Details
| Original language | English |
|---|---|
| Title of host publication | DASIP - Proceedings of the 2013 Conference on Design and Architectures for Signal and Image Processing |
| Pages | 80-87 |
| Number of pages | 8 |
| Publication status | Published - 14 Nov 2013 |
| Externally published | Yes |
| Event | 2013 7th Conference on Design and Architectures for Signal and Image Processing, DASIP 2013 - Cagliari, Italy Duration: 8 Oct 2013 → 10 Oct 2013 |
Abstract
Kd-tree search is widely used today in computer vision - for example in object recognition to process a large set of features and identify the objects in a scene. However, the search times vary widely based on the size of the data set to be processed, the number of objects present in the frame, the size and shape of the kd-tree, etc. Constraining the search interval is extremely critical for real-time applications in order to avoid frame drops and to achieve a good response time. The inherent parallelism in the algorithm can be exploited by using massively parallel architectures like many-core processors. However, the variation in execution time is more pronounced on such hardware (HW) due to the presence of shared resources and dynamically varying load situations created by applications running concurrently. In this work, we propose a new resource-aware nearest-neighbor search algorithm for kd-trees on many-core processors. The novel algorithm can adapt itself to the dynamically varying load on a many-core processor and can achieve a good response time and avoid frame drops. The results show significant improvements in performance and detection rate compared to the conventional approach while the simplicity of the conventional algorithm is retained in the new model.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Hardware and Architecture
- Computer Science(all)
- Signal Processing
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
DASIP - Proceedings of the 2013 Conference on Design and Architectures for Signal and Image Processing. 2013. p. 80-87.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Resource-Aware Nearest-Neighbor Search Algorithm for K-Dimensional Trees
AU - Paul, Johny
AU - Stechele, Walter
AU - Kroehnert, Manfred
AU - Asfour, Tamim
AU - Oechslein, Benjamin
AU - Erhardt, Christoph
AU - Schedel, Jens
AU - Lohmann, Daniel
AU - Schröder-Preikschat, Wolfgang
PY - 2013/11/14
Y1 - 2013/11/14
N2 - Kd-tree search is widely used today in computer vision - for example in object recognition to process a large set of features and identify the objects in a scene. However, the search times vary widely based on the size of the data set to be processed, the number of objects present in the frame, the size and shape of the kd-tree, etc. Constraining the search interval is extremely critical for real-time applications in order to avoid frame drops and to achieve a good response time. The inherent parallelism in the algorithm can be exploited by using massively parallel architectures like many-core processors. However, the variation in execution time is more pronounced on such hardware (HW) due to the presence of shared resources and dynamically varying load situations created by applications running concurrently. In this work, we propose a new resource-aware nearest-neighbor search algorithm for kd-trees on many-core processors. The novel algorithm can adapt itself to the dynamically varying load on a many-core processor and can achieve a good response time and avoid frame drops. The results show significant improvements in performance and detection rate compared to the conventional approach while the simplicity of the conventional algorithm is retained in the new model.
AB - Kd-tree search is widely used today in computer vision - for example in object recognition to process a large set of features and identify the objects in a scene. However, the search times vary widely based on the size of the data set to be processed, the number of objects present in the frame, the size and shape of the kd-tree, etc. Constraining the search interval is extremely critical for real-time applications in order to avoid frame drops and to achieve a good response time. The inherent parallelism in the algorithm can be exploited by using massively parallel architectures like many-core processors. However, the variation in execution time is more pronounced on such hardware (HW) due to the presence of shared resources and dynamically varying load situations created by applications running concurrently. In this work, we propose a new resource-aware nearest-neighbor search algorithm for kd-trees on many-core processors. The novel algorithm can adapt itself to the dynamically varying load on a many-core processor and can achieve a good response time and avoid frame drops. The results show significant improvements in performance and detection rate compared to the conventional approach while the simplicity of the conventional algorithm is retained in the new model.
UR - http://www.scopus.com/inward/record.url?scp=84892665300&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84892665300
SN - 9791092279016
SP - 80
EP - 87
BT - DASIP - Proceedings of the 2013 Conference on Design and Architectures for Signal and Image Processing
T2 - 2013 7th Conference on Design and Architectures for Signal and Image Processing, DASIP 2013
Y2 - 8 October 2013 through 10 October 2013
ER -