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

Radars, due to their robustness to adverse weather conditions and ability tomeasure object motions, have served in autonomous driving and intelligentagents for years. However, Radar-based perception suffers from its unintuitivesensing data, which lack of semantic and structural information of scenes. Totackle this problem, camera and Radar sensor fusion has been investigated as atrending strategy with low cost, high reliability and strong maintenance. Whilemost recent works explore how to explore Radar point clouds and images, richcontextual information within Radar observation are discarded. In this paper,we propose a hybrid point-wise Radar-Optical fusion approach for objectdetection in autonomous driving scenarios. The framework benefits from densecontextual information from both the range-doppler spectrum and images whichare integrated to learn a multi-modal feature representation. Furthermore, wepropose a novel local coordinate formulation, tackling the object detectiontask in an object-centric coordinate. Extensive results show that with theinformation gained from optical images, we could achieve leading performance inobject detection (97.69\% recall) compared to recent state-of-the-art methodsFFT-RadNet (82.86\% recall). Ablation studies verify the key design choices andpracticability of our approach given machine generated imperfect detections.The code will be available at https://github.com/LiuLiu-55/ROFusion.

ROFusion: Efficient Object Detection using Hybrid Point-wise Radar-Optical Fusion