http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Novel Algorithm for Tracking and Forecasting Convective Cells Using Satellite Image Sequences
Jia Liu,Chuancai Liu,Chao Ma,Danyu Qin,Furong Peng 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.2
Accurate storm tracking and forecasting are essential parts of severe weather warning operations. The main problem of existing tracking and forecasting algorithms is unphysical split and merger of cloud clusters within the life cycle of Mesoscale Convective System (MCS). To address this issue, an automatic algorithm called TFCC (Tracking and Forecasting Convective Cells) is proposed for tracking and forecasting convective cells using infrared (IR) image sequences from geostationary meteorology satellite. In this paper, convective cells are utilized for tracking and forecasting instead of MCS because convective cells are stable portion in MCS. TFCC algorithm utilizes overlapping technique and uses a dynamic constraint technique based combinatorial optimization method. Moreover, displacement of the geometrical centroid is utilized to forecast the movement of convective cells. Case studies show that convective cells are tracked and forecasted efficiently in different phases of MCS lifecycle including genesis, maturity and dissipation using TFCC algorithm. Categorical statistics and contingency tables method applied to various case studies over China show that TFCC algorithm efficiently and accurately.
Salient Object Detection Based on Context and Location Prior
Duzhen Zhang,Chuancai Liu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.4
A novel automatic salient object detection algorithm, which integrates context-based saliency with location computation based on the boundary priors, is proposed. Input image is expressed as a close-loop graph with superpixels as nodes and salient object of image has a well-defined graph-based manifold ranking location. The saliency of the image elements is defined based on their relevances to the given seeds or queries. Saliency object location is carried out in a two-stage scheme to extract background regions and foreground salient objects efficiently. We introduce a location weight to measure the relationship of superpixels and the centroid of the detected salient regions to eliminate the background. Saliency map is computed through context analysis and location computing based on multi-scale superpixels. Experimental results on three public benchmark datasets demonstrate that our approach performs well compared to existing state-of-the-art methods.