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

LiDAR sensors are widely used for 3D object detection in various mobilerobotics applications. LiDAR sensors continuously generate point cloud data inreal-time. Conventional 3D object detectors detect objects using a set ofpoints acquired over a fixed duration. However, recent studies have shown thatthe performance of object detection can be further enhanced by utilizingspatio-temporal information obtained from point cloud sequences. In this paper,we propose a new 3D object detector, named D-Align, which can effectivelyproduce strong bird's-eye-view (BEV) features by aligning and aggregating thefeatures obtained from a sequence of point sets. The proposed method includes anovel dual-query co-attention network that uses two types of queries, includingtarget query set (T-QS) and support query set (S-QS), to update the features oftarget and support frames, respectively. D-Align aligns S-QS to T-QS based onthe temporal context features extracted from the adjacent feature maps and thenaggregates S-QS with T-QS using a gated attention mechanism. The dual queriesare updated through multiple attention layers to progressively enhance thetarget frame features used to produce the detection results. Our experiments onthe nuScenes dataset show that the proposed D-Align method greatly improved theperformance of a single frame-based baseline method and significantlyoutperformed the latest 3D object detectors.

D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence