Spatiotemporal segmentation using genetic algorithms

نویسندگان

  • Eun Yi Kim
  • Sang Won Hwang
  • Se Hyun Park
  • Hang Joon Kim
چکیده

Segmentation is the process of identifying uniform regions based on certain conditions. Segmentation has been used for a long time in image analysis and computer vision for a variety of applications. In particular, there has been a growing interest in video sequence segmentation mainly due to the development of MPEG-4, which enables the content-based manipulation of multimedia data [1,2]. For this, the sequence must be "rst segmented into a set of meaningful objects [1,2]. However, since such objects are normally not characterized by a homogeneous intensity, color, or optical #ow, conventional segmentation algorithms using these features cannot produce meaningful partitions [1,2]. To overcome this problem, motion information has been used recently in many segmentation techniques, as one of the most important characteristics for identifying objects in a scene [1]. The methods that use motion can be divided into two main classes: joint motion estimation and segmentation, and spatiotemporal segmentation. The "rst approach estimates motion vectors at the pixel level and then clusters the pixels into regions of coherent motion, however, it has a major drawback: regions with coherent motion may contain multiple objects and need further segmentation for object extraction [1]. To overcome this drawback, the second approach uses information from both the spatial and temporal domain (i.e. color and motion), which produces a more meaningful segmentation [1,2]. This paper presents a new spatiotemporal segmentation of a video sequence. Each frame in a sequence is modeled using a Markov random "eld (MRF), which is e!ective in describing the spatial and temporal dependency of neighboring pixels and robust to degradation.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improving Brain Magnetic Resonance Image (MRI) Segmentation via a Novel Algorithm based on Genetic and Regional Growth

Background: Regarding the importance of right diagnosis in medical applications, various methods have been exploited for processing medical images solar. The method of segmentation is used to analyze anal to miscall structures in medical imaging.Objective: This study describes a new method for brain Magnetic Resonance Image (MRI) segmentation via a novel algorithm based on genetic and regiona...

متن کامل

Spatiotemporal Estimation of PM2.5 Concentration Using Remotely Sensed Data, Machine Learning, and Optimization Algorithms

PM 2.5 (particles <2.5 μm in aerodynamic diameter) can be measured by ground station data in urban areas, but the number of these stations and their geographical coverage is limited. Therefore, these data are not adequate for calculating concentrations of Pm2.5 over a large urban area. This study aims to use Aerosol Optical Depth (AOD) satellite images and meteorological data from 2014 to 2017 ...

متن کامل

Automatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI

Background: Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) provides functional information on the microcirculation in tissues by analyzing the enhancement kinetics which can be used as biomarkers for prostate lesions detection and characterization.Objective: The purpose of this study is to investigate spatiotemporal patterns of tumors by extracting semi-quantitative as well as w...

متن کامل

Identification of High Crash Road Segment using Genetic Algorithm and Dynamic Segmentation

This paper presents an evolutionary algorithm for recognizing high and low crash road segments using Genetic Algorithm as a dynamic segmentation method. Social and economic costs as well as physical and mental injuries make the governments perceiving to road safety indexes in order to diminish the consequences of road accidents. Due to the limitation of budget for safety...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Pattern Recognition

دوره 34  شماره 

صفحات  -

تاریخ انتشار 2001