本文選題：船舶檢測(cè)　切入點(diǎn)：高分辨SAR　出處：《遙感技術(shù)與應(yīng)用》2017年02期

【摘要】：船舶檢測(cè)在民用和軍用領(lǐng)域都具有廣闊的前景。利用高分辨率SAR圖像可以提高海上船舶檢測(cè)精度,但同時(shí)也面臨船舶旁瓣、海表漂浮物及人工設(shè)施等物體的干擾。針對(duì)這些不足,提出了一種基于最佳熵雙閾值算法對(duì)SAR影像檢測(cè)的基礎(chǔ)上,利用多種幾何屬性特征組合優(yōu)化初步檢測(cè)結(jié)果的算法。首先,基于最佳熵雙閾值算法對(duì)研究區(qū)域的Radarsat-2影像進(jìn)行初步檢測(cè),得到潛在船只目標(biāo);其次,計(jì)算潛在目標(biāo)的核密度、長(zhǎng)寬比、潛在像元數(shù)目等3個(gè)特征;最后,利用客觀權(quán)重分配方法——變異系數(shù)法,針對(duì)3個(gè)特征進(jìn)行權(quán)重分配,降低虛警率,達(dá)到優(yōu)化船只檢測(cè)結(jié)果的目的,同時(shí)利用AIS數(shù)據(jù)、K-CFAR算法檢測(cè)結(jié)果及黃河口的ALOS-2數(shù)據(jù)驗(yàn)證了該算法的有效性和實(shí)用性。
[Abstract]:Ship detection has broad prospects in both civil and military fields.In order to solve these problems, a new algorithm based on optimal entropy double threshold algorithm for SAR image detection is proposed, which optimizes the initial detection results by combining various geometric attributes.The objective weight allocation method, variation coefficient method, is used to distribute the weights according to the three characteristics to reduce the false alarm rate and to optimize the detection results of ships.At the same time, the validity and practicability of the algorithm are verified by using the AIS data and the ALOS-2 data of the Yellow River estuary.
【作者單位】： 中國(guó)科學(xué)院遙感與數(shù)字地球研究所;中國(guó)科學(xué)院大學(xué);成都理工大學(xué);
【基金】：高分辨率對(duì)地觀測(cè)系統(tǒng)重大專項(xiàng)(01-Y30A03-9001-12/13)
【分類號(hào)】：TN957.52
，

本文編號(hào)：1720926