mapping and forestry. Investigation was targeted to six land cover classes. Multispectral laser scanner data can be used to distinguish land cover classes of the ground surface, including the roads and separate road surface classes. For forest inventory using point cloud metrics and intensity features combined, total accuracy of 93.5% was achieved for classification of three main boreal tree species (pine, spruce and birch).When using intensity features – without point height metrics - a classification accuracy of 91% was achieved for these three tree species. It was also shown that deciduous trees can be further classified into more species. We propose that intensity-related features and waveform-type features are combined with point height metrics for forest attribute derivation in area-based prediction, which is an operatively applied forest inventory process in Scandinavia. It is expected that multispectral airborne laser scanning can provide highly valuable data for city and forest mapping and is a highly relevant data asset for national and local mapping agencies in the near future.

scholarly journals TOWARDS AUTOMATIC SINGLE-SENSOR MAPPING BY MULTISPECTRAL AIRBORNE LASER SCANNING

2016 ◽  
Vol XLI-B3 ◽  
pp. 155-162 ◽  
Author(s):  
E. Ahokas ◽  
J. Hyyppä ◽  
X. Yu ◽  
X. Liang ◽  
L. Matikainen ◽  
...  
Keyword(s):  
Land Cover ◽  
Tree Species ◽  
Forest Inventory ◽  
Laser Scanning ◽  
Laser Scanner ◽  
Ground Surface ◽  
Airborne Laser Scanning ◽  
Forest Mapping ◽  
Airborne Laser Scanner ◽  
Airborne Laser

This paper describes the possibilities of the Optech Titan multispectral airborne laser scanner in the fields of mapping and forestry. Investigation was targeted to six land cover classes. Multispectral laser scanner data can be used to distinguish land cover classes of the ground surface, including the roads and separate road surface classes. For forest inventory using point cloud metrics and intensity features combined, total accuracy of 93.5% was achieved for classification of three main boreal tree species (pine, spruce and birch).When using intensity features – without point height metrics - a classification accuracy of 91% was achieved for these three tree species. It was also shown that deciduous trees can be further classified into more species. We propose that intensity-related features and waveform-type features are combined with point height metrics for forest attribute derivation in area-based prediction, which is an operatively applied forest inventory process in Scandinavia. It is expected that multispectral airborne laser scanning can provide highly valuable data for city and forest mapping and is a highly relevant data asset for national and local mapping agencies in the near future.

scholarly journals MULTISPECTRAL AIRBORNE LASER SCANNING POINT-CLOUDS FOR LAND COVER CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 79-86
Author(s):  
L. Ma ◽  
Z. Chen ◽  
Y. Li ◽  
D. Zhang ◽  
J. Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Input Data ◽  
Laser Scanning ◽  
Accuracy Assessment ◽  
Point Clouds ◽  
Land Cover Classification ◽  
Airborne Laser Scanning ◽  
Airborne Laser ◽  
3D Cnn

<p><strong>Abstract.</strong> This paper presents an automated workflow for pixel-wise land cover (LC) classification from multispectral airborne laser scanning (ALS) data using deep learning methods. It mainly contains three procedures: data pre-processing, land cover classification, and accuracy assessment. First, a total of nine raster images with different information were generated from the pre-processed point clouds. These images were assembled into six input data combinations. Meanwhile, the labelled dataset was created using the orthophotos as the ground truth. Also, three deep learning networks were established. Then, each input data combination was used to train and validate each network, which developed eighteen LC classification models with different parameters to predict LC types for pixels. Finally, accuracy assessments and comparisons were done for the eighteen classification results to determine an optimal scheme. The proposed method was tested on six input datasets with three deep learning classification networks (i.e., 1D CNN, 2D CNN, and 3D CNN). The highest overall classification accuracy of 97.2% has been achieved using the proposed 3D CNN. The overall accuracy (OA) of the 2D and 3D CNNs was, on average, 8.4% higher than that of the 1D CNN. Although the OA of the 2D CNN was at most 0.3% lower than that of the 3D CNN, the runtime of the 3D CNN was five times longer than the 2D CNN. Thus, the 2D CNN was the best choice for the multispectral ALS LC classification when considering efficiency. The results demonstrated the proposed methods can successfully classify land covers from multispectral ALS data.</p>

Nonparametric estimation of stem volume using airborne laser scanning, aerial photography, and stand-register data

2006 ◽  
Vol 36 (2) ◽  
pp. 426-436 ◽  
Author(s):  
M Maltamo ◽  
J Malinen ◽  
P Packalén ◽  
A Suvanto ◽  
J Kangas
Keyword(s):  
Laser Scanning ◽  
Laser Scanner ◽  
Airborne Laser Scanning ◽  
Data Sources ◽  
Aerial Images ◽  
Stem Volume ◽  
Scanner Data ◽  
Airborne Laser Scanner ◽  
Airborne Laser ◽  
Other Information

In forest management planning and forestry decision-making there is a continuous need for higher quality information on forest resources. The aim of this study was to improve the quality of forest resource information acquired by airborne laser scanning by combining it with aerial images and current stand-register data. A k-MSN (most similar neighbor) application was constructed for the prediction of the plot and stand volumes of standing trees. The application constructed used various data sources, including laser scanner data, aerial digital photographs, class variables describing a stand, and updated old stand volumes. The ability of these data sources to predict stem volume was tested together and separately. In the airborne laser scanner data based k-MSN application, characteristics of canopy quantiles were used as independent variables. The results show that with respect to individual plot and stand volume estimation approaches, the laser-based technique is a superior one. The results were improved further when other information sources were used together with the laser scanner data. Using a combination of laser scanner data, aerial images, and class variables (on the grounds of the current forest database) improved the root mean square error (RMSE) of the estimated plot volume by 15% (from 16% to 13%) as compared to using laser scanner data on their own. When the results were averaged at the stand level, the accuracy improved considerably, but the use of other information sources together with airborne laser scanner data did not further improve the results as it did at the plot level. The RMSE of stand volume was about 6% in all data combinations where airborne laser scanning information was used. One conclusion is that making use of additional available data sources together with laser material improves the reliability of plot volume estimates. As these additional data typically mean no extra material costs (since they are available in any case), making combined use of these data and laser scanner data improves the cost efficiency of a forest inventory.

scholarly journals Archaeological Surveying of Subarctic and Arctic Landscapes: Comparing the Performance of Airborne Laser Scanning and Remote Sensing Image Data

2021 ◽  
Vol 13 (4) ◽  
pp. 1917
Author(s):  
Alma Elizabeth Thuestad ◽  
Ole Risbøl ◽  
Jan Ingolf Kleppe ◽  
Stine Barlindhaug ◽  
Elin Rose Myrvoll
Keyword(s):  
Remote Sensing ◽  
Laser Scanning ◽  
Digital Terrain Model ◽  
Image Data ◽  
Remote Sensing Image ◽  
Airborne Laser Scanning ◽  
Aerial Images ◽  
Detection Rates ◽  
Airborne Laser ◽  
Pros And Cons

What can remote sensing contribute to archaeological surveying in subarctic and arctic landscapes? The pros and cons of remote sensing data vary as do areas of utilization and methodological approaches. We assessed the applicability of remote sensing for archaeological surveying of northern landscapes using airborne laser scanning (LiDAR) and satellite and aerial images to map archaeological features as a basis for (a) assessing the pros and cons of the different approaches and (b) assessing the potential detection rate of remote sensing. Interpretation of images and a LiDAR-based bare-earth digital terrain model (DTM) was based on visual analyses aided by processing and visualizing techniques. 368 features were identified in the aerial images, 437 in the satellite images and 1186 in the DTM. LiDAR yielded the better result, especially for hunting pits. Image data proved suitable for dwellings and settlement sites. Feature characteristics proved a key factor for detectability, both in LiDAR and image data. This study has shown that LiDAR and remote sensing image data are highly applicable for archaeological surveying in northern landscapes. It showed that a multi-sensor approach contributes to high detection rates. Our results have improved the inventory of archaeological sites in a non-destructive and minimally invasive manner.

scholarly journals Estimation of Vegetation-Induced Flow Resistance for Hydraulic Computations Using Airborne Laser Scanning Data

Water ◽  
2021 ◽  
Vol 13 (13) ◽  
pp. 1864
Author(s):  
Peter Mewis
Keyword(s):  
Laser Scanning ◽  
Flow Resistance ◽  
Laser Scanner ◽  
Airborne Laser Scanning ◽  
Density Parameter ◽  
Vegetation Density ◽  
Airborne Laser Scanner ◽  
Airborne Laser ◽  
Bed Roughness ◽  
Available Information

The effect of vegetation in hydraulic computations can be significant. This effect is important for flood computations. Today, the necessary terrain information for flood computations is obtained by airborne laser scanning techniques. The quality and density of the airborne laser scanning information allows for more extensive use of these data in flow computations. In this paper, known methods are improved and combined into a new simple and objective procedure to estimate the hydraulic resistance of vegetation on the flow in the field. State-of-the-art airborne laser scanner information is explored to estimate the vegetation density. The laser scanning information provides the base for the calculation of the vegetation density parameter ωp using the Beer–Lambert law. In a second step, the vegetation density is employed in a flow model to appropriately account for vegetation resistance. The use of this vegetation parameter is superior to the common method of accounting for the vegetation resistance in the bed resistance parameter for bed roughness. The proposed procedure utilizes newly available information and is demonstrated in an example. The obtained values fit very well with the values obtained in the literature. Moreover, the obtained information is very detailed. In the results, the effect of vegetation is estimated objectively without the assignment of typical values. Moreover, a more structured flow field is computed with the flood around denser vegetation, such as groups of bushes. A further thorough study based on observed flow resistance is needed.

Sign in / Sign up

Export Citation Format

Share Document