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

This work addresses the issue of motion compensation and pattern tracking inevent camera data. An event camera generates asynchronous streams of eventstriggered independently by each of the pixels upon changes in the observedintensity. Providing great advantages in low-light and rapid-motion scenarios,such unconventional data present significant research challenges as traditionalvision algorithms are not directly applicable to this sensing modality. Theproposed method decomposes the tracking problem into a local SE(2)motion-compensation step followed by a homography registration of smallmotion-compensated event batches. The first component relies on GaussianProcess (GP) theory to model the continuous occupancy field of the events inthe image plane and embed the camera trajectory in the covariance kernelfunction. In doing so, estimating the trajectory is done similarly to GPhyperparameter learning by maximising the log marginal likelihood of the data.The continuous occupancy fields are turned into distance fields and used astemplates for homography-based registration. By benchmarking the proposedmethod against other state-of-the-art techniques, we show that our open-sourceimplementation performs high-accuracy motion compensation and produceshigh-quality tracks in real-world scenarios.

Continuous-Time Gaussian Process Motion-Compensation for Event-vision Pattern Tracking with Distance Fields