• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.119-126
• /
• 2003

The problem of tracking moving objects in a video stream is discussed in this pa-per. We discussed the popular technique of optical flow for moving object detection. Optical flow finds the velocity vectors at each pixel in the entire video scene. However, optical flow based methods require complex computations and are sensitive to noise. In this paper, we proposed a new method based on the Hough transform and on voting accumulation for improving the accuracy and reducing the computation time. Further, we applied the Boo-lean based edge detector for edge detection. Edge detection and segmentation are used to extract the moving objects in the image sequences and reduce the computation time of the CHT. The Boolean based edge detector provides accurate and very thin edges. The difference of the two edge maps with thin edges gives better localization of moving objects. The simulation results show that the proposed method improves the accuracy of finding the optical flow vectors and more accurately extracts moving objects' information. The process of edge detection and segmentation accurately find the location and areas of the real moving objects, and hence extracting moving information is very easy and accurate. The Combinatorial Hough Transform and voting accumulation based optical flow measures optical flow vectors accurately. The direction of moving objects is also accurately measured.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.5
• /
• pp.277-285
• /
• 2016

Moving object detection system has been an emerging research field in various advanced driver assistance systems (ADAS) and surveillance system. In this paper, we propose two optical flow based moving object detection methods at dynamic scenes. Both proposed methods consist of three successive steps; pre-processing, foreground segmentation, and post-processing steps. Two proposed methods have the same pre-processing and post-processing steps, but different foreground segmentation step. Pre-processing calculates mainly optical flow map of which each pixel has the amplitude of motion vector. Dense optical flows are estimated by using Farneback technique, and the amplitude of the motion normalized into the range from 0 to 255 is assigned to each pixel of optical flow map. In the foreground segmentation step, moving object and background are classified by using the optical flow map. Here, we proposed two algorithms. One is Gaussian mixture model (GMM) based background subtraction, which is applied on optical map. Another is adaptive thresholding based foreground segmentation, which classifies each pixel into object and background by updating threshold value column by column. Through the simulations, we show that both optical flow based methods can achieve good enough object detection performances in dynamic scenes.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.517-521
• /
• 2008

Hand motion classification problem is considered as basis for sign or gesture recognition. We promote optical flow as main feature extracted from images sequences to simultaneously segment the motion's area by its magnitude and characterize the motion' s directions by its orientation. We manage the flow orientation histogram as motion descriptor. A motion is encoded by concatenating the flow orientation histogram from several frames. We utilize simple histogram matching to classify the motion sequences. Attempted experiments show the feasibility of our method for hand motion localization and classification.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.6
• /
• pp.663-673
• /
• 2007

This paper presents a new moving obstacle detection method using an optical flow in mobile robot with an omnidirectional camera. Because an omnidirectional camera consists of a nonlinear mirror and CCD camera, the optical flow pattern in omnidirectional image is different from the pattern in perspective camera. The geometry characteristic of an omnidirectional camera has influence on the optical flow in omnidirectional image. When a mobile robot with an omnidirectional camera moves, the optical flow is not only theoretically calculated in omnidirectional image, but also investigated in omnidirectional and panoramic images. In this paper, the panoramic image is generalized from an omnidirectional image using the geometry of an omnidirectional camera. In particular, Focus of expansion (FOE) and focus of contraction (FOC) vectors are defined from the estimated optical flow in omnidirectional and panoramic images. FOE and FOC vectors are used as reference vectors for the relative evaluation of optical flow. The moving obstacle is turned out through the relative evaluation of optical flows. The proposed algorithm is tested in four motions of a mobile robot including straight forward, left turn, right turn and rotation. The effectiveness of the proposed method is shown by the experimental results.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.1 s.33
• /
• pp.223-229
• /
• 2005

In this paper a coarse-to-fine optical flow detection method is proposed. Provided that optical flow gives reliable approximation to two-dimensional image motion, it can be used to recover the three-dimensional motion, but usually to set the reliable optical flows are difficult. The proposed algorithm uses Horn's algorithm for detecting initial optical flow, then Thin Plate Spline is introduced to warp a image frame of the initial optical flow to the next image frame. The optical flow for the warped image frame is again used iteratively until the mean square error between two image sequence frames is lowered. The proposed method is experimented for the real moving picture image sequence. The proposed algorithm gives dense optical flow vectors.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.53-54
• /
• 2018

This paper introduces an approach to detect motion areas of stationary objects when the camera slightly moves in the scene by computing optical flow. The flow field is computed by two pyramidal architectures of 5 levels which are built by down-sampling the size of the images by half at each level. Two pyramids of images are built and then optical flow is computed at each level. A warping process combines the information and generates a final flow field after applying edge smoothness and outliers reduction steps. Moreover, we convert the flow vectors in order of magnitude and angle to a color map using a pseudo-color palette. Experimental results in the Middlebury optical flow dataset demonstrate the effectiveness of our method compared to other approaches.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.51-58
• /
• 2020

Many types of optical plastic films are essential in optoelectronics display unit fabrication and it is important to develop high precision laser cutting methods of optical films with extremely low level of film surface contamination by fume particles. This study investigates the effects of suction and blowing air motions with air flow misalignment in removing fume particles from laser cut line by employing random particle trajectory simulation and probabilistic particle generation model. The computational results show fume particle dispersion behaviors on optical film under suction and blowing air flow conditions. It is found that suction air flow motion is more advantageous to blowing air motion in reducing film surface contamination outside designated target margin from laser cut line. While air flow misalignment adversely affects particle dispersion in blowing air flows, its effects become much more complicated in suction air flows by showing different particle dispersion patterns around laser cut line. It is required to have more careful air flow alignment in fume particle removal under suction air flow conditions.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.353-355
• /
• 2010

Optical flow 는 컴퓨터 비전에서 기본적이고 중요한 연구 분야 중에 하나이며 지금까지 많은 알고리즘이 제안되었다. 그러나 여전히 Optical flow의 많은 기법들은 텍스처가 없는 영역들과 이미지의 경계부분에서 정확한 결과를 얻는 데 많은 어려움을 갖고 있으며 이러한 Optical flow 의 성능을 평가하기 위해서 지금까지는 Endpoint Error 와 Angular Error 등과 같은 방법을 사용하고 있다. 이 논문에서는 유명한 optical flow 기법들을 초기 모델부터 최근 기법까지 간략하게 설명함으로써 optical flow 기법들이 어떻게 진행되어 왔는지 살펴보고 특히 occlusion 영역과 경계부분에서의 성능을 평가하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.12b
• /
• pp.441-444
• /
• 2011

본 논문은 2D/3D 영상 처리에서 깊이지도 생성을 위한 Optical flow에서 레벨을 간소화하여 연산량을 감소시키고 객체의 고유벡터를 이용하여 영상의 잡음을 제거하는 연구이다. Optical flow는 움직임추정 알고리즘의 하나로 두 프레임간의 픽셀의 변화 벡터 값을 나타내며 블록 매칭과 같은 알고리즘에 비해 정확도가 높다. 그러나 기존의 Optical flow는 긴 연산 시간과 카메라의 이동이나 조명의 변화에 민감한 문제가 있다. 이를 해결하기 위해 연산 시간의 단축을 위한 레벨 간소화 과정을 거치고 영상에서 고유벡터를 갖는 영역에 한해 Optical flow를 적용하여 잡음을 제거하는 방법을 제안하였다. 제안한 방법으로 2차원 영상을 3차원 입체 영상으로 변환하였고 SSIM(Structural SIMilarity Index)으로 최종 생성된 영상의 오차율을 분석하였다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.48-56
• /
• 1995

This paper presents a method of implementing efficient optical flow estimation for dynamic scene analysis using the hierarchical Hopfield neural networks. Given the two consequent inages, Zhou and Chellappa suggested the Hopfield neural network for computing the optical flow. The major problem of this algorithm is that Zhou and Chellappa's network accompanies self-feedback term, which forces them to check the energy change every iteration and only to accept the case where the lower the energy level is guaranteed. This is not only undesirable but also inefficient in implementing the Hopfield network. The another problem is that this model cannot allow the exact computation of optical flow in the case that the disparities of the moving objects are large. This paper improves the Zhou and Chellapa's problems by modifying the structure of the network to satisfy the convergence condition of the Hopfield model and suggesting the hierarchical algorithm, which enables the computation of the optical flow using the hierarchical structure even in the presence of large disparities.