Related Experiment Video
Updated: Aug 10, 2025

Bringing the Visible Universe into Focus with Robo-AO
Published on: February 12, 2013
An Adaptive ORB-SLAM3 System for Outdoor Dynamic Environments
Qiuyu Zang1, Kehua Zhang2, Ling Wang2
1College of Mathematics and Computer Science, Zhejiang Normal University, Yingbin Avenue, Jinhua 321005, China.
This study introduces an adaptive system to improve visual simultaneous localization and mapping (SLAM) accuracy in dynamic outdoor environments by intelligently selecting feature points. The method significantly reduces trajectory errors compared to existing approaches.
Area of Science:
- Robotics
- Computer Vision
- Artificial Intelligence
Background:
- Visual SLAM (Simultaneous Localization and Mapping) faces accuracy challenges in dynamic environments due to moving objects.
- Dynamic objects disrupt epipolar geometry, leading to localization errors in robotic systems.
Purpose of the Study:
- To develop a novel method for enhancing visual SLAM accuracy in outdoor dynamic environments.
- To address the problem of reduced localization precision caused by dynamic objects.
Main Methods:
- Utilized YOLOv5s with an attention mechanism for initial detection of dynamic objects.
- Implemented an adaptive feature point selection system based on dynamic object presence and frame occupancy.
- Employed Lucas-Kanade optical flow and RANSAC for dynamic region determination.
Main Results:
- The proposed system demonstrated significant reductions in Absolute Trajectory Error (up to 39%) and Relative Trajectory Error (up to 30%) on the KITTI dataset.
- Outperformed various dynamic feature point selection strategies and DynaSLAM in accuracy evaluations.
Conclusions:
- The adaptive feature point selection system effectively mitigates the negative impact of dynamic objects on visual SLAM.
- This approach offers a robust solution for improving robotic localization in complex, dynamic outdoor settings.
More Related Videos
Related Concept Videos
One-Degree-of-Freedom System
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
Relative Motion Analysis using Rotating Axes
However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
Three-Dimensional Force System
Three-Dimensional Force System:Problem Solving
To solve a three-dimensional force system, first resolve each force into its respective scalar components. Do this using...
Planar Rigid-Body Motion
Planar motion is typically divided into three distinct categories. The first is rectilinear translation, demonstrated by a subway train that moves along...

