Scene modelling, recognition and tracking with invariant image features

By Iryna Skrypnyk, David G. Lowe. Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004

350 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0e6e97e8e5580e778b853d1c275776d5d36a22bd

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

Accurate Non-Iterative O(n) Solution to the PnP Problem (2007, background): “In particular, applications such as feature point-based camera tracking [26, 18] require dealing with hundreds of noisy feature points in real-time, which requires computationally efficient methods.”
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, methodology): “Later systems used markerless environments, but require a priori information, for example a 3D point model of the scene (Skrypnyk and Lowe 2004), and/or additional inputs such as accelerometers (Bleser and Stricker 2008).”
What and Where: 3D Object Recognition with Accurate Pose (2006, background): “1 The research in this chapter was first presented at the International Symposium on Mixed and Augmented Reality, 2004 [8].”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, positive): “Histogram of oriented gradients used in SIFT [72], [124] is computed such that an image patch is segmented into”
Mobile Augmented Reality Survey: From Where We Are to Where We Go (2017, background): “Skrypnyk and Lowe [211] presented a traditional SIFT-based implementation.”
A Robust O(n) Solution to the Perspective-n-Point Problem (2012, background): “In practice, applications such as feature point-based camera tracking [6], [7] require solutions that can deal with both hundreds of feature points efficiently and a few feature points (n 5) accurately.”
Pose tracking from natural features on mobile phones (2008, background): “In the first step, keypoint localization, Lowe suggests smoothing the input image with Gaussian filters at various scales and then calculating the Difference of Gaussians (DoG), which presents a fast approximation of the Laplacian operator.”
Augmented reality applications in manufacturing: a survey (2008, background): “Recently, Gordon and Lowe (2004) proposed a markerless-based recognition for AR applications using invariant image features.”
A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation (2011, background): “Applications such as feature-point-based camera tracking [29] [21], structure from motion, and visual odometry [26] require dealing with hundreds or even thousands of noisy feature points and outliers in real-time, which requires computationally efficient methods.”