Massive parallelization of approximate nearest neighbor search on KD-tree for high-dimensional image descriptor matching

To overcome the high computing cost associated with high-dimensional digital image descriptor matching, this paper presents a massively parallel approximate nearest neighbor search (ANNS) on K-dimensional tree (KD-tree) on the modern massively parallel architectures (MPA). The proposed algorithm is of comparable quality to traditional sequential counterpart on central processing unit (CPU). However, it achieves a high speedup factor of 121 when applied to high-dimensional real-world image descriptor datasets. The algorithm is also studied for factors that impact its performance to obtain the optimal runtime configurations for various datasets. The performance of the proposed parallel ANNS algorithm is also verified on typical 3D image matching scenarios. With the classical local image descriptor signature of histograms of orientations (SHOT), the parallel image descriptor matching can achieve speedup of up to 128. Our implementation will potentially benefit realtime image descriptor matching in high dimensions.

[1]  Daniel A. Keim,et al.  A Graphics Hardware Accelerated Algorithm for Nearest Neighbor Search , 2006, International Conference on Computational Science.

[2]  Federico Tombari,et al.  Unique Signatures of Histograms for Local Surface Description , 2010, ECCV.

[3]  Mario A. López,et al.  High dimensional similarity search with space filling curves , 2001, Proceedings 17th International Conference on Data Engineering.

[4]  Sunil Arya,et al.  Algorithms for fast vector quantization , 1993, [Proceedings] DCC `93: Data Compression Conference.

[5]  Michel Barlaud,et al.  Fast k nearest neighbor search using GPU , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Lawrence Cayton,et al.  Accelerating Nearest Neighbor Search on Manycore Systems , 2011, 2012 IEEE 26th International Parallel and Distributed Processing Symposium.

[7]  David G. Lowe,et al.  Shape indexing using approximate nearest-neighbour search in high-dimensional spaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Majid Ahmadi,et al.  Massively parallel KD-tree construction and nearest neighbor search algorithms , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[9]  Tim Foley,et al.  KD-tree acceleration structures for a GPU raytracer , 2005, HWWS '05.

[10]  Federico Tombari,et al.  A combined texture-shape descriptor for enhanced 3D feature matching , 2011, 2011 18th IEEE International Conference on Image Processing.

[11]  Hao Su,et al.  Object Bank: An Object-Level Image Representation for High-Level Visual Recognition , 2014, International Journal of Computer Vision.

[12]  Gang Hua,et al.  Discriminative Learning of Local Image Descriptors , 1990, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Emmett Kilgariff,et al.  Fermi GF100 GPU Architecture , 2011, IEEE Micro.

[14]  Timothy M. Chan.  Approximate Nearest Neighbor Queries Revisited , 1998, Discret. Comput. Geom..

[15]  Fabian Gieseke,et al.  Buffer k-d Trees: Processing Massive Nearest Neighbor Queries on GPUs , 2014, ICML.

[16]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[17]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[19]  Yi Yang,et al.  CPU-assisted GPGPU on fused CPU-GPU architectures , 2012, IEEE International Symposium on High-Performance Comp Architecture.

[20]  Andrew Zisserman,et al.  Video Google: a text retrieval approach to object matching in videos , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[21]  Benedict R. Gaster,et al.  Can GPGPU Programming Be Liberated from the Data-Parallel Bottleneck? , 2012, Computer.

[22]  Bobby Bodenheimer,et al.  Synthesis and evaluation of linear motion transitions , 2008, TOGS.

[23]  Pat Hanrahan,et al.  Photon mapping on programmable graphics hardware , 2003, HWWS '03.

[24]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[25]  Andreas Nüchter,et al.  GPU-Accelerated Nearest Neighbor Search for 3D Registration , 2009, ICVS.

[26]  Krzysztof Boryczko,et al.  GPU Bucket Sort Algorithm with Applications to Nearest-neighbour Search , 2008, J. WSCG.

[27]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[28]  John D. Owens,et al.  kANN on the GPU with shifted sorting , 2012, EGGH-HPG'12.

[29]  Matthew A. Brown,et al.  Learning Local Image Descriptors , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Kun Zhou,et al.  Real-time KD-tree construction on graphics hardware , 2008, SIGGRAPH 2008.

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

[32]  Saeid Nooshabadi,et al.  G-SHOT: GPU accelerated 3D local descriptor for surface matching , 2015, J. Vis. Commun. Image Represent..

[33]  H. Kage,et al.  High speed 3-D registration using GPU , 2008, 2008 SICE Annual Conference.

[34]  Piotr Indyk,et al.  Nearest Neighbors in High-Dimensional Spaces , 2004, Handbook of Discrete and Computational Geometry, 2nd Ed..

[35]  Saeid Nooshabadi,et al.  A 3D local descriptor SHOT on massively parallel processors , 2015, 2015 IEEE International Conference on Consumer Electronics (ICCE).

[36]  Won-Ki Jeong,et al.  Exploiting Massive Parallelism for IndexingMulti-Dimensional Datasets on the GPU , 2015, IEEE Transactions on Parallel and Distributed Systems.

[37]  David G. Lowe,et al.  Scalable Nearest Neighbor Algorithms for High Dimensional Data , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.