GPU-based Video Feature Tracking And Matching

TLDR

GPU acceleration of vision algorithms frees the CPU to run other computations in parallel. The paper presents GPU implementations of KLT tracking and SIFT extraction for real‑time video analysis. The authors implement KLT and SIFT on GPUs, achieving ~1,000‑feature tracking at 30 Hz on 1024×768 video (20× faster) and ~800‑feature extraction at 10 Hz on 640×480 video (10× faster), compatible with ATI and NVIDIA cards. The GPU implementations deliver 20‑fold speedups for KLT tracking and 10‑fold speedups for SIFT extraction compared to optimized CPU versions.

Abstract

This paper describes novel implementations of the KLT feature track- ing and SIFT feature extraction algorithms that run on the graphics processing unit (GPU) and is suitable for video analysis in real-time vision systems. While significant acceleration over standard CPU implementations is obtained by ex- ploiting parallelism provided by modern programmable graphics hardware, the CPU is freed up to run other computations in parallel. Our GPU-based KLT im- plementation tracks about a thousand features in real-time at 30 Hz on 1024 £ 768 resolution video which is a 20 times improvement over the CPU. It works on both ATI and NVIDIA graphics cards. The GPU-based SIFT implementation works on NVIDIA cards and extracts about 800 features from 640 £ 480 video at 10Hz which is approximately 10 times faster than an optimized CPU implementation.