Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking

By Steffen Gauglitz, Tobias Höllerer, Matthew A. Turk. International Journal of Computer Vision, 2011

469 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/91a91387f3c886507d4076ef993718c6b7353e99

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey on Structure from Motion (2017, methodology): “For details and performance evaluation of some of the other approaches in the literature (including the computationally eﬃcient speeded up robust features (SURF) method of [8]) for detection and description of local features, we refer the reader to [23].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “The readers are referred to a comprehensive evaluation of different feature detectors and descriptors for tracking by Gauglitz et al. (2011), and the recently presented benchmark (Wu et al. 2015b), which covers a review of modern object tracking methods as well as the role played by feature…”
FREAK: Fast Retina Keypoint (2012, background): “Visual correspondence, object matching, and many other vision applications rely on representing images with sparse number of keypoints.”
A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK (2018, unknown): “In [21], S.”
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition With CNNs (2019, background): “Evaluations and further reading on spatio-temporal detectors can be found in surveys [23, 68, 69].”
Robotic Tactile Perception of Object Properties: A Review (2017, background): “As both visual images and tactile readings are present in numerical matrices, many other vision descriptors [104], [105] also have the potential to be applied in tactile sensing, e.”
R2D2: Repeatable and Reliable Detector and Descriptor (2019, background): “Local feature extraction and description play a vital role in several high-order methods in computer vision and has received a continuous inﬂux of attention in the past several years ( c.f . surveys in [8, 13, 43, 57]).”