English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper we compare event-based decaying and time based-decaying memorysurfaces for high-speed eventbased tracking, feature extraction, and objectclassification using an event-based camera. The high-speed recognition taskinvolves detecting and classifying model airplanes that are dropped free-handclose to the camera lens so as to generate a challenging dataset exhibitingsignificant variance in target velocity. This variance motivated theinvestigation of event-based decaying memory surfaces in comparison totime-based decaying memory surfaces to capture the temporal aspect of theevent-based data. These surfaces are then used to perform unsupervised featureextraction, tracking and recognition. In order to generate the memory surfaces,event binning, linearly decaying kernels, and exponentially decaying kernelswere investigated with exponentially decaying kernels found to perform best.Event-based decaying memory surfaces were found to outperform time-baseddecaying memory surfaces in recognition especially when invariance to targetvelocity was made a requirement. A range of network and receptive field sizeswere investigated. The system achieves 98.75% recognition accuracy within 156milliseconds of an airplane entering the field of view, using only twenty-fiveevent-based feature extracting neurons in series with a linear classifier. Bycomparing the linear classifier results to an ELM classifier, we find that asmall number of event-based feature extractors can effectively project thecomplex spatio-temporal event patterns of the dataset to an almost linearlyseparable representation in feature space.

Investigation of event-based memory surfaces for high-speed tracking, unsupervised feature extraction and object recognition