SRCN3D: Sparse R-CNN 3D Surround-View Camera Object Detection and Tracking for Autonomous Driving

06/29/2022
by   Yining Shi, et al.
0

Detection And Tracking of Moving Objects (DATMO) is an essential component in environmental perception for autonomous driving. While 3D detectors using surround-view cameras are just flourishing, there is a growing tendency of using different transformer-based methods to learn queries in 3D space from 2D feature maps of perspective view. This paper proposes Sparse R-CNN 3D (SRCN3D), a novel two-stage fully-convolutional mapping pipeline for surround-view camera detection and tracking. SRCN3D adopts a cascade structure with twin-track update of both fixed number of proposal boxes and proposal latent features. Proposal boxes are projected to perspective view so as to aggregate Region of Interest (RoI) local features. Based on that, proposal features are refined via a dynamic instance interactive head, which then generates classification and the offsets applied to original bounding boxes. Compared to prior arts, our sparse feature sampling module only utilizes local 2D features for adjustment of each corresponding 3D proposal box, leading to a complete sparse paradigm. The proposal features and appearance features are both taken in data association process in a multi-hypotheses 3D multi-object tracking approach. Extensive experiments on nuScenes dataset demonstrate the effectiveness of our proposed SRCN3D detector and tracker. Code is available at https://github.com/synsin0/SRCN3D.

READ FULL TEXT

page 4

page 7

page 8

research
05/02/2022

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

Accurate and consistent 3D tracking from multiple cameras is a key compo...
research
09/09/2019

MLOD: A multi-view 3D object detection based on robust feature fusion method

This paper presents Multi-view Labelling Object Detector (MLOD). The det...
research
05/04/2022

Dynamic Sparse R-CNN

Sparse R-CNN is a recent strong object detection baseline by set predict...
research
08/17/2023

BOTT: Box Only Transformer Tracker for 3D Object Tracking

Tracking 3D objects is an important task in autonomous driving. Classica...
research
09/27/2022

CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection

To achieve accurate 3D object detection at a low cost for autonomous dri...
research
10/14/2022

Superpixel Perception Graph Neural Network for Intelligent Defect Detection

Aero-engine is the core component of aircraft and other spacecraft. The ...
research
12/29/2022

On Deep Recurrent Reinforcement Learning for Active Visual Tracking of Space Noncooperative Objects

Active tracking of space noncooperative object that merely relies on vis...

Please sign up or login with your details

Forgot password? Click here to reset