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/

Zendy Plus

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

Zendy Tools

Zendy Open

Event-based cameras display great potential for a variety of tasks such ashigh-speed motion detection and navigation in low-light environments whereconventional frame-based cameras suffer critically. This is attributed to theirhigh temporal resolution, high dynamic range, and low-power consumption.However, conventional computer vision methods as well as deep Analog NeuralNetworks (ANNs) are not suited to work well with the asynchronous and discretenature of event camera outputs. Spiking Neural Networks (SNNs) serve as idealparadigms to handle event camera outputs, but deep SNNs suffer in terms ofperformance due to the spike vanishing phenomenon. To overcome these issues, wepresent Spike-FlowNet, a deep hybrid neural network architecture integratingSNNs and ANNs for efficiently estimating optical flow from sparse event cameraoutputs without sacrificing the performance. The network is end-to-end trainedwith self-supervised learning on Multi-Vehicle Stereo Event Camera (MVSEC)dataset. Spike-FlowNet outperforms its corresponding ANN-based method in termsof the optical flow prediction capability while providing significantcomputational efficiency.

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks