本文選題：衛(wèi)星裝配 + 目標(biāo)識(shí)別��； 參考：《系統(tǒng)工程與電子技術(shù)》2017年05期

【摘要】：針對(duì)在衛(wèi)星機(jī)器人地面裝配領(lǐng)域,基于尺度不變特征變換的目標(biāo)識(shí)別方法存在實(shí)時(shí)性能缺陷的問(wèn)題,提出結(jié)合標(biāo)量量化描述和倒排文件索引的典型目標(biāo)快速識(shí)別方法,以滿足衛(wèi)星裝配過(guò)程中準(zhǔn)確高效識(shí)別工件和裝配體的需求。在初始檢測(cè)、定位和描述特征點(diǎn)的基礎(chǔ)上,通過(guò)中值劃分和遮蔽掩模方式完成浮點(diǎn)型描述向量的標(biāo)量量化;利用倒排文件結(jié)構(gòu)的查詢策略快速搜索近鄰特征點(diǎn);依據(jù)距離比率準(zhǔn)則和隨機(jī)采樣原則篩選穩(wěn)定匹配點(diǎn);通過(guò)仿射變換求解出矩形框中心坐標(biāo)和邊界寬度識(shí)別目標(biāo)。實(shí)驗(yàn)結(jié)果表明,所提識(shí)別算法的平均正確率均值曲線圖包圍面積平均達(dá)到尺度不變特征變換的90.12%,能夠正確匹配特征點(diǎn)并框選有效目標(biāo),具備相似的區(qū)分性能優(yōu)勢(shì);同時(shí)匹配階段執(zhí)行時(shí)間只有尺度不變特征變換的19.54%,總體執(zhí)行時(shí)間也只有49.84%,具有實(shí)時(shí)性能方面的優(yōu)勢(shì)。
[Abstract]:In the field of satellite robot ground assembly, the target recognition method based on scale-invariant feature transformation has the defect of real-time performance. A fast target recognition method based on scalar quantization description and inverted file index is proposed. In order to meet the needs of accurate and efficient identification of parts and assembly during satellite assembly. On the basis of initial detection, location and description of feature points, the scalar quantization of floating point description vectors is accomplished by means of median partitioning and masking, and the nearest neighbor feature points are quickly searched by the query strategy of inverted file structure. According to the distance ratio criterion and random sampling principle, the stable matching points are selected, and the center coordinates and boundary width of rectangular frame are solved by affine transformation. The experimental results show that the average correct rate of the proposed recognition algorithm is the mean curve of the mean curve, which reaches 90.12 of the scale-invariant feature transformation, and it can correctly match the feature points and select the effective target in the frame, so it has the similar distinguishing performance advantage. At the same time, the execution time of matching phase is only 19.54 of the scale invariant feature transformation, and the overall execution time is only 49.84, which has the advantage of real-time performance.
【作者單位】： 河北工業(yè)大學(xué)機(jī)械工程學(xué)院;哈爾濱工業(yè)大學(xué)機(jī)器人技術(shù)與系統(tǒng)國(guó)家重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家高技術(shù)研究發(fā)展計(jì)劃(863計(jì)劃)(2015AA043101)資助課題
【分類號(hào)】：TP391.41;TP242

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 大江東去;;借助美圖看看快速識(shí)別人物照片[J];電腦迷;2010年21期

2 陶勝;;人民幣紙幣號(hào)碼的快速識(shí)別[J];電腦編程技巧與維護(hù);2013年03期

3 李會(huì)科;李飛;;高速公路導(dǎo)向系統(tǒng)字體快速識(shí)別研究[J];包裝工程;2010年22期

4 張其可,戴連奎;基于近紅外光譜的汽油牌號(hào)快速識(shí)別[J];化工自動(dòng)化及儀表;2005年04期

5 孫立功;閻保定;李萍;屠文珂;;基于特征差異的彩色目標(biāo)快速識(shí)別方法[J];微計(jì)算機(jī)信息;2006年32期

6 倪政林;;領(lǐng)域本體的快速識(shí)別研究[J];新鄉(xiāng)學(xué)院學(xué)報(bào)(自然科學(xué)版);2012年04期

7 陳恩紅,張振亞,王煦法;相接行凸約束網(wǎng)絡(luò)的快速識(shí)別算法[J];軟件學(xué)報(bào);2002年05期

8 曹學(xué)軍;一個(gè)快速識(shí)別網(wǎng)格化圖紙的方法[J];計(jì)算機(jī)學(xué)報(bào);1994年02期

9 王謙,劉t，

本文編號(hào)：1941737