A rule-based method for object segmentation in video sequences

Date

1997-01-01

Author

Alatan, Abdullah Aydın
Onural, L

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

155
views

0
downloads

Object segmentation and tracking are problems within the scope of MPEG-4 and MPEG-7 standardization activities. A novel algorithm for both object segmentation and tracking is presented. The algorithm fuses motion, color, and accumulated previous segmentation data at 'region level', in contrast to conventional 'pixel level' approaches. The information fusion is achieved by a rule-based region processing unit which intelligently utilizes the motion information to locate the objects in the scene, the color information to extract the true boundaries, and the segmentation result of the previous frame for tracking the objects. The algorithm is generic in the sense that the modules prior to the rule-based region processor can independently be replaced by alternative units which can achieve the same tasks. In the proposed algorithm, while the recursive-shortests-spanning-tree (RSST) algorithm is used for segmentation purposes, hierarchical-block-matching (HBM) is utilized for estimating motion between frames. The simulation results are very promising for this novel object segmentation approach

Subject Keywords

Object segmentation, Video sequences, MPEG 4 Standard, MPEG 7 Standard, Standardization, Fuses, Layout, Color, Data mining, Tracking

URI

https://hdl.handle.net/11511/44388

DOI

https://doi.org/10.1109/icip.1997.638823

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Fine-grained object recognition and zero-shot learning in multispectral imagery Sumbul, Gencer; Cinbiş, Ramazan Gökberk; AKSOY, SELİM (2018-05-05) We present a method for fine-grained object recognition problem, that aims to recognize the type of an object among a large number of sub-categories, and zero-shot learning scenario on multispectral images. In order to establish a relation between seen classes and new unseen classes, a compatibility function between image features extracted from a convolutional neural network and auxiliary information of classes is learnt. Knowledge transfer for unseen classes is carried out by maximizing this function. Per...
Novel Optimization Models to Generalize Deep Metric Learning Gürbüz, Yeti Ziya; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-8-24) Deep metric learning (DML) aims to fit a parametric embedding function to data of semantic information (e.g. images) so that l2-distance between embedded samples is low whenever they share similar semantic entities. An embedding function of such behavior is attained by minimizing empirical expected pairwise loss that penalizes inter-/intra-class proximity violations in embedding space. Proxy-based methods which use a learnable embedding vector per class in their loss formulation are state-of-the-art. We fir...
An index structure for fuzzy databases Yazıcı, Adnan (1996-09-11) Fuzzy querying involves more complex processing than ordinary querying does. In addition, a larger number of tuples will possibly be selected by fuzzy conditions compared to the crisp ones. The current index structures are inefficient in representing and dealing with uncertain and fuzzy data. In this paper we extend one of the multi-dimensional data structures, namely Multi Lever Grid File (Whang and Krishnamurty, 1991) for an efficient access to both crisp and fuzzy data. In order to take advantage of the ...
Multiple Description Coding of 3D Dynamic Meshes Based on Temporal Subsampling Bici, M. Oguz; Akar, Gözde (2010-01-21) In this paper, we propose a Multiple Description Coding (MDC) method for reliable transmission of compressed time consistent 3D dynamic meshes. It trades off reconstruction quality for error resilience to provide the best expected reconstruction of 3D mesh sequence at the decoder side. The method is based on partitioning the mesh frames into two sets by temporal subsampling and encoding each set independently by a 3D dynamic mesh coder. The encoded independent bitstreams or so-called descriptions are transm...
A Methodology to develop process ontology from organizational guidelines written in natural language Gürbüz, Özge; Demirörs, Onur; Department of Information Systems (2017) Integrating ontologies with process modeling improves data representations and makes it easier to query, store and reuse processes at the semantics level. Therefore, in recent years, this topic has become increasingly popular. The studies in the literature have proposed methods for the integration process either to relate domain ontologies to process models or to transform process models to process ontologies. Another way to establish the integration between ontologies and process models is to develop proce...

Citation Formats

A. A. Alatan and L. Onural, “A rule-based method for object segmentation in video sequences,” 1997, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/44388.