Efficient spatio-temporal feature clustering for large event-based datasets. Issue 4 (1st December 2022)

• Record Type: Journal Article
• Authors: Oubari, Omar; Exarchakis, Georgios; Lenz, Gregor; Benosman, Ryad; Ieng, Sio-Hoi
• Is Part Of: Neuromorphic computing and engineering. Volume 2:Issue 4(2022)
• Publication Date: 2022-12-01
• Subjects: clusterings -- asynchronous vision -- event-based processing -- feature extraction -- Gaussian mixture model; Neural networks (Computer science) -- Periodicals; Neural computers -- Periodicals; Neuromorphics -- Periodicals; 006.3
• DOI: 10.1088/2634-4386/ac970d
• Languages: English
• ISSNs: 2634-4386

Abstract

Abstract: Event-based cameras encode changes in a visual scene with high temporal precision and low power consumption, generating millions of events per second in the process. Current event-based processing algorithms do not scale well in terms of runtime and computational resources when applied to a large amount of data. This problem is further exacerbated by the development of high spatial resolution vision sensors. We introduce a fast and computationally efficient clustering algorithm that is particularly designed for dealing with large event-based datasets. The approach is based on the expectation-maximization (EM) algorithm and relies on a stochastic approximation of the E-step over a truncated space to reduce the computational burden and speed up the learning process. We evaluate the quality, complexity, and stability of the clustering algorithm on a variety of large event-based datasets, and then validate our approach with a classification task. The proposed algorithm is significantly faster than standard k-means and reduces computational demands by two to three orders of magnitude while being more stable, interpretable, and close to the state of the art in terms of classification accuracy.