http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Optical Flow Estimation and Error Analysis in Projective Space
Teruo Yamaguchi,Hiroyasu Shinbori 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10
A method of estimating optical flow by introducing a projective space of two-dimensional velocity is proposed. This approach make it possible to analyze measurement error in both spatial- and temporal-differential coefficients of image in a unified manner. In this projective space, velocity estimation can be formulated based on singular value decomposition. It is proved that under Gaussian noise condition, this method provides similar solution as expected in case of noise-free environment. It was shown from simulation and experiments that estimate error in velocity can be greatly reduced by the proposed algorithm.
Real-time optical flow measurement based on parallel processing with multicore computer
Mao Shimokawa,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10
In this paper we propose an optical flow estimation method based on parallel processing with multicore computer. The multichannel integration method refers to the method of measuring more accurate velocity field, but it takes a lot of processing time for the measurement. We divide the procedure of velocity field calculation into piplined stages, and execute them in parallel with a multicore computer. This method reduces the calculating time, and enables more high speed optical flow estimation. Experimental results show that velocity field can be measured faster than single-core processing.
Yuta Eto,Teruo Yamaguchi,Hiroshi Harada,Takeshi Tsusue 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
In this paper we estimate optical flow by using spatiotemporal differentiation scheme based on compensation method. Conventional spatiotemporal differentiation scheme enables us to calculate velocity distribution rapidly, but error in the approximation of derivative coefficients increases as the displacement of the moving pattern between the successive frames becomes large. To expand the range of measurable velocity of spatiotemporal differentiation sheme, we introduced the compensation method. In this research, we have realized how to determine the compensation velocity using multiple resolution images. We applied this method to images captured by an in-vehicle camera in order to calculate velocity distribution in situation where objects of various velocities exist and to locate traffic obstacles.
Implementation of Optical Flow Measurement System with an Embedded Processor
Yukihiro Sugiki,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
Optical flow estimation is one of the measuring method of object motion. It is important to prove that optical flow measurement system can perform in small scale computer to use as visual sensor. In this research, processing speed of optical flow measurement system with a single board computer Raspberry Pi was evaluated. Calclation time of optical flow estimation program based on spatio-temporal differentiation method with eigenvalue decomposition was compared with those using built-in optical flow function in OpenCV library (Lucas-Kanade method and Horn-Schunck method). As a result, the program was about the same processing speed as HS method, and took about six times as long as LK method. It is also shown when an object moves at a velocity of about 10 pixels per frame or more, output results apt to show wrong velocity vectors. Processing speed is to be improved by selecting optimum pixels required for velocity estimation. It will be necessary to compensate for velocity so that it is able to estimate optical flow at a high speed.
Parallel optical flow estimation by dividing image in section
Yusuke Miyajima,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
Spatio-temporal differentiation method is one of the most effective methods of determining the velocity of moving objects. However, the optical flow estimate takes long time so that real-time object tracking is difficult to realize. In this study, we evaluated consuming time of the optical flow estimation when calculating in parallel. The method of parallelization includes dividing input image into several region and assigning each region into each multi-core. Because spatio-temporal differentiation method is composed of a local calculation, it is compatible with the parallelization method of dividing image into section. We can use the commercial multi-core processors to accelerate the optical flow estimation. It was found feasible to accelerate the optical flow estimation by the method. Experimental result shows that the most suitable acceleration can be achieved when dividing calculation region into parts of the same number of the cores.
Optical flow estimation using compensation method
Yoshitaka Nishizaka,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
In this paper we propose an optical flow estimation method based on compensating method by using spa-tiotemporal differentiation. Technique using spatio temporal differentiation is one of optical flow calculation method. This method enables us to calculate velocity distribution rapidly, but the error in the approximation of derivative coefficients in creases as the displacement of the moving pattern between the successive frames becomes large. We suggest a new system which expands the range of measurable velocity based on using spatiotemporal differentiation.
Extraction of Moving Object Based on Fast Optical Flow Estimation
Jun Hirai,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
In this paper, we propose a system to extract the moving object by the segmentation based on fast optical flow estimation. This optical flow estimationis based on multichannel integration for speeding up and can estimate more accurate optical flow fast. Moving object can be extracted by the segmentation using the obtained optical flow. Experimental results show that the segmentation based on the fast optical flow estimate can extract the moving region.
Self evaluation for gait based on optical flow calculation
Ryo Akagi,Teruo Yamaguchi 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
Walking is an activity that can be practiced by almost all people, and it has the effect of preventing diseases and unhealthy conditions that are increasing in many people. If we can walk efficiently, it is expect to reduce the burden on the body and improve our motor skills. At present, it is common for experienced and knowledgeable instructors to evaluate gait in walking, but it is not certain that the evaluation is always objective, and it is time-consuming and costly. Therefore, we expected that if we can analyze the ideal gait and compare our own gait with the ideal gait. we would be able to evaluate how our own gait is close to the ideal gait in a simple way. In this study, to analyze the ideal gait, we measure the head velocity and acceleration of the ideal gait captured by a high-speed camera and compared it with the non-ideal gait using optical flow measurement.
Measurement of Optical Flow in Real-Time
Jun Hirai,Teruo Yamaguchi,Hiroshi Harada 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
In this paper, we propose a system which calculates optical flow in real-time based on multichannel integration using different filters. The multichannel integration refers to the method for calculating more accurate velocity field, but it takes much time to calculate. This calculation time can be shortened by the ingenuity for speeding up including concurrent image capturing and selection of neighboring pixels. Experimental results show that velocity field can be estimated much faster than the conventional method.