Object-guided motion estimation

Prez-Ra, Juan-Manuel; Crivelli, Tomas; Prez, Patrick

doi:10.1016/j.cviu.2016.05.005

Cited by 3 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have experimented with three settings for warping of contour: using a smoothed optical flow masked as in [19], moving each node by averaging the motion of all landmarks connected to given node and robustly estimated similarity transformation with RANSAC from position of landmarks. Table 3 and Fig.…”

Section: Resultsmentioning

confidence: 99%

ROAM: A Rich Object Appearance Model with Application to Rotoscoping

Mikšík

Pérez-Rúa

Torr

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Figure 1: ROAM for video object segmentation. Designed to help rotoscoping, the proposed object appearance model allows the automatic delineation of a complex object in a shot, starting from an initial outline provided by the user. AbstractRotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given a first closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic segmentation with a closed curve or pixel-wise binary labelling.

show abstract

Section: Resultsmentioning

confidence: 99%

ROAM: A Rich Object Appearance Model with Application to Rotoscoping

Mikšík

Pérez-Rúa

Torr

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Meanwhile with motion estimation techniques, temporal information could be introduced to decrease the impact of occluded pixels in disparity maps. Similar to the full frame motion estimation method, Perez et al 13 proposed one object flow motion estimation method, which calculates the flow vectors for each pixel inside an object, which distinguishes different objects according to the motion amplitude. Zhang et al 14 proposed that temporal information, gathered from consecutive frames, had been proven to improve the accuracy of stereo matching, which also reflects the changes in occlusion region happened in the disparity discontinuity area.…”

Section: Related Workmentioning

confidence: 99%

Correspondence matching among stereo images with object flow and minimum spanning tree aggregation

Jing-lin

Liu

Nezan

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Stereoscopic correspondence matching is applied in many applications like robot navigation, automatic driving, virtual, and augmented reality by reconstructing the scene in three-dimensional environments. In the most real scenes, the moving objects attract more attentions than static objects and background. Thus, temporal information of consecutive frames like motion flow has been proven to improve the matching accuracy as weight prior. In this article, we propose a costaggregation method joining object flow and minimum spanning tree-based support region rather than aggregating on fixed size windows. However, directly combining object flow and minimum spanning tree filtering is not straightforward, due to the extremely high computing complexity. The proposed scheme implements nonlocal cost aggregation with object-based optical flow, which extends the idea of the minimum spanning tree and flow-based motion estimation to increase the matching accuracy. Temporal evidence of object flow is not only used in minimum spanning tree support region building but also incorporated with one hybrid edge prior to optimize the disparity estimation. The experimental results with synthetic stereo videos show that the proposed method outperforms other state-of-the-art stereo matching methods in most data sets. The whole stereo correspondence algorithm achieves competitive performance in terms of both accuracy and speed. We also illustrate the performance of the proposed method with the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) benchmark as one extensive comparison.

show abstract