A simple human activity recognition technique using DCT

Abstract : In this paper, we present a simple new human activity recognition method using discrete cosine transform (DCT). The scheme uses the DCT coefficients extracted from silhouettes as descriptors (features) and performs frame-by-frame recognition, which make it simple and suitable for real time applications. We carried out several tests using radial basis neural network (RBF) for classification, a comparative study against stat-of-the-art methods shows that our technique is faster, simple and gives higher accuracy performance comparing to discrete transform based techniques and other methods proposed in literature.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01402057
Contributor : Frédéric Davesne <>
Submitted on : Thursday, November 24, 2016 - 10:57:43 AM
Last modification on : Monday, October 28, 2019 - 10:50:21 AM

Identifiers

Citation

Aziz Khelalef, Fakhr-Eddine Ababsa, Nabil Benoudjit. A simple human activity recognition technique using DCT. 17th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2016), Oct 2016, Lecce, Italy. pp.37--46, ⟨10.1007/978-3-319-48680-2_4⟩. ⟨hal-01402057⟩

Share

Metrics

Record views

162