時空特征提取方法研究
發(fā)布時間：2018-09-05 11:14
【摘要】：視頻內容的認識是計算機視覺中的重要問題,相關研究可以用于智能視頻監(jiān)控、人機交互、視頻檢索等多個領域。視頻的特征表達對于視頻內容的識別至關重要。由于視頻數據量大且內容復雜,同時會受到視角、背景、時間等因素影響,很難提取出良好的視頻特征。近年來相關研究取得了一定進展,但仍存在諸多困難,無法良好的應用到實際場景中。傳統(tǒng)方法以使用人工設計的局部特征表達為主,對視頻中時空信息的描述能力不足。同時,傳統(tǒng)視頻內容識別中特征提取方法依賴復雜的處理運算,其速度難以達到實時性能。本文針對視頻內容識別中的時空特征提取,從識別準確率和識別速度兩方面都進行了研究,本文主要工作如下。1.慢特征分析(SFA:slow feature analysis)從快速變化的信號中提取緩慢變化的特征,這一方法已被證實可以模擬靈長類動物的初級視皮層(V1)的復雜細胞。初級視皮層為腹側和背側通路提供信息,分別用于外觀和運動信息的處理。然而,SFA在局部特征提取中只被用于提取緩慢變化的信息,這些信息主要表征靜態(tài)的外觀信息,不包含運動信息。為了更好的利用時序信息,本文將SFA擴展為時間方差分析(TVA:temporal variance analysis)。TVA學習一個線性映射函數,將原始的時序信息映射為在時序上具有不同變化量的特征分量。受到V1區(qū)域啟發(fā),我們通過TVA學習局部感受野(local receptive field),并通過卷積和池化操作進行局部特征提取。本文對基于TVA的特征提取方法在四個行為識別數據庫上做了測試,實驗結果表明,基于TVA方法提取的慢特征與快特征都能有效的進行特征表達,且能夠獲得比傳統(tǒng)基于梯度方向直方圖特征更好的結果。2.動態(tài)紋理以不同形態(tài)廣泛存在,如火焰、煙霧、車流等,由于動態(tài)紋理視頻在時序上復雜的變化使得動態(tài)紋理識別成為一個具有挑戰(zhàn)性的問題。本文提出一種基于慢特征分析的動態(tài)紋理識別方法。慢特征分析可以從復雜的動態(tài)紋理中學到具有不變性的特征。然而,復雜的時間變化要求高層級的語義信息來進行特征表達以達成時間不變性,這難以通過慢特征分析方法直接從高維視頻中學習到。我們提出了基于流形約束的慢特征分析(MR-SFA:manifold regularized SFA)學習一個低語義級別的局部特征,以描述復雜的動態(tài)紋理。MR-SFA約束具有相似初始狀態(tài)的特征在時間上也具有相似的變化,此方法可以學到一個具有部分可預測性的慢變化特征,以應對動態(tài)紋理的復雜性。本文在動態(tài)紋理識別和動態(tài)場景識別數據庫上進行了實驗,實驗結果驗證了MR-SFA的有效性。3.傳統(tǒng)的視頻特征提取方法對于實時性或大規(guī)模應用而言時間效率太低。通過將特征提取中所需的光流信息替換為視頻壓縮域中的運動向量(MV:motion vector),時間效率可以在一定程度上得到緩解。此外,壓縮域中的其他信息也可以被用于特征提取。在傳統(tǒng)壓縮視頻中,DCT(discrete cosine transform)系數編碼了視頻中連續(xù)幀之間的殘差信息,這部分信息是運動向量所指向的塊(block)無法捕捉的信息。我們提出了一組名為殘差邊緣直方圖的特征,利用DCT系數的不同部分進行視頻的特征提取。另一方面,在深度圖視頻中,我們利用了深度圖視頻的壓縮域信息,包括DWT(discrete wavelet transform)系數和間隔點(breakpoints)信息。DWT系數描述了深度圖中的深度信息,而間隔點保證了深度圖視頻具有銳利清晰的邊緣,本文利用這兩種壓縮域信息提取了一系列用于深度圖視頻的特征。本文在行為識別數據庫上對上述特征提取方法進行了驗證,實驗結果表明,相比傳統(tǒng)方法本文方法在保證良好識別準確率的基礎上具有明顯的速度優(yōu)勢。綜上,一方面,本文基于對視頻時空信息的分析,提出了新的時空局部特征提取方法,以獲得更優(yōu)的識別準確率;另一方面,本文從壓縮域信息出發(fā),直接從被壓縮的視頻信息中進行時空特征的提取,在保證良好識別準確率的情況下大幅提高了識別速度。
[Abstract]:Video content recognition is an important issue in computer vision, and related research can be used in intelligent video surveillance, human-computer interaction, video retrieval and other fields. Video feature expression is very important for video content recognition. It is difficult to extract good video features. In recent years, related research has made some progress, but there are still many difficulties, which can not be well applied to actual scenes. In this paper, the space-time feature extraction in video content recognition is studied from the aspects of recognition accuracy and recognition speed. The main work of this paper is as follows. 1. Slow feature analysis (SFA) extracts slowly changing signals from fast changing signals. The primary visual cortex provides information for ventral and dorsal pathways, respectively, for processing appearance and motion information. However, SFA is only used to extract slowly varying information in local feature extraction, which mainly represents static information. In order to make better use of temporal information, this paper extends SFA to time variance analysis (TVA). TVA learns a linear mapping function, which maps the original temporal information to the characteristic components with different temporal variations. Local receptive field is used to extract local features by convolution and pooling. In this paper, the method of feature extraction based on TVA is tested on four behavioral recognition databases. The experimental results show that both slow and fast features extracted by TVA can be effectively expressed and can be transmitted by comparison. Dynamic texture exists widely in different shapes, such as flame, smoke, traffic flow and so on. Because of the complex changes of dynamic texture video sequence, dynamic texture recognition becomes a challenging problem. This paper presents a dynamic texture recognition method based on slow feature analysis. Slow feature analysis can learn invariant features from complex dynamic textures. However, complex temporal variations require high-level semantic information to express features to achieve time invariance, which is difficult to be learned directly from high-dimensional video by slow feature analysis. We propose a manifold-based slow feature. MR-SFA: manifold regularized SFA (MR-SFA) learns a low semantic level local feature to describe a complex dynamic texture. MR-SFA constraints with similar initial state features also have similar changes in time. This method can learn a partially predictable slow change feature to cope with the complexity of dynamic texture. Experiments on dynamic texture recognition and scene recognition databases demonstrate the effectiveness of MR-SFA. 3. Traditional video feature extraction methods are too time-efficient for real-time or large-scale applications. In traditional compressed video, DCT (discrete cosine transform) coefficients encode the residual information between consecutive frames in the video, which is not available in the block directed by the motion vector. We propose a set of features called residual edge histograms to extract the features of the video using different parts of the DCT coefficients. On the other hand, we use the compression domain information of the depth map video, including DWT (discrete wavelet transform) coefficients and breakpoints. In this paper, a series of features for depth map video are extracted by using the two kinds of compressed domain information. The above feature extraction methods are validated in the behavior recognition database. The experimental results show that the proposed method is better than the traditional method. In summary, on the one hand, based on the analysis of video spatiotemporal information, this paper proposes a new spatiotemporal local feature extraction method to achieve better recognition accuracy; on the other hand, this paper starts from compressed domain information and directly from compressed video information. Spatio-temporal feature extraction in the message greatly improves the recognition speed while ensuring good recognition accuracy.
【學位授予單位】：華南理工大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41
[Abstract]:Video content recognition is an important issue in computer vision, and related research can be used in intelligent video surveillance, human-computer interaction, video retrieval and other fields. Video feature expression is very important for video content recognition. It is difficult to extract good video features. In recent years, related research has made some progress, but there are still many difficulties, which can not be well applied to actual scenes. In this paper, the space-time feature extraction in video content recognition is studied from the aspects of recognition accuracy and recognition speed. The main work of this paper is as follows. 1. Slow feature analysis (SFA) extracts slowly changing signals from fast changing signals. The primary visual cortex provides information for ventral and dorsal pathways, respectively, for processing appearance and motion information. However, SFA is only used to extract slowly varying information in local feature extraction, which mainly represents static information. In order to make better use of temporal information, this paper extends SFA to time variance analysis (TVA). TVA learns a linear mapping function, which maps the original temporal information to the characteristic components with different temporal variations. Local receptive field is used to extract local features by convolution and pooling. In this paper, the method of feature extraction based on TVA is tested on four behavioral recognition databases. The experimental results show that both slow and fast features extracted by TVA can be effectively expressed and can be transmitted by comparison. Dynamic texture exists widely in different shapes, such as flame, smoke, traffic flow and so on. Because of the complex changes of dynamic texture video sequence, dynamic texture recognition becomes a challenging problem. This paper presents a dynamic texture recognition method based on slow feature analysis. Slow feature analysis can learn invariant features from complex dynamic textures. However, complex temporal variations require high-level semantic information to express features to achieve time invariance, which is difficult to be learned directly from high-dimensional video by slow feature analysis. We propose a manifold-based slow feature. MR-SFA: manifold regularized SFA (MR-SFA) learns a low semantic level local feature to describe a complex dynamic texture. MR-SFA constraints with similar initial state features also have similar changes in time. This method can learn a partially predictable slow change feature to cope with the complexity of dynamic texture. Experiments on dynamic texture recognition and scene recognition databases demonstrate the effectiveness of MR-SFA. 3. Traditional video feature extraction methods are too time-efficient for real-time or large-scale applications. In traditional compressed video, DCT (discrete cosine transform) coefficients encode the residual information between consecutive frames in the video, which is not available in the block directed by the motion vector. We propose a set of features called residual edge histograms to extract the features of the video using different parts of the DCT coefficients. On the other hand, we use the compression domain information of the depth map video, including DWT (discrete wavelet transform) coefficients and breakpoints. In this paper, a series of features for depth map video are extracted by using the two kinds of compressed domain information. The above feature extraction methods are validated in the behavior recognition database. The experimental results show that the proposed method is better than the traditional method. In summary, on the one hand, based on the analysis of video spatiotemporal information, this paper proposes a new spatiotemporal local feature extraction method to achieve better recognition accuracy; on the other hand, this paper starts from compressed domain information and directly from compressed video information. Spatio-temporal feature extraction in the message greatly improves the recognition speed while ensuring good recognition accuracy.
【學位授予單位】：華南理工大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41
【相似文獻】
相關期刊論文 前10條
1 馬少華,高峰,李敏,吳成東;神經網絡分類器的特征提取和優(yōu)選[J];基礎自動化;2000年06期
2 管聰慧,宣國榮;多類問題中的特征提取[J];計算機工程;2002年01期
3 胡威;李建華;陳波;;入侵檢測建模過程中特征提取最優(yōu)化評估[J];計算機工程;2006年12期
4 朱玉蓮;陳松燦;趙國安;;推廣的矩陣模式特征提取方法及其在人臉識別中的應用[J];小型微型計算機系統(tǒng);2007年04期
5 趙振勇;王保華;王力;崔磊;;人臉圖像的特征提取[J];計算機技術與發(fā)展;2007年05期
6 馮海亮;王麗;李見為;;一種新的用于人臉識別的特征提取方法[J];計算機科學;2009年06期
7 朱笑榮;楊德運;;基于入侵檢測的特征提取方法[J];計算機應用與軟件;2010年06期
8 王菲;白潔;;一種基于非線性特征提取的被動聲納目標識別方法研究[J];軟件導刊;2010年05期
9 陳偉;瞿曉;葛丁飛;;主觀引導特征提取法在光譜識別中的應用[J];科技通報;2011年04期
10 王華,李介谷;人臉斜視圖象的特征提取與恢復[J];上海交通大學學報;1997年01期
相關會議論文 前10條
1 尚修剛;蔣慰孫;;模糊特征提取新算法[A];1997中國控制與決策學術年會論文集[C];1997年
2 潘榮江;孟祥旭;楊承磊;王銳;;旋轉體的幾何特征提取方法[A];第一屆建立和諧人機環(huán)境聯合學術會議（HHME2005）論文集[C];2005年
3 薛燕;李建良;朱學芳;;人臉識別中特征提取的一種改進方法[A];第十三屆全國圖象圖形學學術會議論文集[C];2006年
4 杜栓平;曹正良;;時間—頻率域特征提取及其應用[A];2005年全國水聲學學術會議論文集[C];2005年
5 黃先鋒;韓傳久;陳旭;周劍軍;;運動目標的分割與特征提取[A];全國第二屆信號處理與應用學術會議�？痆C];2008年
6 魏明果;;方言比較的特征提取與矩陣分析[A];2009系統(tǒng)仿真技術及其應用學術會議論文集[C];2009年
7 林土勝;賴聲禮;;視網膜血管特征提取的拆支跟蹤法[A];1999年中國神經網絡與信號處理學術會議論文集[C];1999年
8 秦建玲;李軍;;基于核的主成分分析的特征提取方法與樣本篩選[A];2005年中國機械工程學會年會論文集[C];2005年
9 劉紅;陳光，
本文編號：2224105
本文鏈接：http://sikaile.net/shoufeilunwen/xxkjbs/2224105.html
