Incremental Slow Feature Analysis with Indefinite Kernel for Online Temporal Video Segmentation
نویسندگان
چکیده
Slow Feature Analysis (SFA) is a subspace learning method inspired by the human visual system, however, it is seldom seen in computer vision. Motivated by its application for unsupervised activity analysis, we develop SFA’s first implementation of online temporal video segmentation to detect episodes of motion changes. We utilize a domainspecific indefinite kernel which takes the data representation into account to introduce robustness. As our kernel is indefinite (i.e. defines instead of a Hilbert, a Krein space), we formulate SFA in Krein space. We propose an incremental kernel SFA framework which utilizes the special properties of our kernel. Finally, we employ our framework to online temporal video segmentation and perform qualitative and quantitative evaluation.
منابع مشابه
Incremental episodic segmentation and imitative learning of humanoid robot through self-exploration
Imitation learning through self-exploration is an essential mechanism in developing sensorimotor skills for human infants as well for robots. We assume that a primitive sense of self is the prerequisite for successful social interaction rather than an outcome of it. During imitation learning, a crucial element of conception involves segmenting the continuous flow of motion into simpler units – ...
متن کاملOnline Streaming Feature Selection Using Geometric Series of the Adjacency Matrix of Features
Feature Selection (FS) is an important pre-processing step in machine learning and data mining. All the traditional feature selection methods assume that the entire feature space is available from the beginning. However, online streaming features (OSF) are an integral part of many real-world applications. In OSF, the number of training examples is fixed while the number of features grows with t...
متن کاملOnline Action Recognition via Nonparametric Incremental Learning
We introduce an online action recognition system that can be combined with any set of frame-by-frame feature descriptors. Our system covers the frame feature space with classifiers whose distribution adapts to the hardness of locally approximating the Bayes optimal classifier. An efficient nearest neighbour search is used to find and combine the local classifiers that are closest to the frames ...
متن کاملUnsupervised Temporal Segmentation of Human Activities in Video
Human motion analysis from video has attracted much interest from computer vision researchers due to its promising applications for visual surveillance, perceptual user interface, content-based image storage and retrieval, video conferencing, athletic performance analysis and virtual reality. A key aspect to understand and build computational models of human actions is the capability to tempora...
متن کاملSubspace Learning in Krein Spaces: Complete Kernel Fisher Discriminant Analysis with Indefinite Kernels
Positive definite kernels, such as Gaussian Radial Basis Functions (GRBF), have been widely used in computer vision for designing feature extraction and classification algorithms. In many cases nonpositive definite (npd) kernels and non metric similarity/dissimilarity measures naturally arise (e.g., Hausdorff distance, Kullback Leibler Divergences and Compact Support (CS) Kernels). Hence, there...
متن کامل