TY - JOUR
T1 - Skeleton matching with applications in severe weather detection
AU - Kamani, Mohammad Mahdi
AU - Farhat, Farshid
AU - Wistar, Stephen
AU - Wang, James Z.
N1 - Funding Information:
This material is based upon work supported by the National Science Foundation under Grant No. 1027854 . The authors would like to thank Jia Li of Penn State and Michael A. Steinberg of Accuweather Inc. for helpful discussions, the National Oceanic and Atmospheric Administration (NOAA) for providing the data, and Yu Zhang and Yukun Chen for assisting with data collection.
Funding Information:
This material is based upon work supported by the National Science Foundation under Grant No. 1027854. The authors would like to thank Jia Li of Penn State and Michael A. Steinberg of Accuweather Inc. for helpful discussions, the National Oceanic and Atmospheric Administration (NOAA) for providing the data, and Yu Zhang and Yukun Chen for assisting with data collection.
Publisher Copyright:
© 2017 Elsevier B.V.
PY - 2018/9
Y1 - 2018/9
N2 - Severe weather conditions cause an enormous amount of damages around the globe. Bow echo patterns in radar images are associated with a number of these destructive conditions such as damaging winds, hail, thunderstorms, and tornadoes. They are detected manually by meteorologists. In this paper, we propose an automatic framework to detect these patterns with high accuracy by introducing novel skeletonization and shape matching approaches. In this framework, first we extract regions with high probability of occurring bow echo from radar images and apply our skeletonization method to extract the skeleton of those regions. Next, we prune these skeletons using our innovative pruning scheme with fuzzy logic. Then, using our proposed shape descriptor, Skeleton Context, we can extract bow echo features from these skeletons in order to use them in shape matching algorithm and classification step. The output of classification indicates whether these regions are bow echo with over 97% accuracy.
AB - Severe weather conditions cause an enormous amount of damages around the globe. Bow echo patterns in radar images are associated with a number of these destructive conditions such as damaging winds, hail, thunderstorms, and tornadoes. They are detected manually by meteorologists. In this paper, we propose an automatic framework to detect these patterns with high accuracy by introducing novel skeletonization and shape matching approaches. In this framework, first we extract regions with high probability of occurring bow echo from radar images and apply our skeletonization method to extract the skeleton of those regions. Next, we prune these skeletons using our innovative pruning scheme with fuzzy logic. Then, using our proposed shape descriptor, Skeleton Context, we can extract bow echo features from these skeletons in order to use them in shape matching algorithm and classification step. The output of classification indicates whether these regions are bow echo with over 97% accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85020742363&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85020742363&partnerID=8YFLogxK
U2 - 10.1016/j.asoc.2017.05.037
DO - 10.1016/j.asoc.2017.05.037
M3 - Article
AN - SCOPUS:85020742363
VL - 70
SP - 1154
EP - 1166
JO - Applied Soft Computing
JF - Applied Soft Computing
SN - 1568-4946
ER -