Loading...
Please wait, while we are loading the content...
Similar Documents
Recognition of Water Bodies from Remotely Sensed Imagery by Using Neural Network
| Content Provider | Semantic Scholar |
|---|---|
| Author | Wang, Kefei Zhu, Yifeng |
| Abstract | A Learning Vector Quantization (LVQ) neural network was used to extract water bodies from Landsat 4 satellite images in this project. We compared LVQ with the Tasseled Cap Transformation (TCT) method and a conventional rule based method. Results show that LVQ can achieve a classification error around 0.35%. Although this is not as good as the rule based algorithm, LVQ provides a more general approach to recognize objects from satellite images. We also found that the error of thresholding on the wetness in the TCT method is too large to be practical. After extraction water bodies from images, we classified them into lakes, rivers and sea. Keywords— computer vision, image processing, Tasseled Cap Transformation, water body detection, geographic information systems, remote sensing, neural network. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.cse.unl.edu/~yzhu/cs873/report.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
