This work develops highly efficient algorithms for analyzing large images. Applications include object-based change detection and screening. The algorithms are 10-100 times as fast as existing software, sometimes even outperforming FGPA/GPU hardware, because they are designed to suit the computer architecture. This thesis describes the implementation details and the underlying algorithm engineering methodology, so that both may also be applied to other applications.
algorithm engineering
- image analysis
- image processing
- lossless image compression
- SIMD