You are in:Home/Publications/SPEEDUP IMAGE SPATIO TEMPORAL FEATURE EXTRACTION USING GPGPU

Ass. Lect. Ahmed Mahmoud Ahmed Mehrez :: Publications:

Title:
SPEEDUP IMAGE SPATIO TEMPORAL FEATURE EXTRACTION USING GPGPU
Authors: Ahmed Mehrez ; Ahmed A. Morgan ; Elsayed E. Hemayed
Year: 2018
Keywords: CUDA Graphics processing unit (GPU) Image matching Scale-invariant feature transform (SIFT) Speeded up robust features (SURF)
Journal: Journal of Real-Time Image Processing Springer
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Springer
Local/International: International
Paper Link:
Full paper Ahmed Mahmoud Ahmed Mehrez_(paper) Speeding up spatiotemporal feature extraction using GPU-ilovepdf-compressed.pdf
Supplementary materials Not Available
Abstract:

Spatiotemporal feature extraction algorithms are widely used in many image processing and computer vision applications. They are favored because of their robust generated features. However, they have high computational complexity. Parallelizing these algorithms, in order to speed their execution up, is of great importance. In this paper, we propose new parallel implementations, using GPU computing, for the two most widely used spatiotemporal feature extraction algorithms: scaleinvariant feature transform and speeded up robust features. In our implementations, we solve problems with previous parallel implementations, such as load imbalance, thread synchronization, and the use of atomic operations. Our implementations speed up the execution by simultaneously processing all the work of each stage of the two algorithms, without dividing that stage into smaller sequential ones. The allocation of the threads in our implementations further allows them to increase the occupancy of the GPU streaming multiprocessors (SMs). We compare our presented implementations to previous CPU and GPU parallel implementations of the two algorithms. Results show that the proposed implementations could do all the processing in real time with high accuracy. They further achieve higher speedup, frame rate, and SM occupancy than the previous best-known parallel implementations of the two algorithms.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus