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

The ability to reliably perceive the environmental states, particularly theexistence of objects and their motion behavior, is crucial for autonomousdriving. In this work, we propose an efficient deep model, called MotionNet, tojointly perform perception and motion prediction from 3D point clouds.MotionNet takes a sequence of LiDAR sweeps as input and outputs a bird's eyeview (BEV) map, which encodes the object category and motion information ineach grid cell. The backbone of MotionNet is a novel spatio-temporal pyramidnetwork, which extracts deep spatial and temporal features in a hierarchicalfashion. To enforce the smoothness of predictions over both space and time, thetraining of MotionNet is further regularized with novel spatial and temporalconsistency losses. Extensive experiments show that the proposed method overalloutperforms the state-of-the-arts, including the latest scene-flow- and3D-object-detection-based methods. This indicates the potential value of theproposed method serving as a backup to the bounding-box-based system, andproviding complementary information to the motion planner in autonomousdriving. Code is available at https://github.com/pxiangwu/MotionNet.

MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps