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 comprehensive representation and understanding of the driving environmentis crucial to improve the safety and reliability of autonomous vehicles. Inthis paper, we present a new approach to establish an environment modelcontaining a segmentation between static and dynamic background and parametricmodeled objects with shape, position and orientation. Multiple laser scannersare fused into a dynamic occupancy grid map resulting in a 360{\deg} perceptionof the environment. A single-stage deep convolutional neural network iscombined with a recurrent neural network, which takes a time series of theoccupancy grid map as input and tracks cell states and its corresponding objecthypotheses. The labels for training are created unsupervised with an automaticlabel generation algorithm.  The proposed methods are evaluated in real-world experiments in complex innercity scenarios using the aforementioned 360{\deg} laser perception. The resultsshow a better object detection accuracy in comparison with our old approach aswell as an AUC score of 0.946 for the dynamic and static segmentation.Furthermore, we gain an improved detection for occluded objects and a moreconsistent size estimation due to the usage of time series as input and thememory about previous states introduced by the recurrent neural network.

Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs