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 accurately detect and localize objects is recognized as beingthe most important for the perception of self-driving cars. From 2D to 3Dobject detection, the most difficult is to determine the distance from theego-vehicle to objects. Expensive technology like LiDAR can provide a preciseand accurate depth information, so most studies have tended to focus on thissensor showing a performance gap between LiDAR-based methods and camera-basedmethods. Although many authors have investigated how to fuse LiDAR with RGBcameras, as far as we know there are no studies to fuse LiDAR and stereo in adeep neural network for the 3D object detection task. This paper presentsSLS-Fusion, a new approach to fuse data from 4-beam LiDAR and a stereo cameravia a neural network for depth estimation to achieve better dense depth mapsand thereby improves 3D object detection performance. Since 4-beam LiDAR ischeaper than the well-known 64-beam LiDAR, this approach is also classified asa low-cost sensors-based method. Through evaluation on the KITTI benchmark, itis shown that the proposed method significantly improves depth estimationperformance compared to a baseline method. Also, when applying it to 3D objectdetection, a new state of the art on low-cost sensor based method is achieved.

Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection