改进Grabcut算法在无人机影像船只识别中的应用与研究-软件工程专业论文.docx

ABSTRACT As UAVs are widely used in ship positioning and regulatory fishery activities, aerial image data quantity is increasing. How to detect and locate ships efficiently and accurately from the aerial image data has become urgent needs of industrial processing. In this paper, some key problems are researched and some results are obtained. For sea template selection problem, a sea template automatically selected model is proposed. In this paper, images of different area, climate conditions and illumination condition are selected to build surface template library. Images in template library not only represent the basic property of the sea, but also determine the characteristics of the surface of the background and foreground threshold. An approach to the sea background model construction problem is proposed. Region growth algorithm is used to automatically generate background Trimap. Based on the template detected, SSQ algorithm is used to find the seed point information automatically, which solves the problem that seeds artificial provided are randomness, uncertain, and weak descriptive to sea surface. To solve the issue of accessing sea background automatically, Grabcut algorithm based on background model is proposed. Background Trimap is used to initialize Grabcut algorithm, which meets the need to process large data in batch and solves the problem that initial rectangle of Grabcut is manually provided. While for the segmentation process, repeatedly iterative processes are no longer necessary in accurate separation of background and foreground. For the candidate domain classification problem, the ships candidates’ recognition model is presented. Images after segmentation with improved Grabcut are classified according to shape of candidate domain and pixel domain size to filter the simple-connect candidate to achieve the identification of ships. In summary, this paper proposes a new ship detection method. Comparing with the recognition method that building train