复杂条件下的船舶目标检测的图象预处理  

Image Preprocessing for Ship Detection Under Complex Conditions

作　　者：任明武[1] 曹雨龙[1] 杨静宇[1] 唐振民[1] 

机构地区：[1]南京理工大学计算机科学与工程系,南京210094

出　　处：《计算机工程》2000年第10期68-70,共3页Computer Engineering

摘　　要：给出了一种复杂条件下基于视频图象的实现船舶目标自动检测的图象预处理方法，其成功运行于长江三峡临时船闸的船舶检测系统中。因在室外环境中，船舶检测受到反光、阴影等的干扰；对干扰区的检测成为提高精度的关键。提出了一种新的基于边缘带周围象素的灰度直方图构造方法．该直方图能同时用于检测极大和极小的目标，用于反光和阴影区域的检测；并分析和使用干扰区的灰度和结构特征，进行干扰区域的进一步确认，提高了检测精度和抗噪性。This paper introduces the image preprocess methods for ship detection method under complex conditions. which has been successfully running in the temporary ship lock of Three Gorges. In the outdoors, the decision of recognition is depended on the decision of disturb area detection. It analyzes the gray value and structure of image, proposes a new method to form a special histogram of only those pixels near the edges. This histogram can be used for small object segment and also large. By used structure and position constrain, the method is accurate and high robust.

关 键 词：船舶 目标检测 图象预处理 模式识别 

分 类 号：U675.79[交通运输工程—船舶及航道工程]