An instantaneous topological mapping model for correlated stimuli

Jockusch, J.; Ritter, Helge

doi:10.1109/ijcnn.1999.831553

Cited by 65 publications

(57 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the proposed approach, the system incrementally learns (following the observation of the location of the vehicle at each time step) a topological map via the Instantaneous Topological Map (ITM) algorithm [23]. In this algorithm, for each observed location, nearest nodes and edges are updated, including centroid adaptation for the closest node, as well as edge and node addition/deletion.…”

Section: A Related Workmentioning

confidence: 99%

Incremental learning of human behaviors using hierarchical hidden Markov models

Kulić

Nakamura

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper proposes a novel approach for extracting a model of movement primitives and their sequential relationships during online observation of human motion. In the proposed approach, movement primitives, modeled as hidden Markov models, are autonomously segmented and learned incrementally during observation. At the same time, a higher abstraction level hidden Markov model is also learned, encapsulating the relationship between the movement primitives. For the higher level model, each hidden state represents a motion primitive, and the observation function is based on the likelihood that the observed data is generated by the motion primitive model. An approach for incremental training of the higher order model during online observation is developed. The approach is validated on a dataset of continuous movement data.

show abstract

Section: A Related Workmentioning

confidence: 99%

Incremental learning of human behaviors using hierarchical hidden Markov models

Kulić

Nakamura

2010

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Therefore, structure learning consists basically in estimating the best space discretization from data and identifying neighboring regions. We have addressed this problem by building a topological map of the environment using the Instantaneous Topological Map (ITM) algorithm [4]. For parameter learning, we basically have adapted the approach proposed by Neal and Hinton [8] in order to deal with variable state cardinality and continuous observations.…”

Section: Growing Hidden Markov Modelsmentioning

confidence: 99%

“…(1) 4 Since space is limited, we have opted for providing a general overview which omits some specific information on optimizations and data structures. The interested reader is referred to [11] for more details.…”

Section: Probabilistic Modelmentioning

confidence: 99%

Incremental Learning of Statistical Motion Patterns With Growing Hidden Markov Models

Vasquez

Fraichard²,

Laugier³

2009

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Summary.Modeling and predicting human and vehicle motion is an active research domain. Due to the difficulty of modeling the various factors that determine motion (eg internal state, perception, etc.) this is often tackled by applying machine learning techniques to build a statistical model, using as input a collection of trajectories gathered through a sensor (eg camera, laser scanner), and then using that model to predict further motion. Unfortunately, most current techniques use off-line learning algorithms, meaning that they are not able to learn new motion patterns once the learning stage has finished. In this paper, we present an approach which is able to learn new motion patterns incrementally, and in parallel with prediction. Our work is based on a novel extension to Hidden Markov Models called Growing Hidden Markov models.

show abstract

“…Contrary to pure color segmentation schemes, we allow for combinations of all kinds of topographic feature maps like edge maps, intensity, difference images, velocity fields, disparity, image position, or different color spaces for forming a combined feature space. In this paper, for the sake of computational efficiency we apply a straightforward vector quantization method to partition this feature space, though more advanced schemes like growing networks as the growing neural gas (29) or the instantaneous topological map (30) can also be used. The vector quantization generates a codebook and respective best-match segments for each codebook vector, which define an over-segmentation of the object and the surround.…”

Section: Introductionmentioning

confidence: 99%

Adaptive scene dependent filters for segmentation and online learning of visual objects

et al. 2007

Self Cite

View full text Add to dashboard Cite

We propose the Adaptive Scene Dependent Filter (ASDF) hierarchy for unsupervised learning of image segmentation, which integrates several processing pathways into a flexible, highly dynamic, and real-time capable vision architecture. It is based on forming a combined feature space from basic feature maps like, color, disparity, and pixel position. To guarantee real-time performance, we apply an enhanced vector quantization method to partition this feature space. The learned codebook defines corresponding best-match segments for each prototype and yields an oversegmentation of the object and the surround. The segments are recombined into a final object segmentation mask based on a relevance map, which encodes a coarse bottom-up hypothesis where the object is located in the image. We apply the ASDF hierarchy for preprocessing input images in a feature-based biologically motivated object recognition learning architecture. and show experiments with this real-time vision system running at 6 Hz including the online learning of the segmentation. Because interaction with user is not perfect, the real world system acquires useful views effectively only at about 1.5 Hz, but we show that for training a new object one hundred views taking only one minute of interaction time is sufficient.

show abstract

An instantaneous topological mapping model for correlated stimuli

Cited by 65 publications

References 6 publications

Incremental learning of human behaviors using hierarchical hidden Markov models

Incremental learning of human behaviors using hierarchical hidden Markov models

Incremental Learning of Statistical Motion Patterns With Growing Hidden Markov Models

Adaptive scene dependent filters for segmentation and online learning of visual objects

Contact Info

Product

Resources

About