Søren Ingvor Olsen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Søren Ingvor Olsen has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
Hong Pan
University of Copenhagen, Denmark
4 shared publicationsJinchao Liu
FORCE Technology, Welding and Production Innovation, Brødby, Denmark
4 shared publicationsKim Hardam Christensen
FORCE Technology, Welding and Production Innovation, Brødby, Denmark
4 shared publicationsZhun Fan
Department of Mechanical Engineering, Technical University of Denmark, Kgs. Lyngby, Denmark
4 shared publicationsYaping Zhu
Department of Computer Science, University of Copenhagen, 1017 Copenhagen K, Denmark
3 shared publications- Adrien Bartoli
Institut Pascal
2 shared publications
Latest Publications
- Open Access
- 10 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (4) , 830
Mapping Key Indicators of Forest Restoration in the Amazon Using a Low-Cost Drone and Artificial Intelligence
Monitoring the vegetation structure and species composition of forest restoration (FR) in the Brazilian Amazon is critical to ensuring its long-term benefits. Since remotely piloted aircrafts (RPAs) associated with deep learning (DL) are becoming powerful tools for vegetation monitoring, this study aims to use DL to automatically map individual crowns of Vismia (low resilience recovery indicator), Cecropia (fast recovery indicator), and trees in general (this study refers to individual crowns of all trees regardless of species as All Trees). Since All Trees can be accurately mapped, this study also aims to propose a tree crown heterogeneity index (TCHI), which estimates species diversity based on: the heterogeneity attributes/parameters of the RPA image inside the All Trees results; and the Shannon index measured by traditional fieldwork. Regarding the DL methods, this work evaluated the accuracy of the detection of individual objects, the quality of the delineation outlines and the area distribution. Except for Vismia delineation (IoU = 0.2), DL results presented accurate values in general, as F1 and IoU were always greater than 0.7 and 0.55, respectively, while Cecropia presented the most accurate results: F1 = 0.85 and IoU = 0.77. Since All Trees results were accurate, the TCHI was obtained through regression analysis between the canopy height model (CHM) heterogeneity attributes and the field plot data. Although TCHI presented robust parameters, such as p-value < 0.05, its results are considered preliminary because more data are needed to include different FR situations. Thus, the results of this work show that low-cost RPA has great potential for monitoring FR quality in the Amazon, because Vismia, Cecropia, and All Trees can be automatically mapped. Moreover, the TCHI preliminary results showed high potential in estimating species diversity. Future studies must assess domain adaptation methods for the DL results and different FR situations to improve the TCHI range of action.
- 10 February 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (4) , 830
Open AccessMapping Key Indicators of Forest Restoration in the Amazon Using a Low-Cost Drone and Artificial Intelligence
Monitoring the vegetation structure and species composition of forest restoration (FR) in the Brazilian Amazon is critical to ensuring its long-term benefits. Since remotely piloted aircrafts (RPAs) associated with deep learning (DL) are becoming powerful tools for vegetation monitoring, this study aims to use DL to automatically map individual crowns of Vismia (low resilience recovery indicator), Cecropia (fast recovery indicator), and trees in general (this study refers to individual crowns of all trees regardless of species as All Trees). Since All Trees can be accurately mapped, this study also aims to propose a tree crown heterogeneity index (TCHI), which estimates species diversity based on: the heterogeneity attributes/parameters of the RPA image inside the All Trees results; and the Shannon index measured by traditional fieldwork. Regarding the DL methods, this work evaluated the accuracy of the detection of individual objects, the quality of the delineation outlines and the area distribution. Except for Vismia delineation (IoU = 0.2), DL results presented accurate values in general, as F1 and IoU were always greater than 0.7 and 0.55, respectively, while Cecropia presented the most accurate results: F1 = 0.85 and IoU = 0.77. Since All Trees results were accurate, the TCHI was obtained through regression analysis between the canopy height model (CHM) heterogeneity attributes and the field plot data. Although TCHI presented robust parameters, such as p-value < 0.05, its results are considered preliminary because more data are needed to include different FR situations. Thus, the results of this work show that low-cost RPA has great potential for monitoring FR quality in the Amazon, because Vismia, Cecropia, and All Trees can be automatically mapped. Moreover, the TCHI preliminary results showed high potential in estimating species diversity. Future studies must assess domain adaptation methods for the DL results and different FR situations to improve the TCHI range of action.
- Open Access
- 19 June 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (12) , 2401
Forest Restoration Monitoring Protocol with a Low-Cost Remotely Piloted Aircraft: Lessons Learned from a Case Study in the Brazilian Atlantic Forest
Traditional forest restoration (FR) monitoring methods employ spreadsheets and photos taken at the ground level. Since remotely piloted aircraft (RPA) generate a panoramic high resolution and georeferenced view of the entire area of interest, this technology has high potential to improve the traditional FR monitoring methods. This study evaluates how low-cost RPA data may contribute to FR monitoring of the Brazilian Atlantic Forest by the automatic remote measurement of Tree Density, Tree Height, Vegetation Cover (area covered by trees), and Grass Infestation. The point cloud data was processed to map the Tree Density, Tree Height, and Vegetation Cover parameters. The orthomosaic was used for a Random Forest classification that considered trees and grasses as a single land cover class. The Grass Infestation parameter was mapped by the difference between this land cover class (which considered trees and grasses) and the Vegetation Cover results (obtained by the point cloud data processing). Tree Density, Vegetation Cover, and Grass Infestation parameters presented F_scores of 0.92, 0.85, and 0.64, respectively. Tree Height accuracy was indicated by the Error Percentage considering the traditional fieldwork and the RPA results. The Error Percentage was equal to 0.13 and was considered accurate because it estimated a 13% shorter height for trees that averaged 1.93 m tall. Thus, this study showed that the FR structural parameters were accurately measured by the low-cost RPA, a technology that contributes to FR monitoring. Despite accurately measuring the structural parameters, this study reinforced the challenge of measuring the Biodiversity parameter via remote sensing because the classification of tree species was not possible. After all, the Brazilian Atlantic Forest is a biodiversity hotspot, and thus different species have similar spectral responses in the visible spectrum and similar geometric forms. Therefore, until improved automatic classification methods become available for tree species, traditional fieldwork remains necessary for a complete FR monitoring diagnostic.
- 19 June 2021
- Published by MDPI AG in Remote Sensing
- Vol. 13 (12) , 2401
Open AccessForest Restoration Monitoring Protocol with a Low-Cost Remotely Piloted Aircraft: Lessons Learned from a Case Study in the Brazilian Atlantic Forest
Traditional forest restoration (FR) monitoring methods employ spreadsheets and photos taken at the ground level. Since remotely piloted aircraft (RPA) generate a panoramic high resolution and georeferenced view of the entire area of interest, this technology has high potential to improve the traditional FR monitoring methods. This study evaluates how low-cost RPA data may contribute to FR monitoring of the Brazilian Atlantic Forest by the automatic remote measurement of Tree Density, Tree Height, Vegetation Cover (area covered by trees), and Grass Infestation. The point cloud data was processed to map the Tree Density, Tree Height, and Vegetation Cover parameters. The orthomosaic was used for a Random Forest classification that considered trees and grasses as a single land cover class. The Grass Infestation parameter was mapped by the difference between this land cover class (which considered trees and grasses) and the Vegetation Cover results (obtained by the point cloud data processing). Tree Density, Vegetation Cover, and Grass Infestation parameters presented F_scores of 0.92, 0.85, and 0.64, respectively. Tree Height accuracy was indicated by the Error Percentage considering the traditional fieldwork and the RPA results. The Error Percentage was equal to 0.13 and was considered accurate because it estimated a 13% shorter height for trees that averaged 1.93 m tall. Thus, this study showed that the FR structural parameters were accurately measured by the low-cost RPA, a technology that contributes to FR monitoring. Despite accurately measuring the structural parameters, this study reinforced the challenge of measuring the Biodiversity parameter via remote sensing because the classification of tree species was not possible. After all, the Brazilian Atlantic Forest is a biodiversity hotspot, and thus different species have similar spectral responses in the visible spectrum and similar geometric forms. Therefore, until improved automatic classification methods become available for tree species, traditional fieldwork remains necessary for a complete FR monitoring diagnostic.
- 24 April 2019
- Published by Springer Nature
- p. 1-15
Deep Learning for Detection of Railway Signs and Signals
- 24 April 2019
- Published by Springer Nature
- p. 1-15
Deep Learning for Detection of Railway Signs and Signals
- 15 December 2018
- Published by Springer Nature in Precision Agriculture
- Vol. 20 (5) , 983-999
Pre-harvest weed mapping of Cirsium arvense in wheat and barley with off-the-shelf UAVs
- 15 December 2018
- Published by Springer Nature in Precision Agriculture
- Vol. 20 (5) , 983-999
Pre-harvest weed mapping of Cirsium arvense in wheat and barley with off-the-shelf UAVs
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-72
An in-depth study of sparse codes on abnormality detection
Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes. While much emphasis is put on discriminative dictionary construction, there are no comparative studies of sparse codes regarding abnormality detection. We present an in-depth study of two types of sparse codes solutions - greedy algorithms and convex L1-norm solutions - and their impact on abnormality detection performance. We also propose our framework of combining sparse codes with different detection methods. Our comparative experiments are carried out from various angles to better understand the applicability of sparse codes, including computation time, reconstruction error, sparsity, detection accuracy, and their performance combining various detection methods. The experiment results show that combining OMP codes with maximum coordinate detection could achieve state-of-the-art performance on the UCSD dataset [14].
- 10 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-72
An in-depth study of sparse codes on abnormality detection
Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes. While much emphasis is put on discriminative dictionary construction, there are no comparative studies of sparse codes regarding abnormality detection. We present an in-depth study of two types of sparse codes solutions - greedy algorithms and convex L1-norm solutions - and their impact on abnormality detection performance. We also propose our framework of combining sparse codes with different detection methods. Our comparative experiments are carried out from various angles to better understand the applicability of sparse codes, including computation time, reconstruction error, sparsity, detection accuracy, and their performance combining various detection methods. The experiment results show that combining OMP codes with maximum coordinate detection could achieve state-of-the-art performance on the UCSD dataset [14].
- 1 September 2016
- Published by Elsevier in Pattern Recognition Letters
- Vol. 80, 239-248
Feature representation of RGB-D images using joint spatial-depth feature pooling
- 1 September 2016
- Published by Elsevier in Pattern Recognition Letters
- Vol. 80, 239-248
Feature representation of RGB-D images using joint spatial-depth feature pooling
- 9 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 14 (2) , 1096-1108
Boosting Active Contours for Weld Pool Visual Tracking in Automatic Arc Welding
Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.
- 9 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 14 (2) , 1096-1108
Boosting Active Contours for Weld Pool Visual Tracking in Automatic Arc Welding
Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 512-516
Object classification from RGB-D images using depth context kernel descriptors
Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 512-516
Object classification from RGB-D images using depth context kernel descriptors
Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21618070,p. 389-394
A real-time passive vision system for robotic arc welding
Visual sensing in arc welding has become more and more important. However, it has remained a challenging problem due to the harsh environment, especially the interference of the extremely strong arc light. A typical industrial solution for seam detection is to use laser scanner which however still suffers from several limitations. Solutions for weld pool sensing mostly rely on high speed cameras and powerful external illuminations and therefore the wide use in industrial environments is limited. In this paper we present a real-time passive machine vision system for both seam tracking and weld pool sensing in robotic arc welding. The system, which consists of a CCD camera and a carefully-selected narrowband pass filter, is capable of extracting the geometrical profile of the seam that is close to the arc region and the weld pool boundary simultaneously in real time. This visual information can be further utilized by the control system to navigate the welding robot and adjust the welding parameters. Experiments including several real-time demonstrations have been made and verified the feasibility of the proposed vision system.
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21618070,p. 389-394
A real-time passive vision system for robotic arc welding
Visual sensing in arc welding has become more and more important. However, it has remained a challenging problem due to the harsh environment, especially the interference of the extremely strong arc light. A typical industrial solution for seam detection is to use laser scanner which however still suffers from several limitations. Solutions for weld pool sensing mostly rely on high speed cameras and powerful external illuminations and therefore the wide use in industrial environments is limited. In this paper we present a real-time passive machine vision system for both seam tracking and weld pool sensing in robotic arc welding. The system, which consists of a CCD camera and a carefully-selected narrowband pass filter, is capable of extracting the geometrical profile of the seam that is close to the arc region and the weld pool boundary simultaneously in real time. This visual information can be further utilized by the control system to navigate the welding robot and adjust the welding parameters. Experiments including several real-time demonstrations have been made and verified the feasibility of the proposed vision system.