It is difficult to balance local development and global exploration in a multi-modal function optimization process, therefore, an Enhanced Multi-Species-based Particle Swarm Optimization (EMSPSO) was proposed. An improved multi-species evolution strategy was introduced to Species-based Particle Swarm Optimization (SPSO). Several species which evolved independently were established by selecting seed in the individual optimal values to improve the stability of algorithm convergence. A redundant particle reinitialization strategy was introduced to the algorithm in order to improve the utilization of the particles, and enhance global search capability and search efficiency of the algorithm. Meanwhile, in order to prevent missing optimal extreme points in the optimization process, the rate update formula was also improved to effectively balance the local development and global exploration capability of the algorithm. Finally, six typical test functions were selected to test the performance of EMSPSO. The experimental results show that, EMSPSO has high multi-modal optimization success rate and optimal performance of global extremum search.

To improve situations as follows: in the strategies of offshore ship and well platform detection, most masks of sea zones use non-real time shoreline database; targets seeking algorithms lack capability of searching targets in large scale images, a strategy of ship and well platform detection based on optical remote sensing images was proposed. The strategy included building masks of sea zones using morphological operations, determining decision algorithms of targets' existence, and extracting targets' locations based on iterative optimal Threshold Segmentation (TS) in Sliding Windows (SW). Parameters in the decision algorithm and the size of sliding window were analyzed, and the corresponding results were cross validated with that of artificial visual interpretation. The experimental results prove that the absolute accuracy of targets extraction arrives 0.981 while relative accuracy of targets extraction arrives 0.954 with proper parameters set. This strategy shows practical value.