A Comparison of Image Feature Detection and Matching on CPU and GPU Implementation

Due to the various limits in the GPU implementation, questions may arise.Is the GPU implementation as faithful as the CPU one/Could the GPU implementation be safely used/In this paper, we take two widely used algorithms as representative examples to evaluate the performance of the GPU implementation, that is, the scale-invariant feature transform (SIFT) for feature detection and the KD-tree traversal for feature matching. We present the design, implementation, and evaluation of these two algorithms on GPU for high-resolution image datasets.Our results show that around 95% of the extracted features are nearly the same, and the repeatability score and matching score are similar under the GPU and CPU implementations under various image changes.The run-time speedup of the GPU implementation for the SIFT detection is about 13X faster than their CPU counterpart, and that for the KD-tree traversal is about 43X.In sum, our results show that the GPU implementations for feature detection and matching are as good as the CPU ones, and can be safely used in real applications.