Conclusions
Image segmentation is the first and most important step in
OBIA
. A refined
HBC-SEG
method, which embeds straight line
features into image segmentation, is developed in this study.
A new neighborhood model called
IPSL
-neighborhood is pro-
posed and utilized to guide the hierarchical segment merging
processes.
IPSL
-neighbors with an appropriate merging cost are
re-merged by undertaking a low risk of under-segmentation
errors. The refined method inherits the advantages of
HBC-SEG
,
including high segmentation accuracy and boundary preci-
sion. This technique effectively reduces over-segmentation
errors and maintains the same level of under-segmentation
error ratio, particularly in man-made areas, and facilitates
subsequent
OBIAs
. In addition, the proposed
IPSL
-neighbor-
hood model has other possible applications aside from image
segmentation. First, object shape analysis might be more
effective. For instance, length calculation might be more
precise for linear objects after segment refinement. Second, in
context-based image classification, this model might screen
out highly relative neighbors and could thus allow for a more
accurate image classification. However, the refined method
requires additional computations on straight-line detec-
tion, segment-line topology calculation, and straight-line-
constrained merging. Future work will focus on improving
method efficiency by using image partitioning and parallel
computation and extensively applying this new neighborhood
model in image feature extraction and classification.
Acknowledgments
This work is jointly supported by the National Natural
Science Foundation of China (41171321), the Distin-
guished Young Scientist Foundation of Jiangsu Province
(BK20140042), the Natural Science Foundation of the Jiangsu
Higher Education Institutions of China (11KJA420001), and
the Priority Academic Program Development of Jiangsu High-
er Education Institutions. The authors would like to thank the
three anonymous reviewers for their very constructive com-
ments which improved the manuscript significantly.
References
Anders, N.S., A.C. Seijmonsbergen, and W. Bouten, 2011.
Segmentation optimization and stratified object-based analysis
for semi-automated geomorphological mapping,
Remote Sensing
of Environment
, 115:2976–2985.
Baatz M., and A. Shäpe, 2000. Multiresolution segmentation: An opti-
mization approach for high quality multi-scale image segmenta-
tion,
Angewandte Geographische Informationsverarbeitung XI
(J.
Strobl, T. Blaschke, and G. Griesebner, editors), Salzburg: Herbert
Wichmann Verlag, Heidelberg, (J. Strobl, pp. 12–23.
Burns, J.B., A.R Hanson, and E.M. Riseman, 1986. Extraction straight
lines,
IEEE Transactions on Pattern Analysis and Machine
intelligence
, 8(4):425–456.
Canny, J.F., 1986. A computational approach to edge detection,
IEEE
Transactions on Pattern Analysis and Machine intelligence
,
8(6):679–698.
Carleer, P., O. Debeir, and E. Wolff, 2005. Assessment of very
high spatial resolution satellite image segmentations,
Photo-
grammetric Engineering & Remote Sensing
, 71(11):1285–1294.
Chen, J., J. Li, D. Pan, Q. Zhu, and Z. Mao, 2012. Edge-guided multi-
scale segmentation of satellite multispectral imagery,
IEEE Trans-
actions on Geoscience and Remote Sensing
, 50(11):4513–4520.
Crevier, D., 2008. Image segmentation algorithm development using
ground truth image data sets,
Computer Vision and Image
Understanding
, 112(2):143–159.
Dey, V., Y. Zhang, and M. Zhong, 2010. A review on image
segmentation techniques with remote sensing perspective,
Proceeding of the International Society for Photogrammetry and
Remote Sensing Symposium (ISPRS10)
, pp. 5–7.
Dr
ǎ
gu
ţ
, L., D. Tiede and S.R. Levick, 2010. ESP: A tool to estimate
scale parameter for multiresolution image segmentation of
remotely sensed data,
International Journal Geographical
Information Science
, 24(6):859–871.
Dr
ǎ
gu
ţ
, L., O. Csillik, C. Eisank, and D. Tiede, 2014. Automated
parameterization for multi-scale image segmentation on multiple
layers,
ISPRS Journal of Photogrammetry and Remote Sensing
,
88:119–127.
Gonzalez, R.C., and R.E. Woods, 1992.
Digital Image Processing
,
Third edition, Addison-Wesley.
Kermad, C.D., and K. Chehdi, 2002. Automatic image segmentation
system through iterative edge-region co-operation,
Image and
Vision Computing
, 20(8):541–555.
Li, D., G. Zhang, Z. Wu, and L. Yi, 2010. An edge embedded marker-
based watershed algorithm for high spatial resolution remote
sensing image segmentation,
IEEE Transactions on Image
Processing
, 19(10):2781–2787.
Pal, N.R., and S.K. Pal, 1993. A review on image segmentation
techniques,
Pattern Recognition
, 26(9):1274–1294.
Schiewe, J., 2002. Segmentation of high-resolution remotely sensed
data-concepts, applications and problems,
International
Archives of Photogrammetry Remote Sensing Spatial
Information Science
, 34(4):358–363.
Shankar, B., 2007. Novel classification and segmentation techniques
with application to remotely sensed images,
Transactions on
Rough Sets VII
, pp. 295–380.
Smith, G.M., and R.D. Morton, 2010. Real world objects in Geographic
Object-Based Image Analysis through the exploitation of existing
digital cartography and image segmentation,
Photogrammetric
Engineering & Remote Sensing
,
76(2):163–171.
Tong, H., T. Maxwell, Y. Zhang, and V. Dey, 2012. A supervised and
fuzzy-based approach to determine optimal multi-resolution
image segmentation parameters,
Photogrammetric Engineering &
Remote Sensing
, 78(10):1029–1044.
Trimble, Inc., 2014. eCognition Developer User Guide, URL:
http://
(last date accessed
28 March 2015).
Tullis, J.A., J.R. Jensen, G.T. Raber, and A.M. Filippi. 2010. Spatial
scale management experiments using optical aerial imagery and
LiDAR data synergy,
GIScience & Remote Sensing
, 47(3):338–359.
Vincent, L., and P. Soille, 1991. Watershed in digital spaces: an
efficient algorithm based on immersion simulations,
IEEE
Transactions on Pattern Analysis and Machine Intelligence
,
13(6):583–598.
Wang, M., and R. Li, 2014. Segmentation of high spatial resolution
remote sensing imagery based on hard-boundary constraint and
two-stage merging,
IEEE Transactions on Geoscience and Remote
Sensing
, 52(9):5712–5725.
Yi, L., G. Zhang, and Z. Wu, 2012. A scale-synthesis method for high
spatial resolution remote sensing image segmentation,
IEEE Trans-
actions on Geoscience and Remote Sensing
, 50(10):4062–4070.
Yu, P., A.K. Qin, and D.A. Clausi, 2012. Unsupervised polarimetric
SAR image segmentation and classification using region growing
with edge penalty,
IEEE Transactions on Geoscience and Remote
Sensing
, 50(4):1302–1317.
(Received 24 August 2014; accepted 19 January 2015; final
version 23 January 2015)
406
May 2015
PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING
