Real-Time Visual Tracking of Complex Structures

By Tom Drummond, Roberto Cipolla. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

707 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/779220bb5190b976e025dc649b2e9a0e4b3597b9

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

ViSP for visual servoing: a generic software platform with a wide class of robot control skills (2005, methodology): “Full-scale nonlinear optimization techniques (e.g., [22], [7], [ 12 ]) consist of minimizing the error between the observation and the forward projection of the model.”
Real-Time Monocular SLAM with Straight Lines (2006, methodology): “The innovation for a line is measured using a set of sample points arrayed along the line, as is common in line-tracking applications [9, 6].”
Stable real-time 3D tracking using online and offline information (2004, methodology): “Our tracker starts with a small user-supplied set of keyframes.”
Real-time markerless tracking for augmented reality: the virtual visual servoing framework (2006, background): “…related computer vision literature, geometric features considered for the estimation are often points [18], [9], segments [11], straight lines [29], contours or points on the contours [34], [38], [12], conics [47], [8], cylindrical objects [10], or a combination of these different features [39].”
Fusing points and lines for high performance tracking (2005, methodology): “We use the tracker described in [4], but with edge threshold used is normalized by image intensity.”
SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again (2017, methodology): “We minimize this energy with an IRLS approach (similar to [8]) and robustify it using Geman-McLure weighting.”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, positive): “Markerless model-based tracking [24], [31], [140].”
Combining edge and texture information for real-time accurate 3D camera tracking (2004, methodology): “We rely on a similar approach than the one used in [15, 5], and introduced earlier in the Moving Edges algorithm [1] and in the RAPID tracker [7].”
Vision-based hand pose estimation: A review (2007, background): “Model-based tracking is common in many studies for tracking various types of objects in 2D and 3D [36] [37] [38] [39] (see Section 5 for details).”
Robust 3D visual tracking using particle filtering on the special Euclidean group: A combined approach of keypoint and edge features (2011, methodology): “For more accurate results, we optimize particles as well, in which Iterative Reweighted Least Squares (IRLS) is employed [24], [2].”