|
Real-Time Vision-Based Localization of Planar Cable-Driven Parallel Robot |
|
Muhammad Awais(Chonnam National University,, Korea), Chang-Sei Kim(Chonnam National University, Korea) |
| Cable-driven parallel robot (CDPR) is a special class of parallel manipulators where the motion of end-effector (EE) is controlled by flexible cables attached to it. In industrial robotics field, CDPRs have quite a high usability. Recently, kinematics and dynamics of CDPRs have been analyzed intensively. But still, there is a problem in identification of position and orientation which need to be researched. In this study, we developed a real-time vision-based localization technique for EE of planar CDPR. We developed a robust algorithm which includes camera calibration and real-time monitoring |
|
|
Estimation of traveling direction of car body using optical flow derived from onboard camera |
|
Hiromichi Koba(Kumamoto university, Japan), Teruo Yamaguchi, Hiroshi Harada(Kumamoto University, Japan) |
| In recent years, an increase in traffic accidents of elderly people became a problem in Japan. Causes of accidents include decline in cognitive function and muscular strength. If they are given a lot of diagnostic opportunities, they can review their driving ability. In order to diagnose the driving ability, it is necessary to estimate the situation of the car. Therefore, in this paper, as the elementary stage of diagnosis, only the information of the image derived from the onboard camera is used to estimate the traveling direction of the car body.
|
|
|
Loosely-Coupled INS/Vision based Absolute Navigation with Adaptive Kalman Filter |
|
Sung Hyuk Choi, Chan Gook Park(Seoul National University, Korea) |
| We represent adaptive Kalman filter which combines advantages of fast output inertial navigation and slow
image based absolute navigation algorithm. In the feature matching process of the scene-matching algorithm, the outliers occasionally occur, resulting in the problem that the state variables of the Kalman filter diverge due to the mismatched improper navigation results. We propose an adaptive Kalman filter algorithm to solve this problem. |
|
|
Semantic Scene Recognition and Zone Labeling for Mobile Robot Benchmark Datasets based on Category Maps |
|
Ryoma Fukushi, Hirokazu Madokoro, Kazuhito Sato(Akita Prefectural University, Japan) |
| For this study, we focus on autonomous locomotion based on visual landmarks that recognizes surrounding environments based on saliency characteristics. This paper presents a feature extraction method combined with saliency maps (SMs), histograms of oriented gradients (HOG) features, and accelerated KAZE (AKAZE) descriptors to describe image features as visual landmarks without removing human regions as dynamic objects. The experimental obtained results revealed that recognition accuracies (RAs) for CWDs and CCWDs, were, respectively 70.76% for 26 categories and 72.24% for 25 categories. |
|
|
Generalized Extreme Value Trimmed Filter for Random Impulse Noise Suppression in Color image |
|
Sakon Chankhachon, Sathit Intajag(Prince of Songkla University, Thailand) |
| Noise suppression is the first prior task in a machine vision and human perception. In this paper, a novel method to remove high volumes of impulse noise is proposed. Our filter has designed based on the concept of a frequency
data distribution that is not always symmetric. The filter employs a Generalized Extreme Value (GEV) distribution for
fitting pixel values in each sliding windows. From the experimental results, the proposed algorithm provided good performance for removing high impulse noise and outperformed when compared with the stateof-the-art methods.
|
| |