Dominant Sets-Based Action Recognition using Image Sequence Matching
Qingdi Wei,Weiming Hu,Xiaoqin Zhang,Guan Luo +3 more
- 12 Nov 2007
- Vol. 6, pp 133-136
TL;DR: This paper proposes a novel method for classifying human actions in a series of image sequences containing certain actions that is robust to non-rigid deformations, significant scale changes, high action irregularities, and low quality video.
read more
Abstract: Action recognition is one of the most active research fields in computer vision. In this paper, we propose a novel method for classifying human actions in a series of image sequences containing certain actions. Human action in image sequences can be recognized by a time-varying contour of human body. We first extract shape context of each contour to form the feature space. Then the dominant sets approach is used for feature clustering and classification to obtain the labeled sequences. Finally, we use a smoothing algorithm upon the labeled sequences to recognize human actions. The proposed dominant sets-based approach has been tested in comparison to three classical methods: K-means, mean shift, and fuzzy-C-mean. Experimental results demonstrate that the dominant sets-based approach achieves the best recognition performance. Moreover, our method is robust to non-rigid deformations, significant scale changes, high action irregularities, and low quality video.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Graph-based quadratic optimization: A fast evolutionary approach
TL;DR: A new population game dynamics (InImDyn) is proposed which is motivated by the analogy with infection and immunization processes within a population of ''players,'' and it is proved that the evolution of the dynamics is governed by a quadratic Lyapunov function, representing the average population payoff.
88
Combining Fuzzy Vector Quantization With Linear Discriminant Analysis for Continuous Human Movement Recognition
TL;DR: A novel method based on fuzzy vector quantization (FVQ) and linear discriminant analysis (LDA) that allows for simple Mahalanobis or cosine distance comparison of not aligned human movements, aiding the design of a real-time continuous human movement recognition algorithm.
43
•Proceedings Article
What is a Cluster? Perspectives from Graph Theory
Marcello Pelillo
- 01 Jan 2009
TL;DR: Despite the tremendous progress in the field, the clustering problem remains elusive and a satisfactory answer even to the most basic questions is still to come.
31
Modeling and Classifying Human Activities From Trajectories Using a Class of Space-Varying Parametric Motion Fields
TL;DR: A new way of modeling trajectories is proposed, based on a mixture of parametric motion vector fields that depend on a small number of parameters that follows a probabilistic mechanism, characterized by a field of stochastic matrices.
16
Graphical modeling and decoding of human actions
Wanqing Li,Zhengyou Zhang,Zicheng Liu +2 more
- 05 Nov 2008
TL;DR: This paper proposes to encode actions in a weighted directed graph, referred to as action graph, where nodes of the graph represent salient postures that are used to characterize the actions and shared by all actions.
References
Shape matching and object recognition using shape contexts
TL;DR: This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.
7.3K
Actions as space-time shapes
M. Blank,Lena Gorelick,E. Shechtman,Michal Irani,Ronen Basri +4 more
- 17 Oct 2005
TL;DR: The method is fast, does not require video alignment and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action and low quality video.
Silhouette analysis-based gait recognition for human identification
TL;DR: A simple but efficient gait recognition algorithm using spatial-temporal silhouette analysis is proposed that implicitly captures the structural and transitional characteristics of gait.
1.3K
Shape Classification Using the Inner-Distance
Haibin Ling,David W. Jacobs +1 more
TL;DR: It is suggested that the inner-distance can be used as a replacement for the Euclidean distance to build more accurate descriptors for complex shapes, especially for those with articulated parts.
1.2K
Identification of humans using gait
Amit Kale,Aravind Sundaresan,A. N. Rajagopalan,Naresh P. Cuntoor,Amit K. Roy-Chowdhury,Volker Krüger,Rama Chellappa +6 more
TL;DR: A view-based approach to recognize humans from their gait by employing a hidden Markov model (HMM) and the statistical nature of the HMM lends overall robustness to representation and recognition.
633