MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation

10/05/2022
by   Hanwei Zhang, et al.
6

Visual SLAM systems targeting static scenes have been developed with satisfactory accuracy and robustness. Dynamic 3D object tracking has then become a significant capability in visual SLAM with the requirement of understanding dynamic surroundings in various scenarios including autonomous driving, augmented and virtual reality. However, performing dynamic SLAM solely with monocular images remains a challenging problem due to the difficulty of associating dynamic features and estimating their positions. In this paper, we present MOTSLAM, a dynamic visual SLAM system with the monocular configuration that tracks both poses and bounding boxes of dynamic objects. MOTSLAM first performs multiple object tracking (MOT) with associated both 2D and 3D bounding box detection to create initial 3D objects. Then, neural-network-based monocular depth estimation is applied to fetch the depth of dynamic features. Finally, camera poses, object poses, and both static, as well as dynamic map points, are jointly optimized using a novel bundle adjustment. Our experiments on the KITTI dataset demonstrate that our system has reached best performance on both camera ego-motion and object tracking on monocular dynamic SLAM.

READ FULL TEXT

page 1

page 4

page 5

page 7

research
10/15/2020

DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM

The assumption of scene rigidity is common in visual SLAM algorithms. Ho...
research
06/01/2018

CubeSLAM: Monocular 3D Object Detection and SLAM without Prior Models

We present a method for single image 3D cuboid object detection and mult...
research
11/26/2018

Joint Monocular 3D Vehicle Detection and Tracking

3D vehicle detection and tracking from a monocular camera requires detec...
research
09/30/2020

DOT: Dynamic Object Tracking for Visual SLAM

In this paper we present DOT (Dynamic Object Tracking), a front-end that...
research
10/07/2022

TRADE: Object Tracking with 3D Trajectory and Ground Depth Estimates for UAVs

We propose TRADE for robust tracking and 3D localization of a moving tar...
research
07/14/2023

Dynamic Object Tracking for Quadruped Manipulator with Spherical Image-Based Approach

Exactly estimating and tracking the motion of surrounding dynamic object...
research
11/26/2022

DynaVIG: Monocular Vision/INS/GNSS Integrated Navigation and Object Tracking for AGV in Dynamic Scenes

Visual-Inertial Odometry (VIO) usually suffers from drifting over long-t...

Please sign up or login with your details

Forgot password? Click here to reset