] by the
iparison,
nost no
le as the
s Figure
th local
precisely
e global
thod are
letection
wn and
yroposed
datasets
nce and
10w the
mework,
| dataset
tep. The
e are 46
1 human
on the
step
original
own. By
tections,
missed correct detections and the newly defined correct
detection rate and completeness rate, it is easy to find that the
detection accuracy is improved step by step. Since the number
of detected regions under each dataset is different from each
other, it is unreasonable to simply use the "ROC (receiver
operating characteristic) curve" to analyze the performance.
Instead we define two new rates to explain it.
n Numberof correct detection
Correct detectionrate 2 ——————————— —————— * 10096 (8)
Overallnumber
; 9
Compleieness rate = Numberof correct detection *100% ( )
Number of correct detection + Missed correct detection
In this example, even for the original datasets, there are 6
changing regions missed. And after the 1°“ and 2" step, the
number of wrong detections is reduced in large numbers. At the
same time there are 2 more changing regions newly extracted
because of the “global location difference rectification” and the
“illumination change adjustment”. While after the 3" step of
“precise location difference rectification”, not only the number
of wrong detections is further greatly reduced, but also all the
changing regions are correctly detected. By greatly reducing the
number of wrong detections, it is expected that the checking
time of operators is reduced a lot. In this way, the overall cost
and processing time is also greatly improved.
We analyze that the precise rectification of location difference
locally makes each object appear almost the same position in
the two orthoimages, and thus makes it possible to correctly
extract even small changing regions and also to extract each
region more precisely in its range and location. By human check,
it is found that from the result of the 2™ step to the 3" step,
except for the 4 newly detected changing regions, the range and
location accuracy of all 42 regions are improved.
We further analyze the left wrongly detected regions in the
result after the 3™ step processing. The analysis result shows
that among them, 65% are due to ortho-rectification noise, 13%
are from moving cars in the street or changing cars in the
parking lot, 10% are from great change of color due to shadow
or other illumination changes, 9% are because of the growing
trees, 3% are from the remaining location difference. According
to this, it is clear that ortho-rectification noise is the main
reason of the remaining wrongly detected regions.
5. CONCLUSION
In this paper, we present a novel framework to improve the
accuracy of change detection by three processing steps, which
are global location difference rectification, illumination change
adjustment, and precise location difference rectification.
Experimental results show that the proposed framework can not
only greatly remove wrong detections while extracting all the
changing regions, but also improve the range and location
accuracy of correctly detected regions. In details, the correct
detection rate is improved from 15.7% to 41.4%, and the
completeness rate improved from 87.0% to 100%.
For future work, we firstly want to remove or reduce the ortho-
rectification noise since it is the main reason of wrongly
detected regions after the processing of the proposed framework.
On the other hand, we are also considering implementing some
post-processing such as removing the wrongly detected regions
with weird shape like elongated one, and the regions detected
because of moving car in the street or changing cars in the
parking lot, and so on.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
References:
[1] Tomowski, D., Ehlers, M., Klonus S., 2011. Color and
Texture Based Change Detection for Urban Disaster Analysis.
Joint Urban Remote Sensing Event (JURSE), pp. 329-332.
[2] Benedek, C., Sziranyi, T., 2009. Change Detection in
Optical Aerial Images by a Multilayer Conditional Mixed
Markov Model. IEEE Transactions on Geoscience and Remote
Sensing, 47(10), pp. 3416-3430.
[3] Nakamura, S., Aoki, Y., 2010. Automatic Change Detection
of Buildings from Aerial Images. Proceedings of SICE Annual
Conference, pp. 92-95.
[4] Koizumi, H., Yagyu, H., Hashizume, K., Kamiya, T.,
Kunieda, K., Shimazu, H., 2009. Metropolitan Fixed Assets
Change Judgment Using Aerial Photographs. Proceedings of
the 21" Innovative Applications of Artificial Intelligence
Conference, pp. 17-24.
[5] Liu, Z, Zhang, C., Zhang, Z., 2007. Learning-based
perceptual image quality improvement for video conferencing.
Proceedings of IEEE International Conference on Multimedia
and Expo (ICME), pp. 1035-1038.
[6] Harris, C. G., Stephens, M. J., 1988. A Combined Corner
and Edge Detector. Proceedings of the Fourth Alvey Vision
Conference, pp. 147-151.
