Related Experiment Video
Updated: Oct 30, 2025
09:41
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
Published on: April 21, 2023
1.9K
Pose Estimation of Excavator Manipulator Based on Monocular Vision Marker System
Jiangying Zhao1, Yongbiao Hu1, Mingrui Tian1
1National Engineering Laboratory for Highway Maintenance Equipment, Chang'an University, Xi'an 710064, China.
Sensors (Basel, Switzerland)
|July 2, 2021
Summary
This study introduces a computer vision (CV) method using a monocular camera and marker to track excavator manipulator poses in real-time. The system achieves accurate pose estimation, enhancing safety and productivity in construction.
Area of Science:
- Construction Engineering
- Computer Vision
- Robotics
Background:
- Excavation safety and productivity are critical in construction.
- Real-time monitoring of excavator manipulator poses is needed to address these challenges.
- Existing monitoring methods may lack accuracy or efficiency.
Purpose of the Study:
- To develop and validate a computer vision-based system for real-time excavator manipulator pose estimation.
- To improve safety and productivity in construction excavation operations.
- To provide an alternative monitoring technology for heavy construction machinery.
Main Methods:
- Utilized computer vision (CV) technology with a monocular camera and a marker.
- Developed a measurement system to simulate pose estimation.
- Conducted comprehensive experiments and error analysis to evaluate system performance.
Main Results:
- The system demonstrated a maximum detectable depth exceeding 11 meters.
- Orientation error was found to be less than 8.5 degrees.
- Position error was measured to be less than 22 millimeters.
Conclusions:
- The proposed CV approach is feasible for real-time excavator manipulator pose estimation.
- The system offers a viable alternative for monitoring construction machines.
- This technology has the potential to enhance safety and productivity in excavation.
