Building Classification of Terrestrial Images by Generic Geometric Hierarchical Cluster Analysis Features

نویسندگان

  • Gerd Brunner
  • Hans Burkhardt
چکیده

C la s s ifi c a tio n o f Te r r e s tr ia l I m a ge s b y G e ne r ic G e o m e tr ic H ie r a r c h ic a l C lus te r A na ly s is Fe a tur e s Gerd B ru n n er a n d H a n s B u rk h a rdt In s titu te fo r Pa ttern R ec o g n itio n a n d Im a g e Pro c es s in g , C o m p u ter S c ien c e D ep a rtm en t, U n ivers ity o f F reib u rg , Geo rg es-K o eh ler-A llee 0 5 2 , 7 9 1 1 0 F reib u rg , Germ a n y Abstract The s co p e o f this p ap er is the challen gin g tas k o f clas s i-fy in g terres trial im ages o f bu ild in gs , au to m atically. S traight lin e s egm en ts an d their co n n ectiv ity in co rp o rate s ign ifi can t in fo rm atio n abo u t o bject s hap es. M an-m ad e bu ild in gs exhibit s p ecial gen eric s hap es w hich are ex tracted fro m embed d ed s p atial an d an gu lar lin e s egm en t relatio n s hip s by clu s ter an aly s is. A fter em p lo y in g an agglo m erativ e hierarchical clu s ter an aly s is w e o btain geo m etrical s tru ctu re in-fo rm atio n featu res o n d ifferen t s cales. Fo r the clas s ifi ca-tio n p ro ces s w e ap p ly s u p p o rt v ecto r m achin es (S V M) w ith p o ly n o m ial an d rad ial bas is fu n ctio n (R B F) kern els to s …

برای دانلود 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

Detection of some Tree Species from Terrestrial Laser Scanner Point Cloud Data Using Support-vector Machine and Nearest Neighborhood Algorithms

acquisition field reference data using conventional methods due to limited and time-consuming data from a single tree in recent years, to generate reference data for forest studies using terrestrial laser scanner data, aerial laser scanner data, radar and Optics has become commonplace, and complete, accurate 3D data from a single tree or reference trees can be recorded. The detection and identi...

متن کامل

A field investigation of application of digital terrestrial photogrammetry to characterize geometric properties of discontinuities in open-pit slopes

In order to analyze the slope stability in open-pit mines, the structural parameters of rock mass such as persistence and spatial orientation of discontinuities are characterized through field surveys, which involve spending high costs and times as well as posing high risks of rock toppling and rock fall. In the present work, a new application of terrestrial digital photogrammetry is introduced...

متن کامل

Spectral-spatial classification of hyperspectral images by combining hierarchical and marker-based Minimum Spanning Forest algorithms

Many researches have demonstrated that the spatial information can play an important role in the classification of hyperspectral imagery. This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. In the proposed method ten spatial/texture features, using mean, standard deviation, contrast, homogeneity, corr...

متن کامل

A novel method for locating the local terrestrial laser scans in a global aerial point cloud

In addition to the heterogeneity of aerial and terrestrial views, the small scale terrestrial point clouds are hardly comparable with large scale and overhead aerial point clouds. A hierarchical method is proposed for automatic locating of terrestrial scans in aerial point cloud. The proposed method begins with detecting the candidate positions for the deployment of the terrestrial laser scanne...

متن کامل

Robust Method for E-Maximization and Hierarchical Clustering of Image Classification

We developed a new semi-supervised EM-like algorithm that is given the set of objects present in eachtraining image, but does not know which regions correspond to which objects. We have tested thealgorithm on a dataset of 860 hand-labeled color images using only color and texture features, and theresults show that our EM variant is able to break the symmetry in the initial solution. We compared...

متن کامل

A Knowledge Based Hierarchical Classification Tree for 3d Facade Modeling Using Terrestrial Laser Scanning Data

Due to high point density, accuracy and cost-effectiveness, Terrestrial Laser Scanner (TLS) do have the great advantage of providing the details of building facade as required for the production of realistic 3D city models. Thus, a significant amount of research efforts has been directed towards reconstructing building facade models using TLS data. Most of reconstruction strategies are based on...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005