Since the publication of the comparative study done by Barron et al. on optical flow estimation, a race was started to achieve more and more accurate and dense velocity fields. For comparison a few synthetic image sequences has been used. The most complex of these is the Yosemite Flying sequence that contains both a diverging field, occlusion and multiple motions at the horizon. About 10 years ago it was suggested to remove the sky region because the correct flow used in earlier work was not found to be the real ground truth for this region. In this paper we present a study of the sky region in this test sequence, and discuss its usefulness for evaluation of optical flow estimation.

/pdf/a-study-of-the-yosemite-sequence-used-as-a-test-sequence-for-40eg4kkdkv.pdf

A study of the yosemite sequence used as a test sequence for estimation of optical flow

Multi-resolution optical flow tracking algorithm decomposes the object displacement in the wavelet pyramid, then sparse optical flow based on LK (Lucas-Kanade) algorithm matches the object feature in all the level of the wavelet pyramid step by step. Steadily tracking rapid motion objects is achieved. As to the feature of motion vehicles, multi-scale Harris corner detection based on wavelet is proposed. Traditional Harris corner detection about omitting corner point and asymmetrical array is improved. It is suitable to extract motion vehicle feature in complicated traffic scene. With the experiment, it can be verified that the corner point is always steady and reliable when the vehicle is turning and moving, and the camera is zooming in and out. The tracking algorithm also can accurately match the feature points with the high real-time performance.

Multi-resolution optical flow tracking algorithm based on multi-scale Harris corner points feature

Multi-resolution optical flow tracking algorithm based on wavelet pyramid is proposed by analyzing the limitations of sparse optical flow based on LK (Lucas-Kanade) algorithm. The problem that LK algorithm cannot steadily track rapid motion objects by LK algorithm is solved. According to the feature of motion vehicles, multi-scale Harris corner detection based on wavelet is proposed. The problem of limitation of Traditional Harris corner detection about omitting corner point and asymmetrical array is solved. It is suitable to extract motion vehicle feature in complicated traffic scene. Experimentation result shows that the corner point is always steady and reliable when the vehicle is rotating and moving, and the camera is zooming in and out. The tracking algorithm also can accurately match the feature points with the high real-time performance.

Motion vehicle tracking based on multi-resolution optical flow and multi-scale Harris corner detection

Optical flow-based tracking methods offer the promise of precise, accurate, and reliable analysis of motion, but they
suffer from several challenges such as elimination of background movement, estimation of flow velocity, and optimal
feature selection. Wavelet approximations can offer similar benefits and retain spatial information at coarser scales,
while optical flow estimation increases with the reduction of finer details of moving objects. Optical flow methods often
suffer from significant computational overload. In this study, we have investigated the necessary processing steps to
increase detection and estimation accuracy, while effectively reducing computation time through the reduction of the
image frame size. We have implemented an object tracking algorithm using the optical flow calculated from a phase
change between representative coarse wavelet coefficients in subsequent image frames. We have also compared phasebased
optical flow with two versions of intensity-based optical flow to determine which method produces superior
results under specific operational conditions. The investigation demonstrates the feasibility of using phase-based optical
flow with wavelet approximations for object detection and tracking of low resolution aerial vehicles. We also
demonstrate that this method can work in tandem with feature-based tracking methods to increase tracking accuracy.

Optical flow object detection, motion estimation, and tracking on moving vehicles using wavelet decompositions

In video surveillance, there are a variety of random disturbances on moving target detection, such as trees sway, camera shake. In order to eliminate these disturbances, this paper presents a novel moving object detection algorithm based on the properties of corner points. Firstly, this paper uses Harris algorithm to detect corner on the video image, and then proposes a novel indicator, Inter-frame Regional Corners Difference, to select the candidate grids of foreground. In this way, the static and slight shaking background is recognized. Secondly, this paper makes use of Horn and Schunck's optical flow algorithm to build the optical flow field of grids that are the candidates of foreground, and extracts the moving target by some velocity constraint of the horizontal and vertical direction. In virtue of the different dynamic properties of background and moving target, the dynamic background can be eliminated. The experimental results show that our algorithm can accurately extract moving target and can meet the needs of real-time processing with strong anti-jamming.

Moving target detection based on the properties of corners

In this paper, a new algorithm for accurate optical flow estimation using discrete wavelet approximation is proposed. The proposed method takes advantages of the nature of wavelet theory, which can efficiently and accurately represent \"things\", to model optical flow vectors and image related functions. Each flow vector and image function are represented by linear combinations of wavelet basis functions. From such wavelet-based approximation, the leading coefficients of these basis functions carry the global information of the approximated \"things\". The proposed method can successfully convert the problem of minimizing a constraint function into that of solving a linear system of a quadratic and convex function of wavelet coefficients. Once all the corresponding coefficients are decided, the flow vectors can be determined accordingly. Experiments conducted on both synthetic and real image sequences show that our approach outperformed the existing methods in terms of accuracy.

J. C. Lin

Papers

Wavelet-based Optical Flow Estimation