Abstract | ||
---|---|---|
The demand for aerial surveillance video keeps growing in recent years. It has been proved to be an effective way to collect information for a wide range of applications, such as intelligence transportation or military applications. In this work, we propose an automatic image segmentation and labeling system for aerial surveillance images. To deal with over segmentation results from existing region segmentation methods, we perform region merging by constructing an undirected-graph based on 8-connected local neighborhood. For each region we extract low-level features and use Support Vector Machine (SVM) classifier to label the region. Based on the output of the SVM classifier adjacent regions with the same label will be further merged to obtain the final labeling result. The experimental results have shown that our proposed system can effectively segment and label various aerial images. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ITST.2012.6425229 | ITST |
Keywords | Field | DocType |
information collection,region labeling,image segmentation,region segmentation,region merging,svm classifier,merging,automatic image segmentation,feature extraction,support vector machine,undirected graph,graph theory,aerial surveillnace,labeling,aerial video surveillance,support vector machines,video surveillance | Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Support vector machine,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Region growing,Connected-component labeling,Minimum spanning tree-based segmentation | Conference |
ISBN | Citations | PageRank |
978-1-4673-3069-5 | 3 | 0.40 |
References | Authors | |
5 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hsu-Yung Cheng | 1 | 243 | 23.56 |
Ding-Wen Wu | 2 | 3 | 0.40 |