International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV. Part B2. Istanbul 2004
8 8 / ;
(a) Origin image
(b) Central lines after feature grouping (c) Road segments after recognition (d) Detection results
Fig.5 Automatic detection and extraction results for road network in low resolution images. (The white lines in origin image are the
vector lines of old map. The red circles in detection results are the wrong results).
5. CONCLUSIONS
[n this paper two kinds of new algorithms for detecting feature
changes that is buffer detection (BD) algorithm and double-
buffer detection (DBD) algorithm are illustrated. It can be scen
that for the change detection between new map and old map the
BD algorithm and DBD algorithm are not only effective for
road detection but also for other features. For change detection
based on new image and old map, some new ideas and
strategies including hybrid feature grouping techniques,
automatic road recognition based on knowledge base,
knowledge inference for road recognition, road re-grouping etc.
are discussed. Corresponding experiments proved that the
algorithms are effective and practical. The future work is to
focus on integration of all kinds of information for assisting in
road extraction and improving the intelligence of automatic
objects extraction using image pattern recognition, AI and other
techniques. Indeed, automatic change detection and updating is
really a very difficult problem. But it is especially useful not
only for geo-spatial data updating but some special application
such as military fields. For geo-spatial data updating. semi-
automatic change detection and updating may be the best
approach at present.
ACKNOLEDGEMENTS
The work described in this paper was substantially funded by
innovation rescarch fund program of Wuhan University and
open research fund program [No.(01)0304] of LIESMARS of
Wuhan University.
REFERENCE
Bruzzone, L.Diego, F.P.. 2000, Automatic Analysis of the
Difference Image for Unsupervised Change Detection. IEEE
Transactions on Geoscience and Remote Sensing, 38(3). pp.
2271-1182.
Chalifoux, S., Cavayas, F.,Gray, J.F.,1998, Map-Guided
Approach for the Automatic Detection on Landsat TM Images
of Forest Stands Damaged by the Spruce
Budworm.Photogrammetric Engineering and Remote
Sensing,64(6),pp. 629-635.
Dai, X.L., Khorram, S.. 1997,Development of a New Automated
Land Cover Change Detection System from Remotely Sensed
Imagery based on Artificial. Neural. Networks, IGARSS '97,
Singapore,pp.1029 -1031.
Darvishzadeh, R..2000. Change Detection for urban spatial
databases using Remote Sensing and GIS, The International
464
Archives of the Pthotogrammetry, Remote Sensing and Spatial
Information Science. 34(IIT).pp.245-251.
Dreshler,F., et.al, 1993, A Knowledge-Based Approach to the
Detection and Interpretation of Changes in Acrial Images,
IGARSS '93, Tokyo, pp. 159 161.
Fan,H., Zhang.J.Q., Zhang, Z.X.. Liu, Z.F., 1999,House Change
Detection based on DSM of Aerial Image in Urban Area,Geo-
spatial information science, 2(1),pp.68-72.
Active
compute
D.,1988, Snakes:
journal of
Kass,M., Witkin, A.,Terzopoulos,
Contour Models. International
vision, 1(4):321-331.
Li, D.R., 2003, Towards the development of RS and GIS in 21
century, Geomatics and Information Science of Wuhan
University, 28(2), pp. 127-131.
Li, D.R, Sui, H.G., 2002, Automatic Change Detection of
Geo-spatial Data from Imagery. The International Archives of
the Pthotogrammetry, Remote Sensing and Spatial Information
Science, 34(1I).pp.245-251.
Macleod,R.D.,Congaltion, R.G.,1999, A Quantitative
Comparison of Change Detection Algorithms for Monitoring
Eelgrass from Remotely Sensed Data, Photogrammetric
Engineering and Remote Sensing, ,64(3).pp.207-216.
Maupin, P., etal, 1997. Contribution of Mathematical
Morphology and Fuzzy Logic to the Detection of Spatial
Change in an Urbanized Area: Towards a Greater Integration of
Image and Geographical Information Systems, IGARSS '97,
Singapore, pp.207 —209.
Peled, A., 1998, Toward Automatic Updating of the Israeli
national GIS--Phase || , The International Archives of the
Photogrammetry, Remote Sensing and Spatial Information
Science, 32(4), pp.467-472.
Sui, H.G., 2001.A Framework for automated change detection
system. Geolnformatics & DMGIS 2001, pp.278-283.
Sui, H.G., 2002, Automatic Change Detection for Road-
Networks based on Features, Wuhan University.
Wang, F., 1993,A Knowledge-Based Vision System for
Detecting Land Changes at Urban Fringes, IEEE Transactions
on Geoscience and Remote Sensing, 31(1), pp.136 —145.
Wang,l.Y.,et.al, 1992, The Cartographical
Generalization, Survey and Mapping Press, 1992.
Principle of
ABS!
In orc
neede
sat da
correc
thoug
reveal
Grour
verific
mum-
repect
realiz
other
detail
over t.
Detec
dersta
the ef
regard
relatec
2003;
which
2000).
sect A
of Ed
can bi
chang:
tainab
The re
rica (s
ing o
close t
tion re
and tl
bance
Kakan
(ses +
data ai
geo-in:
anthro
forests
ent bic
of BI
change
related
spread
the nec
tailed i
—————
* corres
