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

Event-based cameras are predestined for Intelligent Transportation Systems(ITS). They provide very high temporal resolution and dynamic range, which caneliminate motion blur and make objects easier to recognize at night. However,event-based images lack color and texture compared to images from aconventional rgb camera. Considering that, data fusion between event-based andconventional cameras can combine the strengths of both modalities. For thispurpose, extrinsic calibration is necessary. To the best of our knowledge, notargetless calibration between event-based and rgb cameras can handle multiplemoving objects, nor data fusion optimized for the domain of roadside ITSexists, nor synchronized event-based and rgb camera datasets in the field ofITS are known. To fill these research gaps, based on our previous work, weextend our targetless calibration approach with clustering methods to handlemultiple moving objects. Furthermore, we develop an early fusion, simple latefusion, and a novel spatiotemporal late fusion method. Lastly, we publish theTUMTraf Event Dataset, which contains more than 4k synchronized event-based andrgb images with 21.9k labeled 2D boxes. During our extensive experiments, weverified the effectiveness of our calibration method with multiple movingobjects. Furthermore, compared to a single rgb camera, we increased thedetection performance of up to +16% mAP in the day and up to +12% mAP in thechallenging night with our presented event-based sensor fusion methods. TheTUMTraf Event Dataset is available athttps://innovation-mobility.com/tumtraf-dataset.

TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras