Robust Real-Time Periodic Motion Detection, Analysis, and Applications

By Ross Cutler, Larry S. Davis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

819 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4e628aa75f319acf3c5b7f5108d80feb2c69fbb5

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognizing action at a distance (2003, background): “Gavrila and Davis' survey paper [7] provides a thorough review of the tracking literature, but it is largely inapplicable for the type of data we are considering in this work.”
Tracking multiple humans in complex situations (2004, background): “For motion-based human detection, motion periodicity is an important feature since human locomotion is periodic; an overview of these approaches is given in [8].”
Joint segmentation and classification of human actions in video (2011, background): “Time series segmentation has also been implicitly studied from the perspective of analyzing periodicity of cyclic events, e.g., [5] [19].”
Pedestrian detection and tracking with night vision (2005, methodology): “[17], [18], spatial–temporal silhouette analysis of human parts with a three-dimensional (3-D) model [20], periodicity and self-similarity analysis [9], annealed particle filtering for articulated pedestrian [11], and probabilistic modeling of pose and motion, as well as maximum a posteriori detecti”
Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion (2013, background): “In the literature of dynamical systems, the frame kernel matrix ( K ) is alternatively called the recurrence matrix [42], [43], and its structure reveals important information about the dynamics.”
A survey on visual surveillance of object motion and behaviors (2004, methodology): “[18] describe a similarity-based technique to detect and analyze periodic motion.”
Event-based analysis of video (2001, methodology): “model and recognize articulated motions [10], Black and Yacoob treat facial expressions [2], and the approaches of Polana and Nelson [18], Cutler and Davis [5], Liu and Picard [11] and of Saisan et al.”
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin (2011, background): “For example, Cutler and Davis [17] and Polana and Nelson [18] detect and classify periodic motions.”
Human Action Recognition by Semilatent Topic Models (2009, neutral): “For example, Cutler and Davis [1], and Polana and Nelson [4] detect and classify periodic motions.”
Gait analysis for recognition and classification (2002, background): “In addition, using only joint angles ignores the appearance traits that are associated with individuals, such as heavy-set vs. slim, long hair vs. bald, or personal clothing and accessories.”
Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle (2007, methodology): “Given temporal ROI data, previous work has detected people walking laterally to the viewing direction, either using the periodicity cue (Cutler and Davis, 2000; Polana and Nelson, 1994) or by learning the characteristic lateral gait pattern (Heisele and Wöhler, 1998).”
Computer vision and deep learning techniques for pedestrian detection and tracking: A survey (2018, background): “Moreover, as will be discussed in the following section ( Section 4 ), motion information, which is generally extracted using a 3D vision sys-tem, could be obtained following a bi-dimensional approach [3,18,19,21,44,52,53,55,65,76,92,95,135,136] .”
Artificial vision in road vehicles (2002, methodology): “Oiginal work by Cutler and Davis of the University of Maryland [49] uses a subtraction between an image at time and a version of the same image stabilized”
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild (2020, methodology): “Period estimation in videos has been done using periodograms on top of auto-correlation [9] or Wavelet transforms on hand-designed features derived from optical flow [35].”
A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection (2016, neutral): “simple appearance and motion patterns [26, 2].”