Video Object Segmentation using Supervoxel-Based Gerrymandering
Pixels operate locally. Superpixels have some potential to collect information across many pixels; supervoxels have more potential by implicitly operating across time. In this paper, we explore this well established notion thoroughly analyzing how supervoxels can be used in place of and in conjunction with other means of aggregating information across space-time. Focusing on the problem of strictly unsupervised video object segmentation, we devise a method called supervoxel gerrymandering that links masks of foregroundness and backgroundness via local and non-local consensus measures. We pose and answer a series of critical questions about the ability of supervoxels to adequately sway local voting; the questions regard type and scale of supervoxels as well as local versus non-local consensus, and the questions are posed in a general way so as to impact the broader knowledge of the use of supervoxels in video understanding. We work with the DAVIS dataset and find that our analysis yields an unsupervised method that outperforms all other known unsupervised methods and even many supervised ones.
Code (1)
Tasks
ObjectSemantic SegmentationSuperpixelsUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationVideo UnderstandingSimilar Papers 제목 키워드 기반
A Study of Actor and Action Semantic Retention in Video Supervoxel Segmentation
Existing methods in the semantic computer vision community seem unable to deal with the explosion and richness of modern, open-source and social video content. Although sophisticated methods such as object detection or b…
object-detectionObject DetectionSegmentationLIBSVX: A Supervoxel Library and Benchmark for Early Video Processing
Supervoxel segmentation has strong potential to be incorporated into early video analysis as superpixel segmentation has in image analysis. However, there are many plausible supervoxel methods and little understanding as…
Boundary DetectionSegmentationSuperpixelsMulticlass Semantic Video Segmentation With Object-Level Active Inference
We address the problem of integrating object reasoning with supervoxel labeling in multiclass semantic video segmentation. To this end, we first propose an object-augmented dense CRF in spatio-temporal domain, which capt…
ObjectSegmentationSemantic SegmentationVideo Segmentation+1A Coarse-To-Fine Framework For Video Object Segmentation
In this study, we develop an unsupervised coarse-to-fine video analysis framework and prototype system to extract a salient object in a video sequence. This framework starts from tracking grid-sampled points along tempor…
ObjectSegmentationSemantic SegmentationVideo Object Segmentation+1Saliency-guided Adaptive Seeding for Supervoxel Segmentation
We propose a new saliency-guided method for generating supervoxels in 3D space. Rather than using an evenly distributed spatial seeding procedure, our method uses visual saliency to guide the process of supervoxel genera…
Segmentation