Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Carsten Steger"'
Publikováno v:
International Journal of Computer Vision. 130:947-969
The unsupervised detection and localization of anomalies in natural images is an intriguing and challenging problem. Anomalies manifest themselves in very different ways and an ideal benchmark dataset for this task should contain representative examp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15df54000e0ede934201f99ba264fc4a
https://doi.org/10.1007/s11263-022-01578-9
https://doi.org/10.1007/s11263-022-01578-9
Autor:
Markus Ulrich, Carsten Steger
Publikováno v:
Journal of Mathematical Imaging and Vision, 64, 105-130
We propose a novel multi-view camera model for line-scan cameras with telecentric lenses. The camera model supports an arbitrary number of cameras and assumes a linear relative motion with constant velocity between the cameras and the object. We dist
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ff02026125cdaadd4226d3bc8cdf155
https://doi.org/10.1007/s10851-021-01055-x
https://doi.org/10.1007/s10851-021-01055-x
Publikováno v:
International Journal of Computer Vision. 129:1038-1059
The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new app
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50f9766438202d2e33c539edf2d59a88
https://doi.org/10.1007/s11263-020-01400-4
https://doi.org/10.1007/s11263-020-01400-4
Autor:
Markus Ulrich, Carsten Steger
Publikováno v:
International journal of computer vision, 129, 80–99
We propose a camera model for line-scan cameras with telecentric lenses. The camera model assumes a linear relative motion with constant velocity between the camera and the object. It allows to model lens distortions, while supporting arbitrary posit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77b76e81f1b7b2502eedc1a9124b0333
https://doi.org/10.1007/s11263-020-01358-3
https://doi.org/10.1007/s11263-020-01358-3
Autor:
Tobias Böttger, Carsten Steger
Publikováno v:
Journal of Real-Time Image Processing. 18:493-510
We present the shape model object tracker, which is accurate, robust, and real-time capable on a standard CPU. The tracker has a failure mode detection, is robust to nonlinear illumination changes, and can cope with occlusions. It uses subpixel-preci
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8b48890681ec8193c5a6a234680c41c
https://doi.org/10.1007/s11554-020-00978-9
https://doi.org/10.1007/s11554-020-00978-9
Publikováno v:
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
We introduce a powerful student-teacher framework for the challenging problem of unsupervised anomaly detection and pixel-precise anomaly segmentation in high-resolution images. Student networks are trained to regress the output of a descriptive teac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::606751eb2b2b7d9c7ed390314e2823ce
https://doi.org/10.1109/cvpr42600.2020.00424
https://doi.org/10.1109/cvpr42600.2020.00424
Autor:
Carsten Steger
Publikováno v:
Journal of Mathematical Imaging and Vision. 60:246-266
We examine the orthographic-n-point problem (OnP), which extends the perspective-n-point problem to telecentric cameras. Given a set of 3D points and their corresponding 2D points under orthographic projection, the OnP problem is the determination of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48a268f89d62bf926504365e30d8ceb8
https://doi.org/10.1007/s10851-017-0756-y
https://doi.org/10.1007/s10851-017-0756-y
Publikováno v:
CVPR
The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the field of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new ap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74f4325fb66fe8d6e06c6e2c8f3933c9
https://doi.org/10.1109/cvpr.2019.00982
https://doi.org/10.1109/cvpr.2019.00982
Publikováno v:
VISIGRAPP (5: VISAPP)
Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data. Most commonly, this task is performed by thresholding a pixel-wise reconstruction error based on an $\ell^p$ distance. This procedure, howe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d269ed53e89e7e5b79c5f148e16379b
https://doi.org/10.5220/0007364500002108
https://doi.org/10.5220/0007364500002108
Autor:
Markus Ulrich, Carsten Steger
Publikováno v:
Machine vision and applications, 30 (6), 1013–1028
We propose a camera model for cameras with hypercentric lenses. Because of their geometry, hypercentric lenses allow to image the top and the sides of an object simultaneously. This makes them useful for certain inspections tasks, for which otherwise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f3c09ffb96479bebbcebfdef1c5f4ca
https://publikationen.bibliothek.kit.edu/1000118709
https://publikationen.bibliothek.kit.edu/1000118709
