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 autonomous driving, 3D object detection based on multi-modal data hasbecome an indispensable approach when facing complex environments around thevehicle. During multi-modal detection, LiDAR and camera are simultaneouslyapplied for capturing and modeling. However, due to the intrinsic discrepanciesbetween the LiDAR point and camera image, the fusion of the data for objectdetection encounters a series of problems. Most multi-modal detection methodsperform even worse than LiDAR-only methods. In this investigation, we propose amethod named PTA-Det to improve the performance of multi-modal detection.Accompanied by PTA-Det, a Pseudo Point Cloud Generation Network is proposed,which can convert image information including texture and semantic features bypseudo points. Thereafter, through a transformer-based Point Fusion Transition(PFT) module, the features of LiDAR points and pseudo points from image can bedeeply fused under a unified point-based representation. The combination ofthese modules can conquer the major obstacle in feature fusion acrossmodalities and realizes a complementary and discriminative representation forproposal generation. Extensive experiments on the KITTI dataset show thePTA-Det achieves a competitive result and support its effectiveness.

PTA-Det: Point Transformer Associating Point cloud and Image for 3D Object Detection