Learning spatio-temporal patterns for predicting object behaviour

By N. Sumpter, A. Bulpitt. 2000

124 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction (2017, neutral): “Similar approaches were later proposed by Sumpter and Bulpitt [24] and Hue et al.”
Human motion trajectory prediction: a survey (2019, methodology): “…Markov models Several recent sequential methods use neural networks for time series prediction, i.e. assuming higher order Markov property (Sumpter and Bulpitt 2000; Alahi et al. 2016; Bartoli et al. 2018; Varshneya and Srinivasaraghavan 2017; Sun et al. 2018; Jain et al. 2016; Vemula et…”
A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance (2008, background): “Vector quantization reduction is achieved by limiting the number of unique trajectories to a finite alphabet of prototypical vectors which symbolize all trajectories [8], [33], [58], [59].”
Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach (2011, methodology): “The leaky network was modified with feedback between output nodes and the leaky neurons to enable prediction by Sumpter and Bulpitt [11].”
Learning activity patterns using fuzzy self-organizing neural network (2004, methodology): “1(b) shows the neural network structure used in [26].”
Model-Based Probabilistic Collision Detection in Autonomous Driving (2009, background): “The same approaches can be applied for the traffic scenes that are observed from a fixed location, such as intersections, which allows typical behavior patterns of the specific scene to be learned; see, e.g., [17] and [30].”
A system for learning statistical motion patterns (2006, methodology): “Sumpter and Bulpitt [43] present a novel approach for learning long-term spatial-temporal patterns of object motions in image sequences using a neural network paradigm to predict future behaviors.”
Learning hierarchical spatio-temporal pattern for human activity prediction (2016, background): “Sumpter and Bulpitt [26] introduced feedback to the second competitive network to suggest a novel approach for learning long-term spatio-temporal patterns of objects in image sequences, using a neural network paradigm to predict future activities.”