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

In this paper we propose a novel 3D single-shot object detection method fordetecting vehicles in monocular RGB images. Our approach lifts 2D detections to3D space by predicting additional regression and classification parameters andhence keeping the runtime close to pure 2D object detection. The additionalparameters are transformed to 3D bounding box keypoints within the networkunder geometric constraints. Our proposed method features a full 3D descriptionincluding all three angles of rotation without supervision by any labeledground truth data for the object's orientation, as it focuses on certainkeypoints within the image plane. While our approach can be combined with anymodern object detection framework with only little computational overhead, weexemplify the extension of SSD for the prediction of 3D bounding boxes. We testour approach on different datasets for autonomous driving and evaluate it usingthe challenging KITTI 3D Object Detection as well as the novel nuScenes ObjectDetection benchmarks. While we achieve competitive results on both benchmarkswe outperform current state-of-the-art methods in terms of speed with more than20 FPS for all tested datasets and image resolutions.

Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time