• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.542-551
• /
• 2005

A new distance measurement method with the use of a single camera and a rotating mirror is presented. A camera in front of a rotating mirror acquires a sequence of reflected images, from which distance information is extracted. The distance measurement is based on the idea that the corresponding pixel of an object point at a longer distance moves at a higher speed in a sequence of images in this type of system setting. Distance measurement based on such pixel movement is investigated. Like many other image-based techniques, this presented technique requires matching corresponding points in two images. To alleviate such difficulty, two kinds of techniques of image tracking through the sequence of images and the utilization of multiple sets of image frames are described. Precision improvement is possible and is one attractive merit. The presented approach with a rotating mirror is especially suitable for such multiple measurements. The imprecision caused by the physical limit could be improved through making several measurements and taking an average. In this paper, mathematics necessary for implementing the technique is derived and presented. Also, the error sensitivities of related parameters are analyzed. Experimental results using the real camera-mirror setup are reported.

• The Journal of Korea Robotics Society
• /
• v.3 no.4
• /
• pp.263-269
• /
• 2008

Visual odometry is a popular approach to estimating robot motion using a monocular or stereo camera. This paper proposes a novel visual odometry scheme using a stereo camera for robust estimation of a 6 DOF motion in the dynamic environment. The false results of feature matching and the uncertainty of depth information provided by the camera can generate the outliers which deteriorate the estimation. The outliers are removed by analyzing the magnitude histogram of the motion vector of the corresponding features and the RANSAC algorithm. The features extracted from a dynamic object such as a human also makes the motion estimation inaccurate. To eliminate the effect of a dynamic object, several candidates of dynamic objects are generated by clustering the 3D position of features and each candidate is checked based on the standard deviation of features on whether it is a real dynamic object or not. The accuracy and practicality of the proposed scheme are verified by several experiments and comparisons with both IMU and wheel-based odometry. It is shown that the proposed scheme works well when wheel slip occurs or dynamic objects exist.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.10
• /
• pp.1005-1013
• /
• 2008

This paper describes a new sensor system for 3D range measurement using the structured infrared light. Environment and obstacle sensing is the key issue for mobile robot localization and navigation. Laser scanners and infrared scanners cover $180^{\circ}$ and are accurate but too expensive. Those sensors use rotating light beams so that the range measurements are constrained on a plane. 3D measurements are much more useful in many ways for obstacle detection, map building and localization. Stereo vision is very common way of getting the depth information of 3D environment. However, it requires that the correspondence should be clearly identified and it also heavily depends on the light condition of the environment. Instead of using stereo camera, monocular camera and the projected infrared light are used in order to reduce the effects of the ambient light while getting 3D depth map. Modeling of the projected light pattern enabled precise estimation of the range. Identification of the cells from the pattern is the key issue in the proposed method. Several methods of correctly identifying the cells are discussed and verified with experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.610-630
• /
• 2020

A large number of people suffered from traffic accidents each year, so people pay more attention to traffic safety. However, the traditional methods use laser sensors to calculate the vehicle distance at a very high cost. In this paper, we propose a method based on deep learning to calculate the vehicle distance with a monocular camera. Our method is inexpensive and quite convenient to deploy on the mobile platforms. This paper makes two contributions. First, based on Light-Head RCNN, we propose a new vehicle detection framework called Light-Car Detection which can be used on the mobile platforms. Second, the planar homography of projective geometry is used to calculate the distance between the camera and the vehicles ahead. The results show that our detection system achieves 13FPS detection speed and 60.0% mAP on the Adreno 530 GPU of Samsung Galaxy S7, while only requires 7.1MB of storage space. Compared with the methods existed, the proposed method achieves a better performance.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.2
• /
• pp.214-224
• /
• 2016

This paper proposes an algorithm to effectively detect the traffic lights and recognize the traffic signals using a monocular camera mounted on the front windshield glass of a vehicle in day time. The algorithm consists of three main parts. The first part is to generate the candidates of a traffic light. After conversion of RGB color model into HSI and YCbCr color spaces, the regions considered as a traffic light are detected. For these regions, edge processing is applied to extract the borders of the traffic light. The second part is to divide the candidates into traffic lights and non-traffic lights using Haar-like features and Adaboost algorithm. The third part is to recognize the signals of the traffic light using a template matching. Experimental results show that the proposed algorithm successfully detects the traffic lights and recognizes the traffic signals in real time in a variety of environments.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.379-381
• /
• 2008

본 논문에서는 가정용 비디오 게임에 사용 가능한 고속의 저가형 모션캡쳐, 시스템에 사용되는 전 방향 특성을 갖는 IR 능동 마커의 개발을 목표로 하고 있다. 현재 영화나 게임에서 모션캡쳐를 응용한 시스템 및 컨텐츠들이 많이 선보기고 있으며, 인기를 모으고 있는 추세이다. 이러한 흐름에 맞추어 우리는 이미 저가이면서 속도가 빠른 PSD(Position Sensitive Detector) 센서를 이용만 스테레오 비젼 기반의 PSD 모션캡쳐 시스템(Stereo vision based PSD motion capture system)과 광량 보정 기반의 단일 PSD 모션캡쳐 시스템(Intensity Calibration based single PSD motion capture system) 그리고 일정간격의 두 능동마커 기반의 단안 PSD 모션캡쳐 시스템(Two active markers at fixed distance based single PSD motion capture system)등을 소개한 바 있다. 본 논문에서 제안하는 전방향 특성을 갖는 IR 능동 마커는 일정간격의 두 능동마커 기반의 단안 PSD 모션캡쳐 시스템에 적용하여 보다 정밀한 3차원 좌표 측정을 할 수 있도록 한다. 이를 위해 본 논문에서는 동일 특성을 갖는 마커를 제작하고 평가하여 일정간격의 두 능동마커 기반의 단안 PSD 모션캡쳐 시스템에 적합한 마커의 제작 방법을 제안하였다.

• Journal of Advanced Navigation Technology
• /
• v.15 no.5
• /
• pp.696-704
• /
• 2011

In this paper, we propose a mobile robot navigation algorithm using data fusion of a monocular camera and ultrasonic sensors. Threshold values for binary image processing are generated by a fuzzy inference method using image data and data of ultrasonic sensors. Threshold value variations improve obstacle detection for mobile robot to move to the goal under poor illumination environments. Obstacles detected by data fusion of camera and ultrasonic sensors are expressed on the grid map and avoided using the circular planning algorithm. The performance of the proposed method is evaluated by experiments on the Pioneer 2-DX mobile robot in the indoor room with poor lights and a narrow corridor.

• 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.