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

Understanding the semantic characteristics of the environment is a keyenabler for autonomous robot operation. In this paper, we propose a deepconvolutional neural network (DCNN) for the semantic segmentation of a LiDARscan into the classes car, pedestrian or bicyclist. This architecture is basedon dense blocks and efficiently utilizes depth separable convolutions to limitthe number of parameters while still maintaining state-of-the-art performance.To make the predictions from the DCNN temporally consistent, we propose a Bayesfilter based method. This method uses the predictions from the neural networkto recursively estimate the current semantic state of a point in a scan. Thisrecursive estimation uses the knowledge gained from previous scans, therebymaking the predictions temporally consistent and robust towards isolatederroneous predictions. We compare the performance of our proposed architecturewith other state-of-the-art neural network architectures and report substantialimprovement. For the proposed Bayes filter approach, we show results on varioussequences in the KITTI tracking benchmark.

DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scans