Skip to Main content Skip to Navigation
Conference papers

Motion Trend Patterns for Action Modelling and Recognition

Abstract : A new method for action modelling is proposed, which com-bines the trajectory beam obtained by semi-dense point tracking and a local binary trend description inspired from the Local Binary Patterns (LBP). The semi dense trajectory approach represents a good trade-off between reliability and density of the motion field, whereas the LBP component allows to capture relevant elementary motion elements along each trajectory, which are encoded into mixed descriptors called Motion Trend Patterns (MTP). The combination of those two fast operators al-lows a real-time, on line computation of the action descriptors, composed of space-time blockwise histograms of MTP values, which are classified using a fast SVM classifier. An encoding scheme is proposed and com-pared with the state-of-the-art through an evaluation performed on two academic action video datasets.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Thanh Phuong Nguyen <>
Submitted on : Wednesday, February 18, 2015 - 4:58:01 PM
Last modification on : Tuesday, April 7, 2020 - 6:36:10 PM
Long-term archiving on: : Tuesday, May 19, 2015 - 10:50:35 AM


Files produced by the author(s)




Thanh Phuong Nguyen, Antoine Manzanera, Matthieu Garrigues. Motion Trend Patterns for Action Modelling and Recognition. Computer Analysis of Images and Patterns (CAIP), Aug 2013, York, United Kingdom. pp.360 - 367, ⟨10.1007/978-3-642-40261-6_43⟩. ⟨hal-01118278⟩



Record views


Files downloads