• Aerospace Engineering and Technology
• /
• v.11 no.2
• /
• pp.140-148
• /
• 2012

For autonomous navigation, map, pose tracking, and finding the shortest path are required. Because there is no GPS signal in indoor environment, the current position should be recognized in the 3D map by using image processing or something. In this paper, we explain 3D map creation technology by using depth camera like Kinect and pose tracking in 3D map by using 2D image taking from camera. In addition, the mechanism of avoiding obstacles is discussed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.839-846
• /
• 2016

Bin picking is a task of picking a small object from a bin. For accurate bin picking, the 3D pose information, position, and orientation of a small object is required because the object is mixed with other objects of the same type in the bin. Using this 3D pose information, a robotic gripper can pick an object using exact distance and orientation measurements. In this paper, we propose a 3D vision technique for accurate measurement of 3D position and orientation of small objects, on which a paper label is stuck to the surface. We use a maximally stable extremal regions (MSERs) algorithm to detect the label areas in a left bin image acquired from a stereo camera. In each label area, image features are detected and their correlation with a right image is determined by a stereo vision technique. Then, the 3D position and orientation of the objects are measured accurately using a transformation from the camera coordinate system to the new label coordinate system. For stable measurement during a bin picking task, the pose information is filtered by averaging at fixed time intervals. Our experimental results indicate that the proposed technique yields pose accuracy between 0.4~0.5mm in positional measurements and $0.2-0.6^{\circ}$ in angle measurements.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.328-335
• /
• 2022

With the advance of robot capabilities and functionalities, construction robots assisting construction workers have been increasingly deployed on construction sites to improve safety, efficiency and productivity. For close-proximity human-robot collaboration in construction sites, robots need to be aware of the context, especially construction worker's behavior, in real-time to avoid collision with workers. To recognize human behavior, most previous studies obtained 3D human poses using a single camera or an RGB-depth (RGB-D) camera. However, single-camera detection has limitations such as occlusions, detection failure, and sensor malfunction, and an RGB-D camera may suffer from interference from lighting conditions and surface material. To address these issues, this study proposes a novel method of 3D human pose estimation by extracting 2D location of each joint from multiple images captured at the same time from different viewpoints, fusing each joint's 2D locations, and estimating the 3D joint location. For higher accuracy, the probabilistic representation is used to extract the 2D location of the joints, considering each joint location extracted from images as a noisy partial observation. Then, this study estimates the 3D human pose by fusing the probabilistic 2D joint locations to maximize the likelihood. The proposed method was evaluated in both simulation and laboratory settings, and the results demonstrated the accuracy of estimation and the feasibility in practice. This study contributes to ensuring human safety in close-proximity human-robot collaboration by providing a novel method of 3D human pose estimation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.303-310
• /
• 2023

A single vision system limits the ability to accurately understand the spatial constraints and interactions between robots and dynamic workers caused by gantry robots and collaborative robots during production manufacturing. In this paper, we propose a 3D pose registration method for dynamic workers based on a multi-domain vision system for safety monitoring in manufacturing environments. This method uses OpenPose, a deep learning-based posture estimation model, to estimate the worker's dynamic two-dimensional posture in real-time and reconstruct it into three-dimensional coordinates. The 3D coordinates of the reconstructed multi-domain vision system were aligned using the ICP algorithm and then registered to a single 3D coordinate system. The proposed method showed effective performance in a manufacturing process environment with an average registration error of 0.0664 m and an average frame rate of 14.597 per second.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2009.06a
• /
• pp.663-664
• /
• 2009

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.9-17
• /
• 2024

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• Annual Conference of KIPS
• /
• 2014.04a
• /
• pp.904-907
• /
• 2014

In this work we present a robust and fast approach to estimate 3D vehicle pose that can provide results under a specific traffic surveillance conditions. Such limitations are expressed by single fixed CCTV camera that is located relatively high above the ground, its pitch axes is parallel to the reference plane and the camera focus assumed to be known. The benefit of our framework that it does not require prior training, camera calibration and does not heavily rely on 3D model shape as most common technics do. Also it deals with a bad shape condition of the objects as we focused on low resolution surveillance scenes. Pose estimation task is presented as PnP problem to solve it we use well known "POSIT" algorithm [1]. In order to use this algorithm at least 4 non coplanar point's correspondence is required. To find such we propose a set of techniques based on model and scene geometry. Our framework can be applied in real time video sequence. Results for estimated vehicle pose are shown in real image scene.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.337-345
• /
• 2023

In this study, we formulated a method that evaluates Taekwondo Poomsae performance using a series of choreographed training movements. Despite recent achievements in 3D human pose estimation (HPE) performance, the analysis of human actions remains challenging. In particular, Taekwondo Poomsae action analysis is challenging owing to the absence of time synchronization data and necessity to compare postures, rather than directly relying on joint locations owing to differences in human shapes. To address these challenges, we first decomposed human joint representation into joint rotation (posture) and limb length (body shape), then synchronized a comparison between test and reference pose sequences using DTW (dynamic time warping), and finally compared pose angles for each joint. Experimental results demonstrate that our method successfully synchronizes test action sequences with the reference sequence and reflects a considerable gap in performance between practitioners and professionals. Thus, our method can detect incorrect poses and help practitioners improve accuracy, balance, and speed of movement.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.1
• /
• pp.47-52
• /
• 2010

In this paper, we introduce a new approach for real-time 3D face pose discrimination based on active IR illumination from a monocular view of the camera. Under the IR illumination, the pupils appear bright. We develop algorithms for efficient and robust detection and tracking pupils in real time. Based on the geometric distortions of pupils under different face orientations, an eigen eye feature space is built based on training data that captures the relationship between 3D face orientation and the geometric features of the pupils. The 3D face pose for an input query image is subsequently classified using the eigen eye feature space. From the experiment, we obtained the range of results of discrimination from the subjects which close to the camera are from 94,67%, minimum from 100%, maximum.