On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods
The purpose of this study is to give a performance comparison between several classic hand-crafted and deep key-point detector and descriptor methods. In particular, we consider the following classical algorithms: SIFT, SURF, ORB, FAST, BRISK, MSER, HARRIS, KAZE, AKAZE, AGAST, GFTT, FREAK, BRIEF and RootSIFT, where a subset of all combinations is paired into detector-descriptor pipelines. Additionally, we analyze the performance of two recent and perspective deep detector-descriptor models, LF-Net and SuperPoint. Our benchmark relies on the HPSequences dataset that provides real and diverse images under various geometric and illumination changes. We analyze the performance on three evaluation tasks: keypoint verification, image matching and keypoint retrieval. The results show that certain classic and deep approaches are still comparable, with some classic detector-descriptor combinations overperforming pretrained deep models. In terms of the execution times of tested implementations, SuperPoint model is the fastest, followed by ORB. The source code is published on \url{https://github.com/kristijanbartol/keypoint-algorithms-benchmark}.
Code (2)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Comparing Feature Detectors: A bias in the repeatability criteria, and how to correct it
Most computer vision application rely on algorithms finding local correspondences between different images. These algorithms detect and compare stable local invariant descriptors centered at scale-invariant keypoints. Be…
A Comparison of CNN and Classic Features for Image Retrieval
Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of th…
Content-Based Image RetrievalImage RetrievalKeypoint DetectionObject Tracking+2R2D2: Reliable and Repeatable Detector and Descriptor
Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical approaches are based on a detect-then-describe paradigm where separate handcrafted methods are …
Atari GamesCamera LocalizationImage MatchingInterest Point Detection+2Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics
The purpose of this study is to provide a detailed performance comparison of feature detector/descriptor methods, particularly when their various combinations are used for image-matching. The localization experiments of …
R2D2: Repeatable and Reliable Detector and Descriptor
Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted…
Interest Point DetectionKeypoint DetectionMetric Learning