Recognition of High Dimensional Multi-Sensor Remote Sensing Data of Various Spatial Resolution
| Autor: | Viktoriia Hnatushenko, Volodymyr V. Hnatushenko |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Data processing
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Cognitive neuroscience of visual object recognition computer.file_format Computer graphics Digital image Photogrammetry Computer Science::Computer Vision and Pattern Recognition Feature (machine learning) Raster graphics computer Image resolution Remote sensing |
| Zdroj: | 2020 IEEE Third International Conference on Data Stream Mining & Processing (DSMP). |
| DOI: | 10.1109/dsmp47368.2020.9204186 |
| Popis: | High-dimensional multi-sensor image data open new possibilities in remote sensing image analysis. One of the main problems in the field of automated high-dimensional data processing is interpretation and recognition of geometric forms in images. The use of traditional moment invariants in object recognition is limited to simple geometric transforms. In this study, a novel recognition method of high-dimensional multi-sensor remote sensing data of various spatial resolution was proposed. The proposed method of photogrammetric image recognition represented in raster formats of computer graphics enables identification of objects without implementation of complex algorithms involving transformation of digital images. This, in turn, enables improvement of the recognition accuracy. The experiments have shown that the proposed algorithm provides a useful alternative approach to feature reduction in high-dimensional digital image data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|