Good features to track

By Jianbo Shi, Carlo Tomasi. 1994

How researchers see this paper

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

Citations in the corpus

A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, methodology): “the use of color histograms, gradients and other features such as KLT to evaluate the similarity [182].”
Video In Sentences Out (2012, methodology): “The Kanade-LucasTomasi (KLT) [Shi and Tomasi, 1994; Tomasi and Kanade, 1991] feature tracker is then used to project each detection five frames forward to augment the set of detections and further compensate for false negatives in the raw detector output.”
Robust photometric invariant features from the color tensor (2006, methodology): “which is used to select features for tracking [ 24 ].”
ViSP for visual servoing: a generic software platform with a wide class of robot control skills (2005, background): “The authors want to acknowledge the contribution of the members of the Lagadic group: Nicolas Mansard, Anthony Remazeilles, Andrew Comport and Muriel Prssigout as well as the former PHD students (Ezio Malis, Youcef Mezouar,...) who contribute to the creation of this software.”
Instance-Level Video Segmentation from Object Tracks (2016, methodology): “The tracker associates these detections based on KLT tracks [40], interpolates missing detections and smooths the tracks in time [12].”
Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, methodology): “The VO literature is characterized by many point-feature detectors, such as corner detectors (e.g., Moravec [2], For-stner [10], Harris [11], Shi-Tomasi [12], and FAST [13]) and blob detectors (SIFT [14], SURF [15], and CENSURE [16]).”
Subspace video stabilization (2011, methodology): “We first compute a set of sparse 2D feature trajectories using the standard KLT approach [Shi and Tomasi 1994].”
Motion magnification (2005, methodology): “The precision of the flow vector is further refined to sub-pixel level based on a local Lucas-Kanade algorithm [Lucas and Kanade 1981; Shi and Tomasi 1994].”
A Robust and Efficient Video Representation for Action Recognition (2015, unknown): “We select motion vectors for salient feature points using the good-features-totrack criterion (Shi and Tomasi, 1994), i.”
Modeling the World from Internet Photo Collections (2008, methodology): “If features are being tracked from frame to frame, an affine extension of the basic Lucas-Kanade tracker has been shown to perform well (Shi and Tomasi 1994).”
Fast Normalized Cross-Correlation (2010, methodology): “Because (4) can be efficiently computed in the transform domain, several transform domain methods of approximating the image energy normalization in (2) have been developed.”
Remote Heart Rate Measurement from Face Videos under Realistic Situations (2014, methodology): “[15], and are tracked through the following frames using the Kanade-Lucas-Tomasi (KLT) algorithm [19].”
Faster and Better: A Machine Learning Approach to Corner Detection (2008, unknown): “October 14, 2008 DRAFT 6”
Tracking Objects as Points (2020, background): “In early computer vision, tracking was commonly phrased as following interest points through space and time [36, 43].”
The Visual Object Tracking VOT2017 Challenge Results (2017, methodology): “SAPKLTF is a single-object long-term tracker which consists of two phases: The first stage is based on the Kanade Lukas Tomasi approach (KLT) [58] choosing the object features (colour and motion coherence) to track relatively large object displacements.”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, methodology): “%) applied discriminative correlation filters (ANT A.3, BoVW CFT A.4, CCOT A.11, CFCF A.13, CFTR A.15, CPT A.7, CPT fast A.8, CSRDCF A.24, CSRTPP A.25, CSTEM A.9, DCFCF A.22, DCFNet A.18, DeepCSRDCF A.17, DeepSTRCF A.20, DFPReco A.29, DLSTpp A.28, DPT A.21, DRT A.16, DSST A.26, ECO A.31, HMMTxD A.53”
A review of moving object trajectory clustering algorithms (2016, methodology): “Wang et al. (2013) and Yan et al. (2012) develop a semantic approach that progressively transforms the raw mobility data into semantic trajectories enriched with segmentations and annotations on basis of Semantic Model and a Computation and Annotation Platform.”
Where are the Blobs: Counting by Localization with Point Supervision (2018, unknown): “Rabaud and Belongie [19] proposed to use feature points which are detected by motion and appearance cues and are tracked through time using KLT [22].”