A Complete Real-Time Feature Extraction and Matching System Based on Semantic Kernels Binarized - VLSI-SoC: At the Crossroads of Emerging Trends Access content directly
Conference Papers Year : 2015

A Complete Real-Time Feature Extraction and Matching System Based on Semantic Kernels Binarized

P. A. Hager
  • Function : Author
  • PersonId : 990378
L. Cavigelli
  • Function : Author
  • PersonId : 990379
Z. Fang
  • Function : Author
  • PersonId : 990380
P. Greisen
  • Function : Author
  • PersonId : 990381
F. K. Gürkaynak
  • Function : Author
  • PersonId : 990382
A. Smolic
  • Function : Author
  • PersonId : 990383
H. Kaeslin
  • Function : Author
  • PersonId : 990384
L. Benini
  • Function : Author
  • PersonId : 990385

Abstract

Feature extraction and matching is an important step in many current image and video processing algorithms. In this work, we designed and implemented an efficient feature extraction and matching system for sparse point correspondence search in stereo video. Our system is based on the recently proposed Semantic Kernels Binarized (SKB) algorithm, which showed superior performance with respect to other algorithms in our evaluation. The feature extraction stage has been prototyped in 180 nm technology and the complete system with two feature extraction pipelines (left and right view) together with the matching unit have been implemented on a Stratix IV FPGA where it delivers a performance of up to 42 frames per second on 720p video. Especially due to the high throughput of up to 25 k matched descriptors per frame, our system compares favourably with recent hardware implementations of similar algorithms.
Fichier principal
Vignette du fichier
367527_1_En_7_Chapter.pdf (5.47 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01380302 , version 1 (12-10-2016)

Licence

Attribution

Identifiers

Cite

Michael Schaffner, P. A. Hager, L. Cavigelli, Z. Fang, P. Greisen, et al.. A Complete Real-Time Feature Extraction and Matching System Based on Semantic Kernels Binarized. 21th IFIP/IEEE International Conference on Very Large Scale Integration - System on a Chip (VLSI-SoC), Oct 2013, Istanbul, Turkey. pp.144-167, ⟨10.1007/978-3-319-23799-2_7⟩. ⟨hal-01380302⟩
68 View
157 Download

Altmetric

Share

Gmail Facebook X LinkedIn More