基于场景复杂度与不变特征的航拍视频实时配准算法

实时、鲁棒的图像配准是航拍视频电子稳像、全景图拼接和地面运动目标自动检测与跟踪的前提和关键技术.本文以航拍视频序列为处理对象,提出了一种新的基于场景复杂度与不变特征的实时配准算法,其主要特点包括：(1)在对航拍视频配准难点进行详细分析的基础上,有针对性的提出基于积分图的快速图像尺度空间构建、依据场景复杂度的检测特征点数量在线精确控制、基于描述子误差分布统计特性级的联分类器构造等新方法,使得算法配准性能不随场景的复杂度发生改变,能够在各种地貌条件下实时、稳定的进行图像配准;(2)将多尺度Harris角点和SIFT描述子相结合,并通过对帧间变换模型参数进行鲁棒估计,保证了算法具有良好的旋转、尺度、亮度不变性和配准精度.实验结果表明,算法可在场景变化、图像大幅度平移、尺度缩放和任意角度旋转等复杂条件下实时、精确的进行图像配准,对分辨率为320×240的航拍序列的平均处理速度达到20.7帧/秒.     

Using binarization and hashing for efficient SIFT matching

The well-known SIFT is capable of extracting distinctive features for image retrieval. However, its matching is time consuming and slows down the entire process. In the SIFT matching, the Euclidean distance is used to measure the similarity of two features, which is expensive because it involves taking square root. Moreover, the scale of the image database is usually too large to adopt linear search for image retrieval. To improve the SIFT matching, this paper proposes a fast image retrieval scheme transforms the SIFT features to binary representations. The complexity of the distance calculation is reduced to bit-wise operation and the retrieval time is greatly decreased. Moreover, the proposed scheme utilizes hashing for retrieving similar images according to the binarized features and further speeds up the retrieval process. The experiment results show the proposed scheme can retrieve images efficiently with only a little sacrifice of accuracy as compared to SIFT.     

A novel watermarking scheme for H.264/AVC video authentication

As the H.264/AVC-based video products become more and more popular, issues of copyright protection and authentication that are appropriate for this standard will be very important. In this paper, a content-based authentication watermarking scheme for H.264/AVC video is proposed. Considering the new feature of H.264/AVC, the content-based authentication code for spatial tampering is firstly generated using the reliable features extracted from video frame blocks. The authentication code, which can detect malicious manipulations but allow recompression, is embedded into the DCT coefficients in diagonal positions using a novel modulation method. Spatial tampering can be located by comparing the extracted and the original feature-based watermarks. In addition, combining ECC and interleaving coding, the frame index of each video frame is used as watermark information and embedded in the residual coefficients. Temporal tampering can be detected by the mismatch between the extracted and the observed frame index. Experimental results show that the proposed scheme can discriminate the malicious tampering from the mild signal processing. The tampered location can also be approximately determined according to the glide window and the predefined threshold.     

基于尺度不变特征变换的快速景象匹配方法

传统基于特征的景象匹配方法存在冗余点多、匹配精度低等问题,难以同时满足实时性及鲁棒性要求,对此,论文提出一种基于尺度不变特征变换(SIFT)的快速景象匹配方法。在特征提取阶段,采用高速分段特征检测器(FAST)在多尺度检测角点作为初始特征,经过高斯差分(DOG)算子在尺度空间中进行特征的2次筛选,简化原有遍历式的特征搜索过程;在特征匹配阶段,采用仿射模型模拟变换关系建立几何约束条件,克服SIFT算法由于忽略几何信息而产生的误匹配。实验表明：该方法在匹配精度和实时性方面均优于SIFT算法,且对光照、模糊、尺度等变换具有良好的鲁棒性,能够更好地实现景象匹配。

     

边缘特征点序列图像无缝拼接方法的改进

为了将同一场景中具有重叠区域的序列图像合成一幅宽视角、高分辨率的图像,提出了一种结合尺度不变特征变换(SIFT)算法和Canny特征边缘提取的方法进行图像拼接。实验结果表明所提方法与SIFT算法相比,其参考特征点及待拼接特征点所需个数分别降低了26.56%和51.71%,匹配点对数降低51.65%,图像拼接用时降低了9.49%。此方法提高了图像拼接的精确性和实时性,能较好地解决图像间存在光照、旋转、尺度变换、仿射等问题,实现无人工干预的自动拼接。     

基于多特征融合的视频检索算法

随着视频等多媒体数据呈指数式迅猛增长,高效快速的视频检索算法引起越来越多的重视。传统的图像特征如颜色直方图以及尺度不变特征变换等对视频拷贝检测中检索速度以及检测精度等问题无法达到很好的效果,因此文中提出一种多特征融合的视频检索方法。该方法利用前后两帧的时空特征进行基于滑动窗口的时间对齐算法,以达到减少检索的范围和提高检索速度的目的。该算法对关键帧进行灰度序列特征、颜色相关图特征以及SIFT局部特征提取,然后融合全局特征和局部特征两者的优势,从而提高检测精度。实验结果表明,该方法可达到较好的视频检索精度。     

On-line video object segmentation using illumination-invariant color-texture feature extraction and marker prediction

A novel on-line video object segmentation scheme based on illumination-invariant color-texture feature extraction and marker prediction is proposed in this paper. First, the location of the object of interest is initialized based on user-specified markers. Superpixels are generated in the next available frame of the input video to extract the illumination-invariant color-texture features of the object of interest. The proposed object marker prediction scheme consists of estimating the user-specified markers and locating the object of interest in the next available frame via superpixel motion prediction using illumination-invariant optical flow, marker superpixel candidate generation using short-term superpixel affinity, and maximum likelihood computation using long-term superpixel affinity. The experimental results obtained when the proposed method is applied to several challenging video clips demonstrate that the proposed approach is competitive with several other state-of-the-art methods, especially when the illumination and object motion change dramatically.     

Analysis of BICM-ID Receivers Exploiting Transformations of Extrinsic Information

One of the key problems in the field of Computer Vision is recovering the geometry from multiple views of the same scene. Once the homography of two images is known, the motion of a stereo camera system can be determined, images can be rectified or image registration can be performed. A feature-based approach to determine the homography between two images bases on the extraction and matching of SIFT features (SIFT, Scale-Invariant Feature Transform). By extracting image features from varying images of one scene and finding corresponding image features in both images, the homography of the scene can be determined. The extraction of image features, which provide sufficient quality for computation of the homography of a scene, leads to an algorithm complexity, that prevents real-time applications on conventional CPUs. Therefore, we present and discuss an application-specific instruction-set extensions for a Tensilica Xtensa LX5 ASIP to accelerate a SIFT feature extraction (ASIP, Application-Specific Instruction-set Processor). In total, the complete SIFT feature extraction, executed on an extended processor is accelerated by a factor of x125 compared to the baseline processor. At the same time, the accuracy of the SIFT features is preserved. In addition, the proposed processor extensions maintain the full flexibility of an ASIP for a fast integration of further feature extractors.     

一种CSS-SIFT复合图像配准算法

针对SIFT算法的图像配准耗时长的问题,提出一种CSS-SIFT复合图像配准算法.CSS-SIFT算法首先使用CSS算法检测图像特征,然后,使用优化的SIFT算法生成并降维图像特征描述子,最后,使用基于欧式距离和曼哈顿距离的优化双向匹配算法对图像特征进行匹配.仿真实验条件是通过计算机中仿真软件进行仿真实验,统计图像特征...     

联合多尺度多特征的高分遥感图像场景分类

高分辨率遥感图像地物信息丰富,但场景构成复杂,目前基于手工设计的特征提取方法不能满足复杂场景分类的需求,而非监督特征学习方法尽管能够挖掘局部图像块的本征结构,但单一种类及尺度的特征难以有效表达实际应用中复杂遥感场景特性,导致分类性能受限.针对此问题,本文提出了一种基于多尺度多特征的遥感场景分类方法.该算法首先设计了一种改进的谱聚类非监督特征（iUFL-SC）以有效表征图像块的本征结构,然后通过密集采样提取每幅遥感场景的iUFL-SC、LBP、SIFT等三种多尺度局部图像块特征,并通过视觉词袋模型（BoVW）获得场景的中层特征表达,以实现更为准确详实的特征描述,最后基于直方图交叉核的支持向量机（HIKSVM）进行分类.在UC Merced数据集以及WHU-RS19数据集上的实验结果表明本文方法可对遥感场景进行鉴别特征提取,有效提高分类性能.     

Hash key-based video encryption scheme for H.264/AVC

An improved H.264/AVC comprehensive video encryption scheme is proposed. In the proposed scheme, the intra-prediction mode, motion vector difference, and quantization coefficients are encrypted. A novel hierarchical key generation method is likewise proposed, in which the encryption keys are generated based on the cryptographic hash function. Generated frame keys are consistent with the corresponding frame serial numbers, which can ensure frame synchronization in the decrypting process when frame loss occurs. This function provides the property that our scheme is secure against some special attacks for video, such as the frame regrouping attack and frame erasure attack. Our method not only avoids the distribution of encryption keys, but also increases the security. Experimental results show that the proposed scheme is efficient in computing, the encryption process does not affect the compression ratio greatly, and the encryption/decryption process hardly affects the video quality.     

Blind video quality assessment based on multilevel video perception

Blind video quality assessment (VQA) metrics predict the quality of videos without the presence of reference videos. This paper proposes a new blind VQA model based on multilevel video perception, abbreviated as MVP. The model fuses three levels of video features occurring in natural video scenes to predict video quality: natural video statistics (NVS) features, global motion features and motion temporal correlation features. They represent video scene characteristics, video motion types, and video temporal correlation variations. In the process of motion feature extraction, motion compensation filtering video enhancement is adopted to highlight the motion characteristics of videos so as to improve the perceptual correlations of the video features. The experimental results on the LIVE and CSIQ video databases show that the predicted video scores of the new model are highly correlated with human perception and have low root mean square errors. MVP obviously outperforms state-of-art blind VQA metrics, and particularly demonstrates competitive performance even compared against top-performing full reference VQA metrics.     

Robust semi-blind video watermarking based on frame-patch matching

In this paper, we present a frame-patch matching based robust semi-blind video watermarking using KAZE feature. The KAZE feature is employed for matching the feature points of frame-patch with those of all frames in video for detecting the embedding and extracting regions. In our method, the watermark information is embedded in Discrete Cosine Transform (DCT) domain of randomly generated blocks in the matched region. In the extraction process, we synchronize the embedded region from the distorted video by using KAZE feature matching. Based on the matched KAZE feature points, RST (rotation, scaling, translation) parameters are estimated and the watermark information can be successfully extracted. Experimental results show that our proposed method is robust against geometrical attacks, video processing attacks, temporal attacks, and so on.     

Low‐Power Video Decoding on a Variable Voltage Processor for Mobile Multimedia Applications

This paper proposes a novel low‐power video decoding scheme. In the encoded video bitstream, there is quite a large number of non‐coded blocks. When the number of the non‐coded blocks in a frame is known at the start of frame decoding, the workload of the video decoding can be estimated. Consequently, the supply voltage of very large‐scale integration (VLSI) circuits can be lowered, and the power consumption can be reduced. In the proposed scheme, the encoder counts the number of non‐coded blocks and stores this information in the frame header of the bitstream. Simulation results show that the proposed scheme reduces the power consumption to about 1/10 to 1/20.     

A robust blind watermarking algorithm for depth-image-based rendering 3D images

The protection of 3D contents from illegal distribution has attracted considerable attention and depth-image-based rendering (DIBR) is proved to be a promising technology for 3D image and video displaying. In this paper, we propose a new digital watermarking scheme for DIBR 3D images based on feature regions and ridgelet transform (RT). In this scheme, the center view and the depth map are made available at the content provider side. After selecting the reference points of the center view, we construct the feature regions for watermark embedding. Considering the sparse image representation and directional sensitivity of the RT, the watermark bits are embedded into the amplitudes of the ridgelet coefficients of the most energetic direction. The virtual left and virtual right views are generated from the watermarked center view and the associated depth map at the content consumer side. The watermarked view has good perceptual quality under both the objective and subjective image quality evaluations. The embedded watermark can be detected blindly with low bit error rate (BER) from the watermarked center view, the synthesized left and right views even when the views are distorted and distributed separately. The experimental results demonstrate that the proposed scheme exhibits good performance in terms of robustness against various image processing attacks. Meanwhile, our method can be robust to common DIBR processing, such as depth image variation, baseline distance adjustment and different rendering conditions. Furthermore, compared with other related and state-of-the-art methods, the proposed algorithm shows higher accuracy in watermark extraction.     

基于运动区域检测的会议视频清晰度增强处理

视频会议场景对视频增强的实时性有较高的要求.针对现有视频增强算法(如BM3D等)存在的耗时长的问题,基于变化区域检测提出一种基于运动区域检测的视频增强技术.对时序帧数据进行颜色空间转换,快速地将视频场景分为静止区域和运动区域,之后对静止区域进行时域降噪和视频增强.在视频帧集合的实验结果表明,该算法可以显著地增强图像纹理...     

Texture aided depth frame interpolation

Recent development of depth acquiring technique has accelerated the progress of 3D video in the market. Utilizing the acquired depth, arbitrary view frames can be generated based on depth image based rendering (DIBR) technique in free viewpoint video system. Different from texture video, depth sequence is mainly utilized for virtual view generation rather than viewing. Inspired by this, a depth frame interpolation scheme using texture information is proposed in this paper. The proposed scheme consists of a texture aided motion estimation (TAME) and texture aided motion compensation (TAMC) to fully explore the correlation between depth and the accompanying textures. The optimal motion vectors in TAME and the best interpolation weights in TAMC are respectively selected taking the geometric mapping relationship between depth and the accompanying texture frames into consideration. The proposed scheme is able to not only maintain the temporal consistency among interpolated depth sequence but also improve the quality of virtual frames generated by interpolated depth. Besides, it can be easily applied to arbitrary motion compensation based frame interpolation scheme. Experimental results demonstrate that the proposed depth frame interpolation scheme is able to improve the quality of virtual view texture frames in both subjective and objective criterions compared with existing schemes.     

视频检索中基于GMM聚类的无监督情感场景检测

为了高效地从视频中检索出激动人心的场面,提出了一种基于高斯混合模型的无监督情感场景检测方法.首先,从面部选取42个特征点,并定义10种面部特征;然后,利用高斯混合模型将视频的帧划分为多个聚类;最后,利用每一帧的面部表情分类结果将情感场景划分为单个聚类,并通过场景集成和删除完成检测.在生活记录视频和MMI人脸表情数据库上的实验结果表明,该方法的检测率、分类率分别高达98％,95％,检测5分钟左右的情感场景视频仅需0.138 s,性能优于几种较为先进的检测方法.     

Video scene characteristic detection to improve digital watermarking transparency

A new method of video scene content characteristic detection is proposed. This method can be applied in conjunction with digital watermarking schemes in order to improve the transparency. In addition, new methods of video watermarking are also proposed. Three related original aspects are reported. First, the authors' previous robust image watermarking methods, which consider the block texture are extended into video. In the detection process, watermark extraction with or without the original frame is provided. Secondly, a method is proposed to improve imperceptibility by reducing the flickering effect. Finally, a method is introduced to detect video scene characteristics in order to suit the particular embedding scheme. By doing so, the embedding method can be chosen adaptively in accordance with the video scene. The subjective tests illustrate an imperceptibility improvement and experiments with various attacks show the watermarking robustness.