Independent increment processes for human motion recognition
نویسندگان
چکیده
This paper describes an algorithm for classifying human motion patterns (trajectories) observed in video sequences. We address this task in a hierarchical way: high-level activities are described as sequences of low-level motion patterns (dynamic models). These low-level dynamic models are simply independent increment processes, each describing a specific motion regime (e.g., ‘‘moving left’’). Classifying a trajectory thus consists in segmenting it into the sequence its low-level components; each sequence of low-level components corresponds to a high-level activity. To perform the segmentation, we introduce a penalized maximum-likelihood criterion which is able to select the number of segments via a novel MDL-type penalty. Experiments with synthetic and real data illustrate the effectiveness of the proposed approach. 2007 Elsevier Inc. All rights reserved.
منابع مشابه
3D Hand Motion Evaluation Using HMM
Gesture and motion recognition are needed for a variety of applications. The use of human hand motions as a natural interface tool has motivated researchers to conduct research in the modeling, analysis and recognition of various hand movements. In particular, human-computer intelligent interaction has been a focus of research in vision-based gesture recognition. In this work, we introduce a 3-...
متن کاملSelective deficits in human audition: evidence from lesion studies
The human auditory cortex is the gateway to the most powerful and complex communication systems and yet relatively little is known about its functional organization as compared to the visual system. Several lines of evidence, predominantly from recent studies, indicate that sound recognition and sound localization are processed in two at least partially independent networks. Evidence from human...
متن کاملSelective deficits in human audition: evidence from lesion studies
The human auditory cortex is the gateway to the most powerful and complex communication systems and yet relatively little is known about its functional organization as compared to the visual system. Several lines of evidence, predominantly from recent studies, indicate that sound recognition and sound localization are processed in two at least partially independent networks. Evidence from human...
متن کاملHarmonic Functions and Brownian Motion in Several Dimensions
Definition 1. A standard d−dimensional Brownian motion is an Rd−valued continuous-time stochastic process {Wt}t≥0 (i.e., a family of d−dimensional random vectors Wt indexed by the set of nonnegative real numbers t) with the following properties. (A)’ W0 = 0. (B)’ With probability 1, the function t→Wt is continuous in t. (C)’ The process {Wt}t≥0 has stationary, independent increments. (D)’ The i...
متن کاملIncremental symbol-formation, clustering and self-organization of whole body motion patterns
This paper describes a novel approach for incremental symbolization and classification of observed human motion. The acquired symbols can be used for both subsequent motion recognition and generation. The resulting representation is a tree structure with the symbol at each node corresponding to its abstraction level.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Computer Vision and Image Understanding
دوره 109 شماره
صفحات -
تاریخ انتشار 2008