Short-Baseline Binocular Vision System for a Humanoid Ping-Pong Robot

Abstract

We develop a short-baseline vision system for a humanoid ping-pong robot. The vision system can provide four-dimensional space-time information and can predict the future trajectory of a ball. Short baseline poses special challenges for achieving sufficient 3-D reconstruction and prediction accuracy within limited processing time. We propose two algorithms including direct calibration of projection matrix and Gaussian-fitting based ball-center location to guarantee the 3-D reconstruction accuracy; we propose algorithm of five-point based ball representation and utilize the constraint of ball detecting region to guarantee the processing speed; we also propose algorithm of smoothing-based trajectory prediction to improve the prediction accuracy. Experimental results show the accuracy and the speed of our vision system can meet the requirements of a humanoid ping-pong robot.

Intelligent Path Recognition against Image Noises for Vision Guidance of Automated Guided Vehicles in a Complex Workspace

“…The number of the hidden-layer nodes is determined according to the empirical formula. p = s + q+a (11) where s is the number of the input nodes, q is the number of the output nodes, and a is a constant between 1 and 10. The traditional BP learning algorithm is sensitive to the learning rate.…”

“…It seems that scientific results published to date neither provide sufficient accuracy for industrial applications nor have they been extensively tested in realistic, industrial-like operating conditions [10]. In fact, the recognition performance of machine vision systems is susceptible to external environments, especially the surrounding illumination [11,12]. As mentioned by Garibotto in [6], future developments should concern how to improve the adaptability of the vision system to illumination changes, since the frame grabber gain and offset parameters in image processing have to be adjusted in the light of variable contrast conditions.…”

Scale Estimation and Correction of the Monocular Simultaneous Localization and Mapping (SLAM) Based on Fusion of 1D Laser Range Finder and Vision Data

“…For instance, the widely used stereo-SLAM, which uses the real-scale information contained in the fixed baseline between the two cameras to locate and map [ 32 , 33 ]. The depth estimation and the mapping range of the binocular vision heavily rely on the baseline length and the calibration accuracy between the cameras [ 34 ]. On the other hand, with the advent of the RGB-D sensors which capture RGB images along with the per-pixel depth information.…”

A Robust Vision Module for Humanoid Robotic Ping-Pong Game

“…They compute the centre of the ball by averaging the four outermost points on vertical and horizontal boundaries of the contour. Tian et al [23] used a similar five-point method to detect the centre of the ball. The thresholding method was very fast.…”

“…It was an interesting solution but depended heavily on the shadow and environment light. Some other work used binocular cameras [4–6, 8, 14, 15, 17, 22, 23] to improve perception precision. The resolution of these binocular cameras ranged from 232times232 to 2048times2048.…”