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

Accurate moving object segmentation is an essential task for autonomousdriving. It can provide effective information for many downstream tasks, suchas collision avoidance, path planning, and static map construction. How toeffectively exploit the spatial-temporal information is a critical question for3D LiDAR moving object segmentation (LiDAR-MOS). In this work, we propose anovel deep neural network exploiting both spatial-temporal information anddifferent representation modalities of LiDAR scans to improve LiDAR-MOSperformance. Specifically, we first use a range image-based dual-branchstructure to separately deal with spatial and temporal information that can beobtained from sequential LiDAR scans, and later combine them usingmotion-guided attention modules. We also use a point refinement module via 3Dsparse convolution to fuse the information from both LiDAR range image andpoint cloud representations and reduce the artifacts on the borders of theobjects. We verify the effectiveness of our proposed approach on the LiDAR-MOSbenchmark of SemanticKITTI. Our method outperforms the state-of-the-art methodssignificantly in terms of LiDAR-MOS IoU. Benefiting from the devisedcoarse-to-fine architecture, our method operates online at sensor frame rate.The implementation of our method is available as open source at:https://github.com/haomo-ai/MotionSeg3D.

Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation