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

One of the main components of an autonomous vehicle is the obstacle detectionpipeline. Most prototypes, both from research and industry, rely on lidars forthis task. Pointcloud information from lidar is usually combined with data fromcameras and radars, but the backbone of the architecture is mainly based on 3Dbounding boxes computed from lidar data. To retrieve an accuraterepresentation, sensors with many planes, e.g., greater than 32 planes, areusually employed. The returned pointcloud is indeed dense and well defined, buthigh-resolution sensors are still expensive and often require powerful GPUs tobe processed. Lidars with fewer planes are cheaper, but the returned data arenot dense enough to be processed with state of the art deep learning approachesto retrieve 3D bounding boxes. In this paper, we propose two solutions based onoccupancy grid and geometric refinement to retrieve a list of 3D bounding boxesemploying lidar with a low number of planes (i.e., 16 and 8 planes). Oursolutions have been validated on a custom acquired dataset with accurate groundtruth to prove its feasibility and accuracy.

Two algorithms for vehicular obstacle detection in sparse pointcloud