Nvidia corporation (20240410981). TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

Organization Name

nvidia corporation

Inventor(s)

Nikolai Smolyanskiy of Seattle WA (US)

Ryan Oldja of Redmond WA (US)

Ke Chen of Sunnyvale CA (US)

Alexander Popov of Kirkland WA (US)

Joachim Pehserl of Lynnwood WA (US)

Ibrahim Eden of Redmond WA (US)

Tilman Wekel of Sunnyvale CA (US)

David Wehr of Redmond WA (US)

Ruchi Bhargava of Redmond WA (US)

David Nister of Bellevue WA (US)

TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

This abstract first appeared for US patent application 20240410981 titled 'TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

Original Abstract Submitted

a deep neural network(s) (dnn) may be used to detect objects from sensor data of a three dimensional (3d) environment. for example, a multi-view perception dnn may include multiple constituent dnns or stages chained together that sequentially process different views of the 3d environment. an example dnn may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). the dnn outputs may be processed to generate 2d and/or 3d bounding boxes and class labels for detected objects in the 3d environment. as such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.