A partition-based VCA end-member extraction method, comprising: conducting rough partitioning on a high-spectral image by using a non-supervision classification method, partitioning image elements having a similar substance into the same block; conducting end-member extraction on an area in each partitioned block by using VCA, inverting the abundance by using a least square method after end-member extraction, and determining one main end-member for each block according to the size of an abundance value; and extracting the main end-members in all blocks to form an end-member matrix of a global image. A VCA end-member extraction method is used in relatively simple environment block after partitioning, the main end-member in a block is then controlled by using the abundance inversion result feedback in the block, so as to prevent missing out a main end-member.
展开▼
