该文提出一种部分基矩阵稀疏约束的非负矩阵分解(Non-negative Matrix Factorization with Sparseness Constraints on Parts of the Basis Matrix,NMFSCPBM)方法,其次将水印嵌入在NMFSCPBM分解后的基矩阵大系数中,利用NMFSCPBM提取视频运动特征自适应控制水印嵌入强度。最后,在水印检测时,只要残余视频中包含有视频最小剩余子块数,就可以恢复出完整基矩阵,进而提取出完整水印。实验表明,与同类方法相比,该方法抵抗强剪切攻击的能力获得了较大程度提升。
行为识别在语义分析领域具有很高的学术研究价值和广泛的市场应用前景.为了实现对视频行为的准确描述,提出了2类构建稠密轨迹运动描述子的方法.1)通过光流约束和聚类,实现对运动区域的稠密采样,以获取行为的局部位置信息;2)选取目标运动角点为特征点,通过对特征点的跟踪获取运动轨迹;3)在以轨迹为中心的视频立方体内,分别构建三维梯度方向直方图(3Dhistograms of oriented gradients in trajectory centered cube,3DHOGTCC)描述子和三维光流梯度方向直方图(3Dhistograms of oriented optical flow gradients,3DHOOFG)描述子,用以对运动的局部信息进行准确描述.为了充分利用行为发生的场景信息,提出了一种融合动态描述子和静态描述子的行为识别新框架,使得动态特征与静态特征相互融合支撑,即使在摄像头运动等复杂场景下,亦能取得较好的识别效果.在Weizmann和UCF-Sports数据库采用留一交叉验证,在KTH和Youtube数据库采用4折交叉验证.实验证明了提出新框架的有效性.
Focusing on the problem of goal event detection in soccer videos,a novel method based on Hidden Markov Model(HMM) and the semantic rule is proposed.Firstly,a HMM for a goal event is constructed.Then a Normalized Semantic Weighted Sum(NSWS) rule is established by defining a new feature of shots,semantic observation weight.The test video is detected based on the HMM and the NSWS rule,respectively.Finally,a fusion scheme based on logic distance is proposed and the detection results of the HMM and the NSWS rule are fused by optimal weights in the decision level,obtaining the final result.Experimental results indicate that the proposed method achieves 96.43% precision and 100% recall,which shows the effectiveness of this letter.
