Manifold Methods for Action Recognition
| Autor: | Henryk Josiński, Aldona Drabik, Artur Bąk, Sławomir Wojciechowski, Konrad Wojciechowski, Marek Kulbacki, Agnieszka Michalczuk, Jakub Segen, Kamil Wereszczyński |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Geodesic
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Representation (systemics) 020206 networking & telecommunications Pattern recognition 02 engineering and technology law.invention Activity recognition ComputingMethodologies_PATTERNRECOGNITION law Tensor (intrinsic definition) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Point (geometry) Segmentation Artificial intelligence Neural coding business Manifold (fluid mechanics) |
| Zdroj: | Intelligent Information and Database Systems ISBN: 9783319544298 ACIIDS (2) |
| DOI: | 10.1007/978-3-319-54430-4_59 |
| Popis: | Among a broad spectrum of published methods of recognition of human actions in video sequences, one approach stands out, different from the rest by not relying on detection of interest points or events, extraction of features, region segmentation or finding trajectories, which are all prone to errors. It is based on representation of a time segment of a video sequence as a point on a manifold, and uses a geodesic distance defined on manifold for comparing and classifying video segments. A manifold based representation of a video sequence is obtained starting with a 3d array of consecutive image frames or a 3rd order tensor, which is decomposed into three \(3 \times k\) arrays that are mapped to a point of a manifold. This article presents a review of manifold based methods for human activity recognition and sparse coding of images that also rely on a manifold representation. Results of a human activity classification experiment that uses an implemented action recognition method based on a manifold representation illustrate the presentation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|