發(fā)布時(shí)間：2018-09-19 14:51

【摘要】：本文在深入了解相似關(guān)鍵幀檢測(cè)與相似視頻檢測(cè)國(guó)內(nèi)外研究現(xiàn)狀的基礎(chǔ)上,分析兩者存在的不足,并在以下幾個(gè)方面展開深入研究,取得一定進(jìn)展。首先,改進(jìn)了關(guān)鍵幀全局顏色直方圖,提出光照-尺度金子塔特征。通過構(gòu)建關(guān)鍵幀亮度、裁剪尺度空間金字塔,提高該特征對(duì)光照、尺度裁剪變換的魯棒性。實(shí)驗(yàn)證明,基于全局光照-尺度金字塔特征的相似關(guān)鍵幀檢測(cè)查全率較基于全局顏色直方圖的檢測(cè)效果更好,當(dāng)相似距離閾值?(28)2時(shí),算法查全率達(dá)到95.2%。其次,針對(duì)SIFT特征數(shù)據(jù)維度高,計(jì)算效率低的缺點(diǎn),提出一種基于稀疏編碼的尺度不變特征加速算法(ScSIFT)。以超完備字典將SIFT特征稀疏表示,同時(shí)建立二級(jí)特征索引結(jié)構(gòu),提高特征距離計(jì)算速度與檢索效率。實(shí)驗(yàn)證明,ScSIFT算法與SIFT算法匹配結(jié)果類似,但算法運(yùn)行效率較后者提高了52%。最后,基于本文提出的光照-尺度金字塔特征、ScSIFT算法,結(jié)合時(shí)序分塊順序算法,提出一種融合全局與局部特征的相似視頻片段快速檢測(cè)算法。該算法融合相似視頻片段檢測(cè)中全局特征運(yùn)算速度快、局部特征計(jì)算精度高的優(yōu)點(diǎn)。實(shí)驗(yàn)對(duì)比發(fā)現(xiàn),該算法較傳統(tǒng)的算法準(zhǔn)確率更高,達(dá)到78.2%,同時(shí),算法運(yùn)行效率較高。
[Abstract]:On the basis of deeply understanding the research status of similar key-frame detection and similar video detection at home and abroad, this paper analyzes the shortcomings of the two methods, and makes some progress in the following aspects. Firstly, the key frame global color histogram is improved, and the illumination-scale gold tower feature is proposed. By constructing the brightness of the key frame and clipping the pyramid of the scale space, the robustness of the feature to the illumination and scale clipping transformation is improved. Experiments show that the detection recall rate of similar key frames based on global illumination scale pyramid features is better than that based on global color histogram. When the threshold of similar distance is? (28) 2, the recall rate of the algorithm reaches 95.2%. Secondly, aiming at the disadvantages of high dimension and low computational efficiency of SIFT feature data, a scale-invariant feature acceleration algorithm (ScSIFT).) based on sparse coding is proposed. The SIFT features are represented sparsely by an overcomplete dictionary and a secondary feature index structure is established to improve the computing speed and retrieval efficiency of the feature distance. The experimental results show that the Ssift algorithm is similar to the SIFT algorithm, but the efficiency of the algorithm is 52% higher than that of the latter. Finally, based on the illumination scale pyramid feature scsift algorithm proposed in this paper and the sequential block sequence algorithm, a fast detection algorithm for similar video segments is proposed, which combines global and local features. The algorithm combines the advantages of fast global feature operation and high accuracy of local feature computation in similar video segment detection. The experimental results show that the accuracy of the algorithm is higher than that of the traditional algorithm, reaching 78.2. At the same time, the efficiency of the algorithm is high.
【學(xué)位授予單位】：國(guó)防科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 彭勃宇;王崴;周誠(chéng);劉曉衛(wèi);;面向增強(qiáng)現(xiàn)實(shí)的SUSAN-SURF快速匹配算法[J];計(jì)算機(jī)應(yīng)用研究;2015年08期

2 郭延明;謝毓湘;老松楊;白亮;;相似視頻片段的檢測(cè)與定位方法研究[J];計(jì)算機(jī)科學(xué);2014年10期

3 姜超;耿則勛;婁博;魏小峰;沈忱;;基于GPU的SIFT特征匹配算法并行處理研究[J];計(jì)算機(jī)科學(xué);2013年12期

4 張正炎;屈小波;林雁勤;陳忠;;基于近似l_0范數(shù)最小化的NMR波譜稀疏重建算法[J];波譜學(xué)雜志;2013年04期

5 吳瀟;李錦濤;唐勝;郭俊波;;基于時(shí)空軌跡行為特征的視頻拷貝檢測(cè)方法[J];計(jì)算機(jī)研究與發(fā)展;2010年11期

6 張志杰;鄒建華;;面向壓縮域視頻拷貝檢測(cè)的主要邊緣相對(duì)相位算法[J];西安交通大學(xué)學(xué)報(bào);2010年10期

7 王瑞;梁華;蔡宣平;;基于GPU的SIFT特征提取算法研究[J];現(xiàn)代電子技術(shù);2010年15期

8 王金德;李曉燕;壽黎但;陳剛;;面向近重復(fù)圖像匹配的SIFT特征裁減算法[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2010年06期

9 文軍;吳玲達(dá);曾璞;謝毓湘;;新聞視頻中基于“場(chǎng)景詞匯”的故事單元相似度分析[J];國(guó)防科技大學(xué)學(xué)報(bào);2009年06期

10 張勇東;張冬明;郭俊波;唐勝;;壓縮域快速視頻拷貝檢測(cè)算法[J];通信學(xué)報(bào);2009年03期

相關(guān)碩士學(xué)位論文 前1條

1 吳伊萍;中文微博情感分類研究[D];華僑大學(xué);2013年

，

本文編號(hào)：2250449