22 results on '"Schindler, Konrad"'
Search Results
2. Domain adaptation in segmenting historical maps: A weakly supervised approach through spatial co-occurrence.
- Author
-
Wu, Sidi, Schindler, Konrad, Heitzler, Magnus, and Hurni, Lorenz
- Subjects
- *
HISTORICAL maps , *SURFACE of the earth , *COMPUTER vision , *LIPOFUSCINS , *SOURCE code - Abstract
Historical maps depict past states of the Earth's surface and make it possible to trace the natural or anthropogenic evolution of geographic objects back through time. However, the state of the depicted reality is not the only source of change: maps of varying age can differ in terms of graphical design, and also in terms of storage conditions, physical ageing of pigments, and the scanning process for digitization. Consequently, a computer vision system learned from a specific (source) map series will often not generalize well to older or newer (target) maps, calling for domain adaptation. In the present paper we examine – to our knowledge for the first time – domain adaptation for segmenting historical maps. We argue that for geo-spatial data like maps, which are geo-localized by definition, the spatial co-occurrence of geographical objects provides a supervision signal for domain adaptation. Since only a subset of all mapped objects co-occur, and even those are not perfectly aligned due to both real topographic changes and variations in map generalization/production, they only provide weak supervision — still they can bring a substantial benefit over completely unsupervised domain adaptation methods. The core of our proposed method is a novel self-supervised co-occurrence network that detects co-occurring objects across maps (specifically, domains) with a novel loss function that allows for object changes and spatial misalignment. Experiments show that, for the task of segmenting hydrological objects such as rivers, lakes and wetlands, our system significantly outperforms two state-of-art baselines, even with limited supervision (e.g., 5%). The source code is publicly available at https://github.com/sian-wusidi/spatialcooccurrence. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
3. Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs.
- Author
-
Hackel, Timo, Usvyatsov, Mikhail, Galliani, Silvano, Wegner, Jan D., and Schindler, Konrad
- Subjects
ARTIFICIAL neural networks ,PATTERN recognition systems ,GRAPHICS processing units ,COMPUTER vision ,ELECTRONIC data processing ,MATHEMATICAL convolutions - Abstract
Convolutional neural networks (CNNs) are a powerful tool for pattern recognition and computer vision, but they do not scale well to higher-dimensional inputs, because of the associated memory demands for storing and manipulating high-dimensional tensors. This work starts from the observation that higher-dimensional data, like for example 3D voxel volumes, are sparsely populated. CNNs naturally lend themselves to densely sampled data, and sophisticated, massively parallel implementations are available. On the contrary, existing frameworks by and large lack the ability to efficiently process sparse data. Here, we introduce a suite of tools that exploit sparsity in both the feature maps and the filter weights of a CNN, and thereby allow for significantly lower memory footprints and computation times than the conventional dense framework, when processing data with a high degree of sparsity. Our scheme provides (i) an efficient GPU implementation of a convolution layer based on direct, sparse convolution, as well as sparse implementations of the ReLU and max-pooling layers; (ii) a filter step within the convolution layer, which we call attention, that prevents fill-in, i.e., the tendency of convolution to rapidly decrease sparsity, and guarantees an upper bound on the computational resources; and (iii) an adaptation of back-propagation that makes it possible to combine our approach with standard learning frameworks, while still benefitting from sparsity in the data as well as the model. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
4. Towards Scene Understanding with Detailed 3D Object Representations.
- Author
-
Zia, M., Stark, Michael, and Schindler, Konrad
- Subjects
THREE-dimensional display systems ,IMAGE analysis ,SEMANTICS ,COMPUTER vision ,DIGITAL image processing - Abstract
Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are robust and allow for reliable object detection, they discard much of the information about objects' 3D shape and pose, and thus do not lend themselves well to higher-level reasoning. Here, we propose to base scene understanding on a high-resolution object representation. An object class-in our case cars-is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces. We augment that model to explicitly include vertex-level occlusion, and embed all instances in a common coordinate frame, in order to infer and exploit object-object interactions. Specifically, from a single view we jointly estimate the shapes and poses of multiple objects in a common 3D frame. A ground plane in that frame is estimated by consensus among different objects, which significantly stabilizes monocular 3D pose estimation. The fine-grained model, in conjunction with the explicit 3D scene model, further allows one to infer part-level occlusions between the modeled objects, as well as occlusions by other, unmodeled scene elements. To demonstrate the benefits of such detailed object class models in the context of scene understanding we systematically evaluate our approach on the challenging KITTI street scene dataset. The experiments show that the model's ability to utilize image evidence at the level of individual parts improves monocular 3D pose estimation w.r.t. both location and (continuous) viewpoint. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
5. Object detection by global contour shape
- Author
-
Schindler, Konrad and Suter, David
- Subjects
- *
COMPUTER vision , *COMPUTER networks , *INVARIANTS (Mathematics) , *MATHEMATICAL models , *ARTIFICIAL intelligence , *PATTERN perception - Abstract
Abstract: We present a method for object class detection in images based on global shape. A distance measure for elastic shape matching is derived, which is invariant to scale and rotation, and robust against non-parametric deformations. Starting from an over-segmentation of the image, the space of potential object boundaries is explored to find boundaries, which have high similarity with the shape template of the object class to be detected. An extensive experimental evaluation is presented. The approach achieves a remarkable detection rate of 83–91% at 0.2 false positives per image on three challenging data sets. [Copyright &y& Elsevier]
- Published
- 2008
- Full Text
- View/download PDF
6. Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles.
- Author
-
Leibe, Bastian, Schindler, Konrad, Cornelis, Nico, and Van Gool, Luc
- Subjects
- *
MATHEMATICAL optimization , *REMOTE sensing , *DETECTORS , *IMAGE processing , *ARTIFICIAL intelligence , *COMPUTER vision - Abstract
We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approach is formulated in a Minimum Description Length hypothesis selection framework, which allows our system to recover from mismatches and temporarily lost tracks. Building upon a state-of-the-art object detector, it performs multiview/multicategory object recognition to detect cars and pedestrians in the input images. The 2D object detections are checked for their consistency with (automatically estimated) scene geometry and are converted to 3D observations which are accumulated in a world coordinate frame. A subsequent trajectory estimation module analyzes the resulting 3D observations to find physically plausible spacetime trajectories. Tracking is achieved by performing model selection after every frame. At each time instant, our approach searches for the globally optimal set of spacetime trajectories which provides the best explanation for the current image and for all evidence collected so far while satisfying the constraints that no two objects may occupy the same physical space nor explain the same image pixels at any point in time. Successful trajectory hypotheses are then fed back to guide object detection in future frames. The optimization procedure is kept efficient through incremental computation and conservative hypothesis pruning. We evaluate our approach on several challenging video sequences and demonstrate its performance on both a surveillance-type scenario and a scenario where the input videos are taken from inside a moving vehicle passing through crowded city areas. [ABSTRACT FROM AUTHOR]
- Published
- 2008
- Full Text
- View/download PDF
7. A Model-Selection Framework for Multibody Structure-and-Motion of Image Sequences.
- Author
-
Schindler, Konrad, Suter, David, and Wang, Hanzi
- Subjects
- *
MULTIBODY systems , *DIGITAL image processing , *COMPUTER simulation , *THREE-dimensional imaging , *GEOMETRY , *COMPUTER vision - Abstract
Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the different rigid objects and compute the multiple-view geometry of each object. We present a framework for multibody structure-and-motion based on model selection. In a recover-and-select procedure, a redundant set of hypothetical scene motions is generated. Each subset of this pool of motion candidates is regarded as a possible explanation of the image feature tracks, and the most likely explanation is selected with model selection. The framework is generic and can be used with any parametric camera model, or with a combination of different models. It can deal with sets of correspondences, which change over time, and it is robust to realistic amounts of outliers. The framework is demonstrated for different camera and scene models. [ABSTRACT FROM AUTHOR]
- Published
- 2008
- Full Text
- View/download PDF
8. Guest Editorial: Special Issue on ACCV 2018.
- Author
-
Jawahar, C. V., Li, Hongdong, Mori, Greg, and Schindler, Konrad
- Subjects
COMPUTER architecture ,HOSPITALITY ,COMPUTER vision ,DEEP learning - Abstract
This special issue consists of papers ranging from both classical multi-view geometry to recent deep learning methods deep stereo matching networks, GAN and adversarial learning, and multi-task learning for video object segmentation. The idea for a special issue about architectures and theories for computer vision came from the ACCV conference held in 2018. We, the program chairs of ACCV 2018 and guest editors of this special issue, invited the authors of the ACCV'18 award-winning papers to submit extended manuscripts to this special issue. [Extracted from the article]
- Published
- 2020
- Full Text
- View/download PDF
9. Photogrammetric Computer Vision 2014 – Best Papers of the ISPRS Technical Commission III Symposium.
- Author
-
Schindler, Konrad
- Subjects
- *
PHOTOGRAMMETRY , *COMPUTER vision , *CONFERENCES & conventions - Published
- 2015
- Full Text
- View/download PDF
10. Pioneer Networks: Progressively Growing Generative Autoencoder
- Author
-
Heljakka, Ari, Solin, Arno, Kannala, Juho, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Jawahar, C. V., editor, Li, Hongdong, editor, Mori, Greg, editor, and Schindler, Konrad, editor
- Published
- 2019
- Full Text
- View/download PDF
11. Multi-level Dense Capsule Networks
- Author
-
Phaye, Sai Samarth R., Sikka, Apoorva, Dhall, Abhinav, Bathula, Deepti R., Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Jawahar, C.V., editor, Li, Hongdong, editor, Mori, Greg, editor, and Schindler, Konrad, editor
- Published
- 2019
- Full Text
- View/download PDF
12. Hand Pose Estimation Based on 3D Residual Network with Data Padding and Skeleton Steadying
- Author
-
Ting, Pai-Wen, Chou, En-Te, Tang, Ya-Hui, Fu, Li-Chen, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Pandu Rangan, C., Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Jawahar, C.V., editor, Li, Hongdong, editor, Mori, Greg, editor, and Schindler, Konrad, editor
- Published
- 2019
- Full Text
- View/download PDF
13. Efficient Machine Learning for Ecosystem Monitoring with Earth Observation and Terrestrial Images
- Author
-
Rodriguez Escallon, Andrés C., Schindler, Konrad, Wegner, Jan D., Gómez Chova, Luis, and Zuffi, Silvia
- Subjects
Image Classification ,Computer Vision ,Few-shot learning ,Active Learning ,Remote Sensing ,Machine Learning ,Deep Learning ,Sentinel-2 ,Crop Mapping ,Zero-shot learning ,change detection ,Earth sciences ,Data processing, computer science ,ddc:550 ,ddc:004 - Abstract
Climate change and the subsequent biodiversity loss are two of the greatest threats we face in our time. To tackle these problems, we require timely and localised monitoring of specific metrics such as (1) agricultural expansion, its relation to forest loss and degradation; and (2) the characterisation of species with decreased populations, at the brink of extinction, or extinct; among many others. Earth observation and terrestrial images are crucial for large-scale and fine-grained monitoring of such metrics. In the increased availability of such data, machine learning models enable the understanding of the massive amount of information that is continuously available. Most successful applications rely on a fully labelled and well-balanced training set with a low noise level. Such datasets in practice are not always possible to obtain, as several factors might arise. In this thesis, we have proposed methods to deal with scenarios commonly found in practice and to efficiently leverage the available resources. We focused specifically on two important types of datasets: First, with Earth observation datasets, we used medium resolution satellite images to perform tree density estimation, this allows us to make large-scale estimates of certain tree crops despite not having universal access to high-resolution images. Furthermore, we proposed an active learning approach that is well suited for country-scale applications and saves resources in terms of computation, time, and labelling effort. With this method, we obtained country-scale density maps of oil palms and coconuts in Southeast Asia. Furthermore, after a Typhoon passed over large plantations of coconuts in the Philippines, we relied on our method and a robustness analysis to understand the changes observed before and after the Typhoon in a relatively short time window. Second, using terrestrial images from animal species, we explored how to use side-information to deal with unbalanced and biased datasets. We explored two types of side-information: (1) Keypoint annotations of training samples to guide the model towards discriminative aspects of the image for fine-grained classification. This proved to be helpful in cases of scarce samples, long-tailed class distributions or biased backgrounds. And (2) side-information at a class level in the form of (bird) field-guides. We used them in a Zero-shot learning setting to classify samples from unseen classes by leveraging the information from the field-guides and their similarities to the seen ones. Our work shows that it is possible to carry out efficient labelling campaigns with large-scale areas of interest and to deal with biased datasets and unbalanced class distributions. Future lines of research include sensor fusion, meta-learning and the role of datasets overall to better assess generalisation beyond a single dataset. This work shows some of the potential that efficient machine learning models have for ecosystem monitoring under common and realistic scenarios., ISBN:978-3-03837-014-7
- Published
- 2022
14. Mapping Vegetation Height — Probabilistic Deep Learning for Global Remote Sensing
- Author
-
Lang, Nico, Schindler, Konrad, Wegner, Jan Dirk, Jetz, Walter, and Le Saux, Bertrand
- Subjects
Probabilistic deep learning ,Vegetation height ,Canopy height ,Global mapping ,High Carbon Stock Approach ,Remote Sensing ,Machine Learning ,Deep learning ,Computer Vision ,image interpretation ,Convolutional neural network (CNN) ,Deep ensembles ,Uncertainty estimation ,Sentinel-2 ,satellite data ,GEDI ,LIDAR ,Carbon conservation ,Forest conservation ,Carbon stock ,Biomass ,Data processing, computer science ,ddc:550 ,Earth sciences ,ddc:004 - Abstract
Mapping vegetation properties globally is crucial to understand the role of terrestrial ecosystems in the global carbon cycle. Spatially explicit, high-resolution data are needed to manage terrestrial ecosystems so that climate change can be mitigated and biodiversity loss prevented. Since no current single data source can provide such data with global coverage and high spatial resolution, new solutions must be found. This thesis aims to develop novel data-driven tools based on state-of-the-art deep learning to advance the mapping of vegetation properties, in particular canopy height, at global scale. Two ongoing space missions, namely the Copernicus Sentinel-2 mission and NASA’s GEDI LIDAR mission, deliver publicly available data that form the basis of the methods presented in this thesis. While GEDI is a key climate mission that provides sparse vegetation structure measurements at global scale (between 51.6° N & S), Sentinel-2 delivers dense optical images with global coverage, but cannot directly measure vertical vegetation structure. The presented work is a holistic approach based on gradually extended methods towards the large-scale fusion of Sentinel-2 and GEDI for the global mapping of canopy top height with high spatial resolution. Furthermore, since transparency of the modelling limitations is critical to build trust and to inform downstream applications about the reliability of the estimates, probabilistic deep learning techniques are integrated to quantify the predictive uncertainty. In a first step, a novel approach based on deep convolutional neural networks (CNNs) was developed to estimate dense canopy height maps from Sentinel-2 optical images by training with local dense reference data from airborne measurement campaigns (LIDAR and photogrammetry) in Gabon and Switzerland. By exploiting textural image features, the model achieved low error, even for canopies up to 50 m height. However, its applicability is limited to regions represented by the available training data. The launch of the spaceborne GEDI full waveform LIDAR in December 2018 promised to provide sparse reference data of vegetation structure measurements at global scale. Since interpreting on-orbit GEDI LIDAR waveforms proved to be a difficult task due to unknown noise in the data, a novel probabilistic deep learning approach was developed to retrieve canopy top height globally and quantify the predictive uncertainty from GEDI. Given these footprint-level estimates, the Sentinel-2 based canopy height mapping approach could be extended to be trained with sparse supervision. After demonstrating that this approach allows to estimate canopy top height suitable to map indicative high carbon stocks in tropical Southeast Asia, a global probabilistic model was developed to retrieve canopy top height anywhere on Earth. Ultimately, the first global, wall-to-wall canopy top height map at 10 m ground sampling distance was computed for the year 2020., ISBN:978-3-03837-013-0
- Published
- 2022
15. Object discovery, interactive and 3D segmentation for large-scale computer vision tasks
- Author
-
Kontogianni, Theodora, Leibe, Bastian, and Schindler, Konrad
- Subjects
interactive segmentation ,ddc:004 ,object discovery ,computer vision , object discovery , semantic segmentation , interactive segmentation ,computer vision ,semantic segmentation - Abstract
Dissertation, RWTH Aachen University, 2021; Aachen : RWTH Aachen University 1 Online-Ressource : Illustrationen (2022). = Dissertation, RWTH Aachen University, 2021, Computer vision has made tremendous leaps during the past decade. One of the key factors behind this growth is the vast amount of data that we can generate today: millions of pictures are shared online daily and new specialized sensors allow to easily capture 3D data. Along with the recent advances in deep learning and increased availability of computational power, it is now possible to take advantage of these large amounts of high-quality data. As a result, computer vision achieved impressive performance gains across numerous fields and applications. However, the increased amount of available data also introduces new challenges. To exploit the large body of available data, we either need efficient unsupervised algorithms to learn patterns from unlabeled data, or we require efficient labeling tools to allow the creation of large-scale labeled datasets. These are essential for the success of most deep learning models. In this thesis, we deal with issues arising from these different aspects of computer vision: unsupervised algorithms for landmark recognition, fully-supervised methods for semantic segmentation on large-scale 3D point clouds and interactive object segmentation for out-of-domain dataset labeling. More specifically, the main contributions of this thesis are organized into three parts, each one covering an individual computer vision topic: In the first part, we address the problem of object discovery in time - varying, large - scale image collections. We propose a novel tree structure that closely approximates the Minimum Spanning Tree and present an efficient construction approach to incrementally update the tree structure when new data is added to the image database. This happens either in online-streaming or batch form. Our proposed tree structure is created in a local neighborhood of the matching graph during image retrieval and can be efficiently updated whenever the image database is extended. We show how our tree structure can be incorporated in existing clustering approaches such as Single-Link and Iconoid Shift for efficient large-scale object discovery in image collections. In the second part of the thesis, we focus on defining novel 3D convolutional and recurrent operators over unstructured 3D point clouds. The goal is to learn point representations for the task of 3D semantic segmentation. The recurrent consolidation unit layer operates on multi-scale and grid neighborhoods along and allows our model to learn long-range dependencies. Additionally, we introduce two types of local neighborhoods for each 3D point that encode local geometry to facilitate the definition and use of convolutions on 3D point clouds. Finally, in the third part, we address the task interactive object segmentation. Aided by an algorithm, a user segments an object mask in a given image by clicking inside or outside the object. We present a method that significantly reduces the number of required user clicks compared to previous work. In particular, we look at out-of-domain settings where the test datasets are significantly different from the datasets used to train our deep model. We propose to treat user corrections as sparse supervision to adapt our model parameters on-the-fly. Our adaptive method can significantly reduce the number of required clicks to segment an object and handle distribution shifts from small to large, specialize to a new class of objects introduced during test time, and can even handle large domain changes from commercial images to medical and aerial data., Published by RWTH Aachen University, Aachen
- Published
- 2021
16. 3D Fluid Flow Estimation from Multi-View Particle Images using Physical Priors
- Author
-
Lasinger, Katrin, Schindler, Konrad, Pock, Thomas, and Rösgen, Thomas
- Subjects
Data processing, computer science ,Computer Vision ,Motion perception ,Fluid Dynamics ,Particle image velocimetry (PIV) ,ddc:004 - Abstract
High-resolution 3D velocimetry estimation of fluids is a key problem in experimental fluid mechanics. It offers important applications for aero- and hydrodynamic measurements in academia and industry and facilitates fundamental research in turbulent flows. By injecting tracer particles into a fluid and observing their displacements over time from multiple view-points, a dense velocity field can be obtained. However, with increased particle seeding densities, ambiguities in the 3D particle reconstruction arise, which, in turn, affect the reconstruction accuracy of the underlying flow field. Existing approaches are limited to low seeding densities, which limit the spatial resolution of the flow field, or require long time sequences to heuristically resolve ambiguities of large, self-occluding particle sets. This thesis focuses on novel, physically-motivated approaches for high accuracy 3D flow estimation from few time steps. Multiple contributions are presented to tackle high seeding densities and, thus, facilitate high-resolution velocity field estimation. First, a variational formulation of the 3D flow estimation problem is introduced. The coarse- to-fine optimization scheme allows incorporation of physical priors, such as the incompressible stationary Stokes equations. To counteract the high memory requirement of voxel-based representations, a sparse particle reconstruction approach is subsequently proposed, combined with a sparse descriptor for 3D correspondence matching. Finally, a joint energy formulation is presented that optimizes both the sparse 3D particle locations and the dense motion field. Taking into account all available input views and both time steps jointly results in a better disambiguation of particle reconstructions and a more detailed flow field estimation. This favorable formulation is further extended to multiple time steps, allowing to further improve the particle reconstruction. Hence, even higher particle seeding densities can be supported. The proposed approaches were quantitatively validated on synthetic fluid simulations and delivered compelling results on experiments in water and air., ISBN:978-3-03837-010-9
- Published
- 2020
- Full Text
- View/download PDF
17. Pioneer Networks
- Author
-
Heljakka, Ari, Solin, Arno, Kannala, Juho, Mori, Greg, Jawahar, C.V., Schindler, Konrad, Li, Hongdong, Department of Computer Science, Aalto-yliopisto, and Aalto University
- Subjects
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Generative models ,Computer vision ,Autoencoder - Abstract
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, but they cannot reconstruct existing images. Previous works have attempted to extend GANs to support such inference but, so far, have not delivered satisfactory high-quality results. Instead, we propose the Progressively Growing Generative Autoencoder (Pioneer) network which achieves high-quality reconstruction with images without requiring a GAN discriminator. We merge recent techniques for progressively building up the parts of the network with the recently introduced adversarial encoder–generator network. The ability to reconstruct input images is crucial in many real-world applications, and allows for precise intelligent manipulation of existing images. We show promising results in image synthesis and inference, with state-of-the-art results in CelebA inference tasks.
- Published
- 2019
18. 3D Reconstruction of Urban Scenes from Street-Side and Airborne Imagery
- Author
-
Bódis-Szomorú, András, Van Gool, Luc, Schindler, Konrad, and Lafarge, Florent
- Subjects
Multi-view texturing ,Urban modelling ,Computer Vision ,Image Processing ,Superpixels ,Mobile mapping ,Airborne photogrammetry ,Surface Mesh ,Image-based modelling ,Volumetric reconstruction ,Earth sciences ,Data processing, computer science ,Multi-view reconstruction ,Structure-from-Motion ,Semantic Segmentation ,Multi-view stereo ,ddc:550 ,ddc:4 - Published
- 2018
19. Multi-View 3D Reconstruction with Geometry and Shading
- Author
-
Galliani, Silvano, Schindler, Konrad, Furukawa, Yasutaka, and Brostow, Gabriel J.
- Subjects
Data processing, computer science ,Computer vision ,ddc:4 - Abstract
IGP Mitteilungen, 119, ISBN:978-3-03837-007-9
- Published
- 2018
20. Fast registration of laser scans with 4-point congruent sets - what works and what doesn't
- Author
-
Jan Dirk Wegner, P. W. Theiler, Konrad Schindler, Schindler, Konrad, and Paparoditis, Nicolas
- Subjects
lcsh:Applied optics. Photonics ,Parallelizable manifold ,Laser scanning ,Point cloud registration ,3D feature extraction ,lcsh:T ,Computer science ,business.industry ,Point cloud ,lcsh:TA1501-1820 ,Sampling (statistics) ,RANSAC ,Laser ,lcsh:Technology ,law.invention ,Error function ,lcsh:TA1-2040 ,law ,Robustness (computer science) ,Computer vision ,Artificial intelligence ,lcsh:Engineering (General). Civil engineering (General) ,business - Abstract
Sampling-based algorithms in the mould of RANSAC have emerged as one of the most successful methods for the fully automated registration of point clouds acquired by terrestrial laser scanning (TLS). Sampling methods in conjunction with 3D keypoint extraction, have shown promising results, e.g. the recent K-4PCS (Theiler et al., 2013). However, they still exhibit certain improbable failures, and are computationally expensive and slow if the overlap between scans is low. Here, we examine several variations of the basic K-4PCS framework that have the potential to improve its runtime and robustness. Since the method is inherently parallelizable, straight-forward multi-threading already brings down runtimes to a practically acceptable level (seconds to minutes). At a conceptual level, replacing the RANSAC error function with the more principled MSAC function (Torr and Zisserman, 2000) and introducing a minimum-distance prior to counter the near-field bias reduce failure rates by a factor of up to 4. On the other hand, replacing the repeated evaluation of the RANSAC error function with a voting scheme over the transformation parameters proved not to be generally applicable for the scan registration problem. All these possible extensions are tested experimentally on multiple challenging outdoor and indoor scenarios., ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3, ISSN:2194-9042, ISSN:2194-9050
- Published
- 2014
21. Validation of Vehicle Candidate Areas in Aerial Images Using Color Co-Occurrence Histograms
- Author
-
Uwe Stilla, Peter Reinartz, K. H. Hoffmann, Sebastian Tuermer, W. Leister, Sunar, F, Altan, Orhan, and Schindler, Konrad
- Subjects
lcsh:Applied optics. Photonics ,traffic monitoring ,Photogrammetrie und Bildanalyse ,business.industry ,lcsh:T ,color co-occurrence histograms ,Co-occurrence ,lcsh:TA1501-1820 ,HSL and HSV ,Object (computer science) ,lcsh:Technology ,3K+ camera system ,vehicles ,Aerial imagery ,Geography ,Inner city ,lcsh:TA1-2040 ,aerial imagery ,Histogram ,Computer vision ,Artificial intelligence ,business ,Likelihood function ,Focus (optics) ,lcsh:Engineering (General). Civil engineering (General) - Abstract
Traffic monitoring plays an important role in transportation management. In addition, airborne acquisition enables a flexible and realtime mapping for special traffic situations e.g. mass events and disasters. Also the automatic extraction of vehicles from aerial imagery is a common application. However, many approaches focus on the target object only. As an extension to previously developed car detection techniques, a validation scheme is presented. The focus is on exploiting the background of the vehicle candidates as well as their color properties in the HSV color space. Therefore, texture of the vehicle background is described by color co-occurrence histograms. From all resulting histograms a likelihood function is calculated giving a quantity value to indicate whether the vehicle candidate is correctly classified. Only a few robust parameters have to be determined. Finally, the strategy is tested with a dataset of dense urban areas from the inner city of Munich, Germany. First results show that certain regions which are often responsible for false positive detections, such as vegetation or road markings, can be excluded successfully.
- Published
- 2013
22. A New Paradigm for Matching UAV- and Aerial Images
- Author
-
Peter Reinartz, Tobias Koch, Friedrich Fraundorfer, Xiangyu Zhuo, Halounova, L., Schindler, Konrad, Limpouch, A., Pajdla, P., Šafář, V., Mayer, Helmut, Oude Elberink, S., Mallet, Clément, Rottensteiner, F., Brédif, M., Skaloud, J., and Stilla, U.
- Subjects
lcsh:Applied optics. Photonics ,Matching (statistics) ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Image registration ,Scale-invariant feature transform ,02 engineering and technology ,Geo-registration ,lcsh:Technology ,Feature-based matching ,SIFT ,0202 electrical engineering, electronic engineering, information engineering ,Image scaling ,Computer vision ,A-SIFT ,Aerial image ,Mathematics ,Photogrammetrie und Bildanalyse ,Pixel ,Image matching ,business.industry ,lcsh:T ,Template matching ,lcsh:TA1501-1820 ,020206 networking & telecommunications ,Pattern recognition ,Navigation ,ddc ,Feature (computer vision) ,lcsh:TA1-2040 ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,lcsh:Engineering (General). Civil engineering (General) ,3D Reconstruction - Abstract
This paper investigates the performance of SIFT-based image matching regarding large differences in image scaling and rotation, as this is usually the case when trying to match images captured from UAVs and airplanes. This task represents an essential step for image registration and 3d-reconstruction applications. Various real world examples presented in this paper show that SIFT, as well as A-SIFT perform poorly or even fail in this matching scenario. Even if the scale difference in the images is known and eliminated beforehand, the matching performance suffers from too few feature point detections, ambiguous feature point orientations and rejection of many correct matches when applying the ratio-test afterwards. Therefore, a new feature matching method is provided that overcomes these problems and offers thousands of matches by a novel feature point detection strategy, applying a one-to-many matching scheme and substitute the ratio-test by adding geometric constraints to achieve geometric correct matches at repetitive image regions. This method is designed for matching almost nadir-directed images with low scene depth, as this is typical in UAV and aerial image matching scenarios. We tested the proposed method on different real world image pairs. While standard SIFT failed for most of the datasets, plenty of geometrical correct matches could be found using our approach. Comparing the estimated fundamental matrices and homographies with ground-truth solutions, mean errors of few pixels can be achieved.
- Published
- 2016
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.