• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.3
• /
• pp.229-235
• /
• 2011

To make a robust object tracking and identifying system for an intelligent robot and/or home system, heterogeneous sensor fusion between visible ray system and infrared ray system is proposed. The proposed system separates the object by combining the ROI (Region of Interest) estimated from two different images based on a heterogeneous sensor that consolidates the ordinary CCD camera and the IR (Infrared) camera. Human's body and face are detected in both images by using different algorithms, such as histogram, optical-flow, skin-color model and Haar model. Also the pose of human body is estimated from the result of body detection in IR image by using PCA algorithm along with AdaBoost algorithm. Then, the results from each detection algorithm are fused to extract the best detection result. To verify the heterogeneous sensor fusion system, few experiments were done in various environments. From the experimental results, the system seems to have good tracking and identification performance regardless of the environmental changes. The application area of the proposed system is not limited to robot or home system but the surveillance system and military system.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1109-1116
• /
• 2020

The matching score evaluating human copying ability can be a good measure to check children's developmental stages, or sports movements like golf swing and dance, etc. It also can be used as HCI for AR, VR applications. This paper presents a method to evaluate the motion similarity between demonstrator who initiates movement and participant who follows the demonstrator action. We present a quantification method of the similarity which utilizes Euclidean L2 distance of Openpose keypoins vector similarity. The proposed method adapts DTW, thus can flexibly cope with the time delayed motions.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.11 s.188
• /
• pp.58-67
• /
• 2006

Due to the variety of signal processing and complicated mathematical analysis, it is not easy to accomplish 3D bin-picking with non-contact sensor. To solve this difficulties the reliable signal processing algorithm and a good sensing device has been recommended. In this research, 3D laser scanner and CCD camera is applied as a sensing device respectively. With these sensor we develop a two-step bin-picking method and reliable algorithm for the recognition of 3D bin object. In the proposed bin-picking, the problem is reduced to 2D intial recognition with CCD camera at first, and then 3D pose detection with a laser scanner. To get a good movement in the robot base frame, the hand eye calibration between robot's end effector and sensing device should be also carried out. In this paper, we examine auto-calibration technique in the sensor calibration step. A new thinning algorithm and constrained hough transform is also studied for the robustness in the real environment usage. From the experimental results, we could see the robust bin-picking operation under the non-aligned 3D hole object.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.67-76
• /
• 2008

Reliable face recognition under various illumination environments is essential for successful commercialization. Feature-based face recognition relies on a good choice of feature vectors. Gabor feature vectors are known to be more robust to variations of pose and illumination than any other feature vectors so that they are popularly adopted for face recognition. However, they are not completely independent of illuminations. In this paper, we propose an illumination-robust face recognition method based on the Gabor feature vector illumination PCA model. We first construct the Gabor feature vector illumination PCA model where Gator feature vector space is rendered to be decomposed into two orthogonal illumination subspace and face identity subspace. Since the Gabor feature vectors obtained by projection into the face identity subspace are separated from illumination, the face recognition utilizing them becomes more robust to illumination. Through experiments, it is shown that the proposed face recognition based on Gabor feature vector illumination PCA model performs more reliably under various illumination and Pose environments.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.355-362
• /
• 2010

Face tracking is to estimate the motion of a non-rigid face together with a rigid head in 3D, and plays important roles in higher levels such as face/facial expression/emotion recognition. In this paper, we propose an AAM-based face tracking algorithm. AAM has been widely used to segment and track deformable objects, but there are still many difficulties. Particularly, it often tends to diverge or converge into local minima when a target object is self-occluded, partially or completely occluded. To address this problem, we utilize the scale invariant feature transform (SIFT). SIFT is an effective method for self and partial occlusion because it is able to find correspondence between feature points under partial loss. And it enables an AAM to continue to track without re-initialization in complete occlusions thanks to the good performance of global matching. We also register and use the SIFT features extracted from multi-view face images during tracking to effectively track a face across large pose changes. Our proposed algorithm is validated by comparing other algorithms under the above 3 kinds of occlusions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.116-122
• /
• 2010

This paper proposes a method for classifying targets robust to geometric transformations of targets such as rotation, scale change, translation, and pose change. Targets which have rotation, scale change, and shift is firstly classified based on CM(Confidence Map) which is generated by similarity, scale ratio, and range of orientation for SIFT(Scale-Invariant Feature Transform) feature vectors. On the other hand, DB(DataBase) which is acquired in various angles is used to deal with pose variation of targets. Range of the angle is determined by comparing and analyzing the execution time and performance for sampling intervals. We experiment on various images which is geometrically changed to evaluate performance of proposed target classification method. Experimental results show that the proposed algorithm has a good classification performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.762-766
• /
• 2003

In this paper, we present a new approach to solve the problem of estimating the camera 3-D location and orientation from a matched set of 3-D model and 2-D image features. An iterative least-square method is used to solve both rotation and translation simultaneously. Because conventional methods that solved for rotation first and then translation do not provide good solutions, we derive an error equation using roll-pitch-yaw angle to present the rotation matrix. To minimize the error equation, Levenberg-Marquardt algorithm is introduced with uniform sampling strategy of rotation space to avoid stuck in local minimum. Experimental results using real images are presented.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.27-29
• /
• 2004

This paper presents a sensor model design based on Monte Carlo Localization method. First, we define the measurement error of each sample using a map matching method by 2-D laser scanners and a pre-constructed grid-map of the environment. Second, samples are assigned probabilities due to matching errors from the gaussian probability density function considered of the sample's convergence. Simulation using real environment data shows good localization results by the designed sensor model.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.3
• /
• pp.83-91
• /
• 2000

During static walking of a quadruped walking robot, stability of the robot depends on whether the projection of the mass center is located within the supporting area that is varying with leg motion and formed by standing legs. In this paper, force margin instead of the mass center was used to determine stability and body-tilting method was used to enhance it. On-line control of body tilting was realized with simple reaction feedback based on force margin of the static walking model of the robot instead of complicated calculation. Model reference on-line control where the model searches stable pose for predefined force margin also gave good walking performance.