Fast SIFT Design for Real-Time Visual Feature Extraction

Visual feature extraction with scale invariant feature transform (SIFT) is widely used for object recognition. However, its real-time implementation suffers from long latency, heavy computation, and high memory storage because of its frame level computation with iterated Gaussian blur operations. Thus, this paper proposes a layer parallel SIFT (LPSIFT) with integral image, and its parallel hardware design with an on-the-fly feature extraction flow for real-time application needs. Compared with the original SIFT algorithm, the proposed approach reduces the computational amount by 90% and memory usage by 95%. The final implementation uses 580-K gate count with 90-nm CMOS technology, and offers 6000 feature points/frame for VGA images at 30 frames/s and ~ 2000 feature points/frame for 1920 × 1080 images at 30 frames/s at the clock rate of 100 MHz.

[1]  Hao Feng,et al.  Parallelization and characterization of SIFT on multi-core systems , 2008, 2008 IEEE International Symposium on Workload Characterization.

[2]  Donghyun Kim,et al.  81.6 GOPS Object Recognition Processor Based on a Memory-Centric NoC , 2009, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[3]  Horst Bischof,et al.  Fast Approximated SIFT , 2006, ACCV.

[4]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[5]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[6]  Yung-Chang Chen,et al.  High-Performance SIFT Hardware Accelerator for Real-Time Image Feature Extraction , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Timothy B. Terriberry,et al.  GPU Accelerating Speeded-Up Robust Features , 2008 .

[8]  Wenquan Feng,et al.  An architecture of optimised SIFT feature detection for an FPGA implementation of an image matcher , 2009, 2009 International Conference on Field-Programmable Technology.

[9]  Thomas Wiegand,et al.  SIFT Implementation and Optimization for General-Purpose GPU , 2007 .

[10]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[11]  Konstantinos G. Derpanis,et al.  Fast Scale-Space Feature Representations by Generalized Integral Images , 2007, 2007 IEEE International Conference on Image Processing.

[12]  Tian-Sheuan Chang,et al.  Low memory cost bilateral filtering using stripe-based sliding integral histogram , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[13]  Yoshinobu Yamamoto,et al.  Embedded vision system for mobile robot navigation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[14]  Luc Van Gool,et al.  Fast scale invariant feature detection and matching on programmable graphics hardware , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Qi Zhang,et al.  SIFT implementation and optimization for multi-core systems , 2008, 2008 IEEE International Symposium on Parallel and Distributed Processing.

[16]  Donghyun Kim,et al.  Vision platform for mobile intelligent robot based on 81.6 GOPS object recognition processor , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[17]  George A. Constantinides,et al.  A Parallel Hardware Architecture for Scale and Rotation Invariant Feature Detection , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[18]  Yakup Genc,et al.  GPU-based Video Feature Tracking And Matching , 2006 .