Deeply optimized Hough transform: Application to action segmentation

Abstract : Hough-like methods like Implicit Shape Model (ISM) and Hough forest have been successfully applied in multiple computer vision fields like object detection, tracking, skeleton extraction or human action detection. However, these methods are known to generate false positives. To handle this issue, several works like Max-Margin Hough Transform (MMHT) or Implicit Shape Kernel (ISK) have reported significant performance improvements by adding discriminative parameters to the generative ones introduced by ISM. In this paper, we offer to use only discriminative parameters that are globally optimized according to all the variables of the Hough transform. To this end, we abstract the common vote process of all Hough methods into linear equations, leading to a training formulation that can be solved using linear programming solvers. Our new Hough Transform significantly outperforms the previous ones on HoneyBee and TUM datasets, two public databases of action and behaviour segmentation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-01813733
Contributor : Léna Le Roy <>
Submitted on : Friday, January 18, 2019 - 12:03:52 PM
Last modification on : Thursday, March 21, 2019 - 2:29:56 PM

File

Chan-Hon-Tong2013.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

A. Chan-Hon-Tong, C. Achard, L. Lucat. Deeply optimized Hough transform: Application to action segmentation. 17th International Conference on Image Analysis and Processing, ICIAP 2013, Sep 2013, Naples, Italy. pp.51-60, ⟨10.1007/978-3-642-41181-6_6⟩. ⟨cea-01813733⟩

Share

Metrics

Record views

103

Files downloads

78