Fast Algorithms of Multi-Object Recognition and High Precision Localization for Pose Estimation

2013 ◽  
Vol 333-335 ◽  
pp. 1192-1197
Author(s):  
Ying Jin Zhang ◽  
Shi Yin Qin ◽  
Xiao Hui Hu

The recognition and localization of cooperative objects are very important for spacecraft pose estimation towards autonomous rendezvous and docking (RVD). In this paper, an adaptive threshold segmentation algorithm is proposed base on weighted maximum gray value for multi-object detection, and eight-neighborhood region growing is employed for multi-object recognition. In order to achieve high-accurate localization, a sub-pixel object positioning approach is put forward by combination bilinear interpolation with median filtering, which employs bilinear interpolation to calculate sub-pixel centroid for reducing algorithm systematic errors, and applies median filter to reduce random errors produced by image noises. The experimental results show that the proposed algorithms are feasible and effective with high positioning accuracy of 0.01 pixels, and have outstanding advantages of anti-disturbance and real-time performance, thus can satisfy the practical requirements in the visual measurement and pose estimation of cooperative objects for the RVD in space exploration.

2015 ◽  
Vol 791 ◽  
pp. 189-194
Author(s):  
Frantisek Durovsky

Presented paper describes experimental bin picking using Kinect sensor, region-growing algorithm, latest ROS-Industrial drivers and dual arm manipulator Motoman SDA10f.As well known if manipulation with objects of regular shapes by suction cup is required, it is sufficient to estimate only 5DoF for successful pick. In such a case simpler region growing algorithm may be used instead of complicated 3D object recognition and pose estimation techniques, resulting in shorter processing time and decrease of computational load. Experimental setup for such a scenario, manipulated objects and results using region growing segmentation algorithm are explained in detail. Video and link to open-source code of described application are provided as well.


2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Panfeng Huang ◽  
Lu Chen ◽  
Bin Zhang ◽  
Zhongjie Meng ◽  
Zhengxiong Liu

In the ultra-close approaching phase of tethered space robot, a highly stable self-attitude control is essential. However, due to the field of view limitation of cameras, typical point features are difficult to extract, where commonly adopted position-based visual servoing cannot be valid anymore. To provide robot’s relative position and attitude with the target, we propose a monocular visual servoing control method using only the edge lines of satellite brackets. Firstly, real time detection of edge lines is achieved based on image gradient and region growing. Then, we build an edge line based model to estimate the relative position and attitude between the robot and the target. Finally, we design a visual servoing controller combined with PD controller. Experimental results demonstrate that our algorithm can extract edge lines stably and adjust the robot’s attitude to satisfy the grasping requirements.


Sign in / Sign up

Export Citation Format

Share Document