Authors:
Laure Acin
1
;
Pierre Jacob
2
;
Camille Simon-Chane
1
and
Aymeric Histace
1
Affiliations:
1
ETIS UMR 8051, CY Cergy Paris University, ENSEA, CNRS, F-95000, Cergy, France
;
2
Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France
Keyword(s):
Event-based Camera, Event-based Vision, Asynchronous Camera, Machine Learning, Time-surface, Recognition.
Abstract:
Event-based cameras are a recent non-conventional sensor which offer a new movement perception with low latency, high power efficiency, high dynamic range and high-temporal resolution. However, event data is asynchronous and sparse thus standard machine learning and deep learning tools are not optimal for this data format. A first step of event-based processing often consists in generating image-like representations from events, such as time-surfaces. Such event representations are proposed with specific applications. These event representations and learning algorithms are most often evaluated together. Furthermore, these methods are often evaluated in a non-rigorous way (i.e. by performing the validation on the testing set). We propose a generic event representation for multiple applications: a trainable extension of Speed Invariant Time Surface, coined VK-SITS. This speed and spatial-invariant framework is computationally fast and GPU-friendly. A second contribution is a new benchm
ark based on 10-Fold cross-validation to better evaluate event-based representation of DVS128 Gesture and N-Caltech101 recognition datasets. Our VK-SITS event-based representation improves recognition performance of state-of-art methods.
(More)