Objects as Spatio-Temporal 2.5D points

12/06/2022
by   Paridhi Singh, et al.
0

Determining accurate bird's eye view (BEV) positions of objects and tracks in a scene is vital for various perception tasks including object interactions mapping, scenario extraction etc., however, the level of supervision required to accomplish that is extremely challenging to procure. We propose a light-weight, weakly supervised method to estimate 3D position of objects by jointly learning to regress the 2D object detections and scene's depth prediction in a single feed-forward pass of a network. Our proposed method extends a center-point based single-shot object detector, and introduces a novel object representation where each object is modeled as a BEV point spatio-temporally, without the need of any 3D or BEV annotations for training and LiDAR data at query time. The approach leverages readily available 2D object supervision along with LiDAR point clouds (used only during training) to jointly train a single network, that learns to predict 2D object detection alongside the whole scene's depth, to spatio-temporally model object tracks as points in BEV. The proposed method is computationally over ∼10x efficient compared to recent SOTA approaches while achieving comparable accuracies on KITTI tracking benchmark.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

research
12/14/2021

Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds

In this paper, we propose a new joint object detection and tracking (JoD...
research
10/29/2022

Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision

Recent advances in monocular 3D detection leverage a depth estimation ne...
research
02/24/2021

4D Panoptic LiDAR Segmentation

Temporal semantic scene understanding is critical for self-driving cars ...
research
04/25/2022

MLO: Multi-Object Tracking and Lidar Odometry in Dynamic Environment

The SLAM system built on the static scene assumption will introduce sign...
research
09/01/2021

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds

To date, various 3D scene understanding tasks still lack practical and g...
research
09/08/2023

Weakly Supervised Point Clouds Transformer for 3D Object Detection

The annotation of 3D datasets is required for semantic-segmentation and ...

Please sign up or login with your details

Forgot password? Click here to reset