Shape Training for Video Object Segmentation
نویسندگان
چکیده
Since most algorithms for automatic video segmentation cannot extract video objects in a picture frame accurately, we can take a user-assisted approach in generating VOPs of moving objects. In this paper, we propose a semiautomatic video segmentation algorithm using semantic information. In order to reduce effects of unwanted feature points due to the low-level image processing operations, we employ an active contour with B-spline curves. In addition, we define an external energy with the SUSAN feature detector whose computational complexity is lower than popular morphological filtering operation.
منابع مشابه
Segmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation (pre-print)
The Segmentation According to Natural Examples (SANE) algorithm learns to segment objects in static images from video training data. SANE uses background subtraction to find the segmentation of moving objects in videos. This provides object segmentation information for each video frame. The collection of frames and segmentations forms a training set that SANE uses to learn the image and shape p...
متن کاملLearning static object segmentation from motion segmentation
This thesis describes the SANE (Segmentation According to Natural Examples) algorithm for learning to segment objects in static images from video data. SANE uses background subtraction to find the segmentation of moving objects in videos. This provides object segmentation information for each video frame. The collection of frames and segmentations forms a training set that SANE uses to learn th...
متن کاملIntegrated Video Object Segmentation and Shape Coding
To enable content-based access and manipulation of video content, modern multimedia communications require per-object based access to video data. Two additional building blocks of video transmission systems needs to be defined, which enable access to video objects at the receiver end. These are video segmentation, which decomposes video frame into a set of layers, where each layer includes segm...
متن کاملA Lvq-based Temporal Tracking for Semi-automatic Video Object Segmentation
This paper presents a Learning Vector Quantization (LVQ)-based temporal tracking method for semi-automatic video object segmentation. A semantic video object is initialized using user assistance in a reference frame to give initial classification of video object and its background regions. The LVQ training approximates video object and background classification and use them for automatic segmen...
متن کاملCombining Self Training and Active Learning for Video Segmentation
This work addresses the problem of segmenting an object of interest out of a video. We show that video object segmentation can be naturally cast as a semi-supervised learning problem and be efficiently solved using harmonic functions. We propose an incremental self-training approach by iteratively labeling the least uncertain frame and updating similarity metrics. Our self-training video segmen...
متن کامل