A two-step face hallucination approach for video surveillance applications

Multimedia Tools and Applications - In this paper we propose a novel face hallucination algorithm to synthesize a high-resolution face image from several low-resolution input face images. Face...     

A deep learning approach to building an intelligent video surveillance system

Recent advances in the field of object detection and face recognition have made it possible to develop practical video surveillance systems with embedded object detection and face recognition functionalities that are accurate and fast enough for commercial uses. In this paper, we compare some of the latest approaches to object detection and face recognition and provide reasons why they may or may not be amongst the best to be used in video surveillance applications in terms of both accuracy and speed. It is discovered that Faster R-CNN with Inception ResNet V2 is able to achieve some of the best accuracies while maintaining real-time rates. Single Shot Detector (SSD) with MobileNet, on the other hand, is incredibly fast and still accurate enough for most applications. As for face recognition, FaceNet with Multi-task Cascaded Convolutional Networks (MTCNN) achieves higher accuracy than advances such as DeepFace and DeepID2+ while being faster. An end-to-end video surveillance system is also proposed which could be used as a starting point for more complex systems. Various experiments have also been attempted on trained models with observations explained in detail. We finish by discussing video object detection and video salient object detection approaches which could potentially be used as future improvements to the proposed system.

     

A pixel-based outlier-free motion estimation algorithm for scalable video quality enhancement

Scalable video quality enhancement refers to the process of enhancing low quality frames using high quality ones in scalable video bitstreams with time-varying qualities. A key problem in the enhancement is how to search for correspondence between high quality and low quality frames. Previous algorithms usually use block-based motion estimation to search for correspondences. Such an approach can hardly estimate scale and rotation transforms and always introduces outliers to the motion estimation results. In this paper, we propose a pixel-based outlier-free motion estimation algorithm to solve this problem. In our algorithm, the motion vector for each pixel is calculated with respect to estimate translation, scale, and rotation transforms. The motion relationships between neighboring pixels are considered via the Markov random field model to improve the motion estimation accuracy. Outliers are detected and avoided by taking both blocking effects and matching percentage in scaleinvariant feature transform field into consideration. Experiments are conducted in two scenarios that exhibit spatial scalability and quality scalability, respectively. Experimental results demonstrate that, in comparison with previous algorithms, the proposed algorithm achieves better correspondence and avoids the simultaneous introduction of outliers, especially for videos with scale and rotation transforms.     

A security framework for cloud-based video surveillance system

Multimedia Tools and Applications - Utilizing cloud services in running large-scale video surveillance systems is not uncommon. However, special attention should be given to data security and...     

基于支持向量机的监控视频遮挡树叶检测

针对安防监控摄像头被树叶遮挡的问题,提出一种基于支持向量机(SVM)的视频树叶遮挡检测算法。该算法利用视频的时域特性,采用累积帧差法实现对视频中疑似树叶区域的分割,提取视频中某一帧图像的整个区域和疑似树叶区域的颜色信息与面积信息作为视频的特征,最后采用支持向量机进行建模并用于视频树叶遮挡的检测。在有限样本前提下,算法准确率能够达到84%。实验结果表明,所提算法对于有树叶遮挡的监控视频能够进行有效识别。     

A method of video image enhancement

A new method of image enhancement that allows improving the quality of required image details is proposed. To enhance local contrasts, a special transformation function is submitted. By the example of enhancement of a video-shot image of a car, we show the efficiency of the proposed technique in comparison with known methods of contrast enhancement.     

一种基于聚类的主持人镜头检测算法

随着数字视频的广泛应用,视频数据库系统已成为基于内容的视频检索领域的一个研究热点.在建立视频数据库的过程中,主持人镜头的检测是一个重要而又难以解决的问题.本文先在镜头级别对视频提取一系列的时域和空域特征,如人脸特征,彩色纹理特征,镜头时间长度等.然后综合采用决策树和聚类分析方法对镜头分类,判断镜头中是否有主持人,从而实现主持人镜头的检测.实验表明,采用本文提出的算法,准确率可达98.7%,同时查全率为95.2%,较好的解决了这一问题.     

An energy-efficient storage for video surveillance

With the rapid growth of the video surveillance applications, the storage energy consumption of video surveillance is more noticeable, but existed energy-saving methods for massive storage system most concentrate on the data centers mainly with random accesses. The storage of video surveillance has inherent access pattern, and requires special energy-saving approach to save more energy. An energy-efficient data layout for video surveillance, Semi-RAID is proposed. It adopts partial-parallelism strategy, which partitions disk data into different groups, and implements parallel accesses in each group. Grouping benefits to realize only partial disks working and the rest ones idle, and inner-group parallelism provides the performance guarantee. In addition, greedy strategy for address allocation is adopted to effectively prolong the idle period of the disks; particular Cache strategies are used to filter the small amount of random accesses. The energy-saving efficiency of Semi-RAID is verified by a simulated video surveillance consisting of 32 cameras with D1 resolution. The experiment shows: Semi-RAID can save 45 % energy than Hibernator; 80 % energy than PARAID; 33 % energy than MAID; 79 % energy than eRAID-5, while providing single disk fault tolerance and meeting the performance requirement, such as throughput.     

Big data analytics for video surveillance

This article addresses the usage and scope of Big Data Analytics in video surveillance and its potential application areas. The current age of technology provides the users, ample opportunity to generate data at every instant of time. Thus in general, a tremendous amount of data is generated every instant throughout the world. Among them, amount of video data generated is having a major share. Education, healthcare, tours and travels, food and culture, geographical exploration, agriculture, safety and security, entertainment etc., are the key areas where a tremendous amount of video data is generated every day. A major share among it are taken by the daily used surveillance data captured from the security purpose camera and are recorded everyday. Storage, retrieval, processing, and analysis of such gigantic data require some specific platform. Big Data Analytics is such a platform, which eases this analysis task. The aim of this article is to investigate the current trends in video surveillance and its applications using Big Data Analytics. It also aims to focus on the research opportunities for visual surveillance in Big Data frameworks. We have reported here the state-of-the-art surveillance schemes for four different imaging modalities: conventional video scene, remotely sensed video, medical diagnostics, and underwater surveillance. Several works were reported in this research field over recent years and are categorized based on the challenges solved by the researchers. A list of tools used for video surveillance using Big Data framework is presented. Finally, research gaps in this domain are discussed.

     

视频监控场景下的面部遮挡检测

提出了一种监控场景下的面部遮挡检测方法。基于AdaBoost算法进行人脸验证,通过面部划分,分块分析是否存在遮挡情况。首先判断是否有人进入,在有人进入的情况下进行面部遮挡检测,对眼部区域采用AdaBoost方法及墨镜特征提取方法判断是否遮挡,而对嘴部区域采用高斯肤色模型进行判断。实验结果表明,该方法能实时检测面部遮挡的情况,并达到了较好的效果,适用于银行ATM等监控场景,具有较高的应用价值。     

背景重建在视频监视系统中的应用

利用FPGA和USB控制芯片实现了实时视频监视采集系统,根据视频监视和传输特点,将采集得到的图像数据先做背景重建,然后利用重建得到的背景进行视频对象分割,最后将重建的背景、视频对象以及视频对象在视频图像中的位置保存,作为后续视频检测分析的依据.实验结果表明本文给出的背景重建算法能够较好地重建背景,得到较精确的运动目标,同时能够大幅度的提高实时视频对象分割速率.     

背景重建在视频监视系统中的应用

利用FPGA和USB控制芯片实现了实时视频监视采集系统,根据视频监视和传输特点,将采集得到的图像数据先做背景重建,然后利用重建得到的背景进行视频对象分割,最后将重建的背景、视频对象以及视频对象在视频图像中的位置保存,作为后续视频检测分析的依据。实验结果表明本文给出的背景重建算法能够较好地重建背景,得到较精确的运动目标,同时能够大幅度的提高实时视频对象分割速率。     

Quality-based fusion of multiple video sensors for video surveillance.

In this correspondence, we address the problem of fusing data for object tracking for video surveillance. The fusion process is dynamically regulated to take into account the performance of the sensors in detecting and tracking the targets. This is performed through a function that adjusts the measurement error covariance associated with the position information of each target according to the quality of its segmentation. In this manner, localization errors due to incorrect segmentation of the blobs are reduced thus improving tracking accuracy. Experimental results on video sequences of outdoor environments show the effectiveness of the proposed approach.     

An improved surveillance video synopsis framework: a HSATLBO optimization approach

Video surveillance cameras capture huge amount of data 24 hours a day. However, most of these videos contain redundant data which make the process difficult for browsing and analysis. A significant amount of research findings have been made in summarization of recorded video, but such schemes do not have much impact on video surveillance applications. On the contrary, video synopsis is a smart technology that preserves all the activities of every single object and projects them concurrently in a condensed time. The energy minimization module in video synopsis framework plays a vital role, which in turn minimizes the activity loss, number of collision and temporal consistency cost. In most of the reported schemes, Simulated Annealing (SA) algorithm is employed to solve the energy minimization problem. However, it suffers from slow convergence rate resulting in a high computational load to the system. In order to mitigate this issue, this article presents an improved energy minimization scheme using hybridization of SA and Teaching Learning based Optimization (TLBO) algorithms. The suggested framework for static surveillance video synopsis generation consists of four computational modules, namely, Object detection and segmentation, Tube formation, Optimization, and finally Stitching and the central focus is on the optimization module. Thus, the present work deals with an improved hybrid energy minimization problem to achieve global optimal solution with reduced computational time. The motivation behind hybridization (HSATLBO) is that TLBO algorithm has the ability to search rigorously, ensuring to reach the optimum solution with less computation. On the contrary, SA reaches the global optimum solution, but it may get disarrayed and miss some critical search points. Exhaustive experiments are carried out and results compared with that of benchmark schemes in terms of minimizing the activity, collision and temporal consistency costs. All the experiments are conducted on five widely used videos taken from standard surveillance video data set (PETS 2001, MIT Surveillance Dataset, ChangeDetection.Net, PETS 2006 and UMN Dataset) as well as one real generated surveillance video from the IIIT Bhubaneswar Surveillance Dataset. To make a fair comparison, additionally, performance of the proposed hybrid scheme to solve video synopsis optimization problem is also compared with that of the other benchmark functions. Experimental evaluation and analysis confirm that the proposed scheme outperforms other state-of-the-art approaches. Finally, the suggested scheme can be easily and reliably deployed in the off-line video synopsis generation.

     

A template-based approach to automatic face enhancement

This paper presents Visual ENhancement of USers (VENUS), a system able to automatically enhance male and female frontal facial images exploiting a database of celebrities as reference patterns for attractiveness. Each face is represented by a set of landmark points that can be manually selected or automatically localized using active shape models. The faces can be compared remapping the landmarks by means of Catmull–Rom splines, a class of interpolating splines particularly useful to extract shape-based representations. Given the input image, its landmarks are compared against the known beauty templates and moved towards the K-nearest ones by 2D image warping. The VENUS performances have been evaluated by 20 volunteers on a set of images collected during the Festival of Creativity, held in Florence, Italy, on October 2007. The experiments show that the 73.9% of the beautified faces are more attractive than the original pictures.     

Logistic视频字幕增强模型

目的：为提高复杂背景下的视频字幕在OCR中的识别率,需要对提取的视频字幕进行有效地字幕增强。该文首次将Logistic模型应用到视频字幕增强中,提出了基于Logistic模型的融合多帧信息的视频字幕增强方法。方法：对字幕进行检测与跟踪,将出现在连续多帧中的同一字幕片段进行对齐;通过分析字幕片段在多帧中信息,提出字幕背景在时域上的变化特征、背景和字幕文本的固有特征,并将三个特征进行量化与融合,构建适用于字幕增强的Logistic模型,实现对视频字幕的增强。结果：对含阴影或描边效果的特殊复杂背景字幕、普通复杂背景字幕、单一背景字幕分别进行实验,增强后的字幕在OCR软件中的识别正确率分别为81.76%、97.13%、98.19%,与对比方法比较均有一定的提高。结论：实验结果表明,该文方法既可以降低字幕背景的复杂度,又可以提高字幕背景与文本的对比度,从而可以对复杂背景和单一背景下的视频字幕进行有效地增强。     

A multi-processor NoC-based architecture for real-time image/video enhancement

The paper presents a multi-processor architecture for real-time and low-power image and video enhancement applications. Differently from other state-of-the-art parallel architectures the proposed solution is composed of heterogeneous tiles. The tiles have computational and memory capabilities, support different algorithmic classes and are connected by a novel Network-on-Chip (NoC) infrastructure. The proposed packet-switched data transfer scheme avoids communication bottlenecks when more tiles are working concurrently. The functional performances of the NoC-based multi-processor architecture are assessed by presenting the achieved results when the platform is programmed to support different enhancement algorithms for still images or videos. The implementation complexity of the NoC-based multi-tile platform, integrated in 65 nm CMOS technology, is reported and discussed.