Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow
نویسندگان
چکیده
Handling all together large displacements, motion details and occlusions remains an open issue for reliable computation of optical flow in a video sequence. We propose a two-step aggregation paradigm to address this problem. The idea is to supply local motion candidates at every pixel in a first step, and then combine them to determine the global optical flow field in a second step. We exploit local parametric estimations combined with patch correspondences and we experimentally demonstrate that they are sufficient to produce highly accurate motion candidates. The aggregation step is designed as the discrete optimization of a global regularized energy. The occlusion map is estimated jointly with the flow field throughout the two steps. We propose a generic exemplar-based approach for occlusion filling with motion vectors. We achieve state-of-the-art results in computer vision benchmarks, with particularly significant improvements in the case of large displacements and occlusions.
منابع مشابه
Microfluidic system for simultaneous optical measurement of platelet aggregation at multiple shear rates in whole blood.
Thrombosis is the pathological formation of platelet aggregates which occlude blood flow causing stroke and heart attack-the leading causes of death in developed nations. Instrumentation for diagnosing and exploring treatments for pathological platelet aggregation thus has the potential for major clinical impact. Most current thrombosis methods focus on single flow conditions, non-occlusive pla...
متن کاملThe Origin of Artificial Kinetic Spectroscopy and Its Application
Intentionally creating local blood flow cessation at different body sites initiates the time dependent optical response. Specifically, applying circumferential over systolic pressure at the finger base creates a very stable post-occlusion optical signal (POS). Geometrically independent features of light absorption and scattering of the blood are extracted from POS by evaluating the parametric s...
متن کاملExemplar-based Action Recognition in Video
Over recent years, a lot of progress has been made towards automatic annotation of video material, especially in the context of object and scene recognition. However, in comparison, action recognition is still in its infancy. Whereas originally silhouette-based approaches or approaches based on pose estimation have been studied mostly, good results have been reported recently using extensions o...
متن کاملHandling occlusion in optical flow algorithms for object tracking
In this paper, we study simple algorithms for tracking objects in a video sequence, based on the selection of landmark points representative of the moving objects in the first frame of the sequence to be analyzed. The movement of these points is estimated using a sparse optical-flow method. Methods of this kind are fast, but they are not very robust. Particularly, they are not able to handle th...
متن کاملDense Stereo Correspondence with Contrast Context Histogram, Segmentation-Based Two-Pass Aggregation and Occlusion Handling
In a local and perceptual organization framework, a novel stereo correspondence algorithm is proposed to provide dense and accurate disparity maps under point ambiguity. First, the initial matching technique is based on raw matching cost obtained from local descriptor with contrast context histogram and two-pass cost aggregation via segmentation-based adaptive support weight. Second, the dispar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Computer Vision and Image Understanding
دوره 145 شماره
صفحات -
تاریخ انتشار 2016