| 1. |
- Kristanl, Matej, et al.
(författare)
-
The Seventh Visual Object Tracking VOT2019 Challenge Results
- 2019
-
Ingår i: 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW). - : IEEE COMPUTER SOC. - 9781728150239 ; , s. 2206-2241
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2019 focused on long-term tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard short-term, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website(1).
|
|
| 2. |
- Kristan, Matej, et al.
(författare)
-
The first visual object tracking segmentation VOTS2023 challenge results
- 2023
-
Ingår i: 2023 IEEE/CVF International conference on computer vision workshops (ICCVW). - : Institute of Electrical and Electronics Engineers Inc.. - 9798350307443 - 9798350307450 ; , s. 1788-1810
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking Segmentation VOTS2023 challenge is the eleventh annual tracker benchmarking activity of the VOT initiative. This challenge is the first to merge short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. A new dataset was created; the ground truth has been withheld to prevent overfitting. New performance measures and evaluation protocols have been created along with a new toolkit and an evaluation server. Results of the presented 47 trackers indicate that modern tracking frameworks are well-suited to deal with convergence of short-term and long-term tracking and that multiple and single target tracking can be considered a single problem. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available at the challenge website1
|
|
| 3. |
- Kristan, Matej, et al.
(författare)
-
The Ninth Visual Object Tracking VOT2021 Challenge Results
- 2021
-
Ingår i: 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021). - : IEEE COMPUTER SOC. - 9781665401913 ; , s. 2711-2738
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, (ii) VOT-RT2021 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website(1).
|
|
| 4. |
- Aamodt, K., et al.
(författare)
-
Alignment of the ALICE Inner Tracking System with cosmic-ray tracks
- 2010
-
Ingår i: Journal of Instrumentation. - 1748-0221. ; 5
-
Konferensbidrag (refereegranskat)abstract
- ALICE (A Large Ion Collider Experiment) is the LHC (Large Hadron Collider) experiment devoted to investigating the strongly interacting matter created in nucleus-nucleus collisions at the LHC energies. The ALICE ITS, Inner Tracking System, consists of six cylindrical layers of silicon detectors with three different technologies; in the outward direction: two layers of pixel detectors, two layers each of drift, and strip detectors. The number of parameters to be determined in the spatial alignment of the 2198 sensor modules of the ITS is about 13,000. The target alignment precision is well below 10 mu m in some cases (pixels). The sources of alignment information include survey measurements, and the reconstructed tracks from cosmic rays and from proton-proton collisions. The main track-based alignment method uses the Millepede global approach. An iterative local method was developed and used as well. We present the results obtained for the ITS alignment using about 10(5) charged tracks from cosmic rays that have been collected during summer 2008, with the ALICE solenoidal magnet switched off.
|
|
| 5. |
- Bergseth, Ellen, 1979-, et al.
(författare)
-
Study of surface roughness and surface orientation on friction in rolling/sliding contacts: barrel-on-disc versus twin-disc
- 2017
-
Konferensbidrag (refereegranskat)abstract
- Gears are one of the most important means of mechanical power transmission. Even though the efficiency is high for a gear pair today, further decrease in friction can contribute to lower the fuel consumption. A barrel-on-disc machine (same setup as ball-on-disc) to simulate a rolling/sliding gear contact was used to study the impact of manufacturing method, grinding and superfinishing, on friction. To evaluate the extent to which friction and wear can be diminished by reducing surface roughness and changing surface orientation. Measurement results showed that the change of lubricant had an impact on friction in the mixed to boundary lubrication regimes similar to that of the change of main surface orientation. The results were compared with those from a parallel study involving a twin-disc machine, also used to simulate rolling/sliding contacts (see Figure). Measurements and simulations showed that the barrel-on-disc and twin-disc setups reflected the same friction trends. However, the friction coefficient using the barrel-on-disc setup was almost twice as large as that found using the twin-disc machine. The wear mechanisms also differed: micropits occurred on discs used in the twin-disc set-up whereas normal or no wear was found on the barrel-on-disc specimens. The difference in contact geometry is believed to be the main reason for the higher friction level in the barrel-on-disc machine. A computer contact analysis was used to clarify the differences using perfectly smooth and computer-generated textured surfaces.
|
|
| 6. |
- Jaskorzynska, Bozena, et al.
(författare)
-
Dielectric and Plasmon Slot Waveguides for Photonic Integration
- 2009
-
Ingår i: ICTON 2009: 11th International Conference on Transparent Optical Networks. - NEW YORK : IEEE. ; , s. 653-656
-
Konferensbidrag (refereegranskat)abstract
- Slot waveguides formed either in high-index dielectrics or in metals attract great interest because they provide sub-wavelength confinement in the slot region. While this feature is very attractive for devices relying on stimulated emission or nonlinear effects, it does not necessarily improve the integration density. The spacing between dielectric slot waveguides is still limited by diffraction. Although for metal (plasmon) waveguides the total field can be shrunk far beyond the diffraction limit, the associated increase in propagation loss will set practical limits on both the minimum waveguide width and edge-to-edge separation. Here we compare the packing densities for 3D slot waveguides in silicon and plasmon waveguides in gold with a silicon slot. As a reference we also consider silicon photonic wire. We calculate center-to-center waveguide separations (pitch) versus cross-talk level. We show that at ca 24 dB/mu m cross-talk and requiring the attenuation length of at least 5 mu m, plasmon slot waveguides can be packed ca 3.5 times denser than silicon slot waveguides, and ca 2.5 times denser than photonic wires. We also show examples of the fabricated devices.
|
|
| 7. |
- Kristan, Matej, et al.
(författare)
-
The Sixth Visual Object Tracking VOT2018 Challenge Results
- 2019
-
Ingår i: Computer Vision – ECCV 2018 Workshops. - Cham : Springer Publishing Company. - 9783030110086 - 9783030110093 ; , s. 3-53
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).
|
|
| 8. |
- Kristan, Matej, et al.
(författare)
-
The Visual Object Tracking VOT2014 Challenge Results
- 2015
-
Ingår i: COMPUTER VISION - ECCV 2014 WORKSHOPS, PT II. - Cham : Springer. - 9783319161808 - 9783319161815 ; , s. 191-217
-
Konferensbidrag (refereegranskat)abstract
- The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2014 challenge that go beyond its VOT2013 predecessor are introduced: (i) a new VOT2014 dataset with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2013 evaluation methodology, (iii) a new unit for tracking speed assessment less dependent on the hardware and (iv) the VOT2014 evaluation toolkit that significantly speeds up execution of experiments. The dataset, the evaluation kit as well as the results are publicly available at the challenge website (http://votchallenge.net).
|
|
| 9. |
- Lingas, Andrzej, et al.
(författare)
-
On exact complexity of subgraph homeomorphism
- 2007
-
Ingår i: Theory and Applications of Models of Computation / Lecture Notes in Computer Science. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 9783540725039 ; 4484, s. 256-261
-
Konferensbidrag (refereegranskat)abstract
- The subgraph homeomorphism problem is to decide whether there is an injective mapping of the vertices of a pattern graph into vertices of a host graph so that the edges of the pattern graph can be mapped into (internally) vertex-disjoint paths in the host graph. The restriction of subgraph homeomorphism where an injective mapping of the vertices of the pattern graph into vertices of the host graph is already given is termed fixed-vertex subgraph homeomorphism. We show that fixed-vertex subgraph homeomorphism for a pattern graph on p vertices and a host graph on n vertices can be solved in time O(2n − pnO(1)) or in time O(3n − pn6) and polynomial space. In effect, we obtain new non-trivial upper time-bounds on the exact complexity of the problem of finding k vertex-disjoint paths and general subgraph homeomorphism.
|
|
| 10. |
- Olofsson, Ulf, et al.
(författare)
-
An optical sensor for the identification of low adhesion in the wheel rail contact
- 2012
-
Ingår i: 9th International Conference on Contact Mechanics and Wear of Rail/Wheel Systems, CM 2012. - Chengdu : Southwest Jiaotong University. ; , s. 318-323, s. 318-323
-
Konferensbidrag (refereegranskat)abstract
- Low adhesion between railway wheel and rail, which is usually induced by contaminants such as water, oil, leaves etc., affects railway operation in terms of performance and safety. This study uses an optical sensor to identify different surface layers which cause low adhesion. A laboratory set up and field tests under various conditions were subject to the surface layer identification by the optical sensor. In addition, the friction coefficient was measured on the same surface layers. The results show that the sensor can distinguish between different surface layers. This information further linked to the levels of the friction coefficient, which can be used in the prediction system for the railway operator.
|
|
