Research on the Video Detection of Human Respiratory Motion Based on Sequential Images

Objective:Explore the feasibility of the high precision accelerometer for measuring the human respiratory displacement.Methods:A wireless acceleration acquisition system with the low power consumption and the high precision was designed with the high precision acceleration sensor ADXL355 as the core device.Based on the frequency characteristics of the breathing motion and the principle that the displacement can be calculated by the acceleration quadratic integration,two displacement measurement algorithms for the quasi-periodic weak motion are designed.Results:The simulation results show that the proposed algorithm is effective.The experimental results show that the designed acquisition system and algorithm can calculate the human respiratory displacement.Conclusion:The high precision accelerometer can be used to measure the human respiratory displacement,which provides a new method for the measurement of the human respiratory displacement.

RESEARCH ON KEY THECHNOLOGIES OF PORNOGRAPHIC IMAGE/VIDEO RECOGNITION IN COMPRESSED DOMAIN

Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc., are studied in compressed domain. A skin detection method based on data-mining in compressed domain is proposed firstly and achieves the higher detection accuracy as well as higher speed. Then, a cascade scheme of pornographic image recognition based on selective decision tree ensemble is proposed in order to improve both the speed and accuracy of recognition. A pornographic video oriented key frame extraction solution in compressed domain and an approach of pornographic video recognition are discussed respectively in the end.

Realtime Object Detection Through M-ResNet in Video Surveillance System

Object detection plays a vital role in the video surveillance systems.To enhance security,surveillance cameras are now installed in public areas such as traffic signals,roadways,retail malls,train stations,and banks.However,monitor-ing the video continually at a quicker pace is a challenging job.As a consequence,security cameras are useless and need human monitoring.The primary difficulty with video surveillance is identifying abnormalities such as thefts,accidents,crimes,or other unlawful actions.The anomalous action does not occur at a high-er rate than usual occurrences.To detect the object in a video,first we analyze the images pixel by pixel.In digital image processing,segmentation is the process of segregating the individual image parts into pixels.The performance of segmenta-tion is affected by irregular illumination and/or low illumination.These factors highly affect the real-time object detection process in the video surveillance sys-tem.In this paper,a modified ResNet model(M-Resnet)is proposed to enhance the image which is affected by insufficient light.Experimental results provide the comparison of existing method output and modification architecture of the ResNet model shows the considerable amount improvement in detection objects in the video stream.The proposed model shows better results in the metrics like preci-sion,recall,pixel accuracy,etc.,andfinds a reasonable improvement in the object detection.

An Efficient Method for Underwater Video Summarization and Object Detection Using YoLoV3

Currently,worldwide industries and communities are concerned with building,expanding,and exploring the assets and resources found in the oceans and seas.More precisely,to analyze a stock,archaeology,and surveillance,sev-eral cameras are installed underseas to collect videos.However,on the other hand,these large size videos require a lot of time and memory for their processing to extract relevant information.Hence,to automate this manual procedure of video assessment,an accurate and efficient automated system is a greater necessity.From this perspective,we intend to present a complete framework solution for the task of video summarization and object detection in underwater videos.We employed a perceived motion energy(PME)method tofirst extract the keyframes followed by an object detection model approach namely YoloV3 to perform object detection in underwater videos.The issues of blurriness and low contrast in underwater images are also taken into account in the presented approach by applying the image enhancement method.Furthermore,the suggested framework of underwater video summarization and object detection has been evaluated on a publicly available brackish dataset.It is observed that the proposed framework shows good performance and hence ultimately assists several marine researchers or scientists related to thefield of underwater archaeology,stock assessment,and surveillance.

MOTION-BASED REGION GROWING SEGMENTATION OF IMAGE SEQUENCES

This paper proposes a motion-based region growing segmentation scheme for the object-based video coding, which segments an image into homogeneous regions characterized by a coherent motion. It adopts a block matching algorithm to estimate motion vectors and uses morphological tools such as open-close by reconstruction and the region-growing version of the watershed algorithm for spatial segmentation to improve the temporal segmentation. In order to determine the reliable motion vectors, this paper also proposes a change detection algorithm and a multi-candidate pro- screening motion estimation method. Preliminary simulation results demonstrate that the proposed scheme is feasible. The main advantage of the scheme is its low computational load.

Video Based Vehicle Detection and its Application in Intelligent Transportation Systems

Video based vehicle detection technology is an integral part of Intelligent Transportation System (ITS), due to its non-intrusiveness and comprehensive vehicle behavior data collection capabilities. This paper proposes an efficient video based vehicle detection system based on Harris-Stephen corner detector algorithm. The algorithm was used to develop a stand alone vehicle detection and tracking system that determines vehicle counts and speeds at arterial roadways and freeways. The proposed video based vehicle detection system was developed to eliminate the need of complex calibration, robustness to contrasts variations, and better performance with low resolutions videos. The algorithm performance for accuracy in vehicle counts and speed was evaluated. The performance of the proposed system is equivalent or better compared to a commercial vehicle detection system. Using the developed vehicle detection and tracking system an advance warning intelligent transportation system was designed and implemented to alert commuters in advance of speed reductions and congestions at work zones and special events. The effectiveness of the advance warning system was evaluated and the impact discussed.

Detection of Objects in Motion—A Survey of Video Surveillance

Video surveillance system is the most important issue in homeland security field. It is used as a security system because of its ability to track and to detect a particular person. To overcome the lack of the conventional video surveillance system that is based on human perception, we introduce a novel cognitive video surveillance system (CVS) that is based on mobile agents. CVS offers important attributes such as suspect objects detection and smart camera cooperation for people tracking. According to many studies, an agent-based approach is appropriate for distributed systems, since mobile agents can transfer copies of themselves to other servers in the system.

Detection of oil spills in a complex scene of SAR imagery

We present a method for detecting oil spills in a complex scene of SAR imagery,including segmenting oil spills,and avoiding false alarms.Segmentation is carried out using a multi-time and multi-hierarchical method by dividing the complex sea surface into bright sea and dark sea.Gray-based and edge-based segmentations are done to extract oil spills from bright and dark sea,respectively.The proposed method can extract complete oil spills,obtain better visual results,and increase detection probability more accurately than the traditional method.Based on the surrounding features and the oil spills’features,dark land spots and low contrast dark spots are removed efficiently,thus reducing false alarms.The experimental results demonstrate that the proposed algorithm has fast computation speed,high detection accuracy,and is very useful and effective for detecting oil spills in SAR imagery.

A robust system for real-time pedestrian detection and tracking

A real-time pedestrian detection and tracking system using a single video camera was developed to monitor pedestrians. This system contained six modules: video flow capture, pre-processing, movement detection, shadow removal, tracking, and object classification. The Gaussian mixture model was utilized to extract the moving object from an image sequence segmented by the mean-shift technique in the pre-processing module. Shadow removal was used to alleviate the negative impact of the shadow to the detected objects. A model-free method was adopted to identify pedestrians. The maximum and minimum integration methods were developed to integrate multiple cues into the mean-shift algorithm and the initial tracking iteration with the competent integrated probability distribution map for object tracking. A simple but effective algorithm was proposed to handle full occlusion cases. The system was tested using real traffic videos from different sites. The results of the test confirm that the system is reliable and has an overall accuracy of over 85%.

Detecting Objectionable Videos

This paper addresses the problem of detecting objectionable videos, which has never been carefully studied before. Our method can be efficiently used to filter objectionable videos on Internet. One tensor based key-frame selection algorithm, one cube based color model and one objectionable video estimation algorithm are presented. The key frame selection is based on motion analysis using the three-dimensional structure tensor. Then the cube based color model is employed to detect skin color in each key frame. Finally, the video estimation algorithm is applied to estimate objectionable degree in videos. Experimental results on a variety of real-world videos downloaded from Internet show that this method is promising.

视频侦查技术关键及其发展展望

视频侦查技术的核心是通过视频图像的提取、查看、分析和研判来获取侦查线索、固定涉案证据。多年来经过在实战应用中不断地发展创新,视频侦查技术形成了自己独特的关键技术体系:视频信息分析解读技术是侦查应用和证据固定的基础和核心;视频证据固定保全技术的规范是审判中心主义的客观要求,可以获取视频侦查记录报告、视频检验鉴定报告或视频数据关联报告;低质量视频图像的增强恢复技术专业性强,应用范围窄,技术成熟度高,然而它不断面临新的挑战。目前,视频数据的智能应用在大数据背景下变得越来越重要,仍需进一步突破视频自动识别技术的应用范畴,建立完善多层次的视频数据综合应用体系,打造适应不同业务需要的视频数据实战应用模型。

边缘异常识别下视频图像篡改细节检测

视频图像不同栅格位置或不同压缩区域被合成为篡改图像时会出现特征块效应的差异,改变原视频的关键信息。为了准确识别图像中被篡改的像素点,提出基于边缘异常识别的视频图像篡改检测方法。通过离散余弦变换,将能量全部集中到图像的低频系数内,描述出视频的边缘等细节。利用能量比与频域熵间关系得出图像中能量的可疑度,结合预测掩膜概率图划分出发生篡改的位置区域。利用Sobel边缘检测边缘点,量化边缘点特征判断出边缘是否异常,当出现异常对其跟踪直至目标消失,检测出视频图像中的篡改位置区域。实验结果表明,所提方法能够精准检测出视频图像被篡改位置,且耗时低于1ms,应用优势显著。

机器视觉中角点检测算法研究

角点检测是运动检测、图像匹配、视频跟踪、三维重建和目标识别等必不可少的关键步骤,角点检测的准确性直接影响实验结果;为了更好地了解角点检测技术的发展现状,根据3种现有的角点检测方法分类对角点检测方法及相关改进进行了总结分析,并选择了FAST、SUSAN、SIFT、Shi-Tomas这几种较为典型的角点检测算法进行了实验对比,并给出了实验结果;不同的实际应用对角点检测的要求不同,不同的角点检测算法也可以相互结合,通过对现有角点检测技术的总结分析为在实际应用中对角点检测技术的选择和改进方向提供了借鉴和参考。

基于时空流特征融合的俯视视角下奶牛跛行自动检测方法

[目的/意义]奶牛跛行检测是规模化奶牛养殖过程中亟待解决的重要问题,现有方法的检测视角主要以侧视为主。然而,侧视视角存在着难以消除的遮挡问题。本研究主要解决侧视视角下存在的遮挡问题。[方法]提出一种基于时空流特征融合的俯视视角下奶牛跛行检测方法。首先,通过分析深度视频流中跛行奶牛在运动过程中的位姿变化,构建空间流特征图像序列。通过分析跛行奶牛行走时躯体前进和左右摇摆的瞬时速度,利用光流捕获奶牛运动的瞬时速度,构建时间流特征图像序列。将空间流与时间流特征图像组合构建时空流融合特征图像序列。其次,利用卷积块注意力模块(Convolutional Block Attention Module, CBAM)改进PP-TSMv2 (PaddlePaddle-Temporal Shift Module v2)视频动作分类网络,构建奶牛跛行检测模型Cow-TSM (Cow-Temporal Shift Module)。最后,分别在不同输入模态、不同注意力机制、不同视频动作分类网络和现有方法 4个方面对比,进行奶牛跛行实验,以探究所提出方法的优劣性。[结果和讨论]共采集处理了180段奶牛图像序列数据,跛行奶牛与非跛行奶牛视频段数比例为1∶1,所提出模型识别精度达到88.7%,模型大小为22 M,离线推理时间为0.046 s。与主流视频动作分类模型TSM、PP-TSM、PP-TSMv2、SlowFast和TimesFormer模型相比,综合表现最好。同时,以时空流融合特征图像作为输入时,识别精度分别比单时间模态与单空间模态分别提升12%与4.1%,证明本研究中模态融合的有效性。通过与通道注意力(Squeeze-and-Excitation, SE)、卷积核注意力(Selective Kernel, SK)、坐标注意力(Coordinate Attention, CA)与CBAM不同注意力机制进行消融实验,证明利用CBAM注意力机制构建奶牛跛行检测模型效果最佳。最后,与现有跛行检测方法进行对比,所提出的方法同时具有较好的性能和实用性。[结论]本研究能够避免侧视视角下检测跛行奶牛时出现的遮挡问题,对于减少奶牛跛行发生率、提高牧场经济效益具有重要意义,符合牧场规模化建设的需求。

基于多任务学习的视频和图像显著目标检测方法

显著目标检测(Salient Object Detection,SOD)能够模拟人类的注意力机制,在复杂的场景中快速发现高价值的显著目标,为进一步的视觉理解任务奠定了基础。当前主流的图像显著目标检测方法通常基于DUTS-TR数据集进行训练,而视频显著目标检测方法(Video Salient Object Detection,VSOD)基于DAVIS,DAVSOD以及DUTS-TR数据集进行训练。图像和视频显著目标检测任务既有共性又有特性,因此需要部署独立的模型进行单独训练,这大大增加了运算资源和训练时间的开销。当前研究大多针对单个任务提出独立的解决方案,而缺少统一的图像和视频显著目标检测方法。针对上述问题,提出了一种基于多任务学习的图像和视频显著目标检测方法,旨在构建一种通用的模型框架,通过一次训练同时适配两种任务,并进一步弥合图像和视频显著目标检测方法之间的性能差异。12个数据集上的定性和定量实验结果表明,所提方法不仅能够同时适配两种任务,而且取得了比单任务模型更好的检测结果。

改进Faster R-CNN的视频SAR动目标检测算法

针对当前可用于深度学习的视频SAR数据稀少的现状,以及动目标检测算法中存在较多的漏检和虚警问题,基于美国桑迪亚国家实验室真实视频SAR数据制作深度学习数据集,提出一种改进Faster R-CNN的视频SAR动目标检测算法。算法以截取后的ResNet50为特征提取网络,利用K-means加遗传算法自适应计算锚框,并在数据预处理环节加入S型曲线增强方法,来增强图像的对比度信息。经实验验证,所提出方法能够显著提升动目标检测率和检测速度,其中,平均精度(AP)和F1分数提升均达到10个点以上,有效降低了虚警和漏检,整体表现优于一阶段算法SSD和RetinaNet。

基于视频图像分析的行人遇袭安全预警监测技术研究

在对行人身体的攻击发生之前,提前发现早期潜在攻击威胁可减少暴力事件的发生。为实现该目的,提出了基于视频图像分析的自动威胁行为检测新方法,通过该方法,可在行人身体接触发生之前产生潜在攻击威胁的早期预警,即当攻击者离受害者还有一段距离时,就可以检测到潜在的威胁,从而实现预警生成。为验证所提出的算法在攻击威胁检测中的有效性,将其性能与3种方法进行了对比。对比结果表明,与所对比方法相比,所提出的方法对攻击威胁检测的准确率更高。

基于双边截断的双参数海上风电站SAR图像CFAR检测

文章提出了1种基于双边截断的双参数海上风电站SAR图像CFAR检测器DTCS-TPCFAR,目的是提高在具有多个目标海上区域和石油泄漏区域等环境下对海上风电站的检测性能。DTCS-TPCFAR所提出的双边截断杂波的方法,能够同时消除高强度和低强度异常值的干扰,同时保留真实的杂波样本。通过使用最大似然估计计算双边截断后样本的均值和标准差,然后通过这2个参数估计值计算出截断阈值,最后再结合指定的虚警率(Probability of False Alarm,PFA)来对测试单元(Test Cell,TC)进行判断,完成最终的目标检测。这也是首次将CFAR检测器用于检测海上风电站。文章通过Sentinel-1数据集来验证该方法的有效性。实验结果表明,文章所提出的算法在相同指定虚警率下,具有更高的检测率(Detection Rate,DR)和更低的误报率(False Alarm Rate,FAR)。

基于动态特征融合的监控视频图像小目标检测研究

在实际监控场景中,监控视频图像往往会受到复杂的背景干扰和光照变化的影响,使得小目标的检测变得非常困难且准确性较差。因此,文章提出基于动态特征融合的监控视频图像小目标检测方法。首先对监控视频图像进行预处理,主要是对不同类型的噪声进行噪声滤除操作,以提高图像质量并突出小目标;其次融合数学形态学处理技术,提取预处理后图像的小目标相关特征;最后采用动态特征融合方式进行小目标检测,将多个特征融合在一起,以更全面地描述图像中的小目标。通过这种动态特征融合方法完成了监控视频图像小目标检测方法设计。实验结果表明:新方法在检测不同类型的小目标中具有明显优势,能够实现对小目标的准确监测,说明其在监控视频图像小目标检测中具有应用价值。

SAR图像中舰船目标恒虚警率检测技术的研究

在各种各样的合成孔径雷达图像舰船目标检测方法中,应用最广泛、最重要的就是具有自适应阈值的恒虚警率(CFAR)检测器。为了提高SAR图像中舰船目标的检测性能,人们试图通过各种统计分布模型对SAR图像中的杂波背景进行统计建模,如Gamma分布、K分布、对数正态分布、G0分布、alpha稳定分布等,再通过相应的统计分布模型以及各种样本筛选技术的CFAR检测器对舰船目标实施检测。SAR图像中杂波背景是复杂多变的,当实际杂波背景与假定统计分布失配时,参量型CFAR检测器的性能会恶化,非参数CFAR检测器就会显示出优势。该文提出了基于Wilcoxon非参数检测器的新途径对SAR图像中舰船目标进行检测,并在Radarsat-2,ICEYE-X6和Gaofen-3卫星的实测数据上,与几种典型的参量型CFAR检测方法进行了对比。实验结果表明,Wilcoxon非参数检测方法在这3种实测数据上的虚警控制能力具有良好的鲁棒性,还可以带来弱目标检测性能的改善,具有运算速度快、易于硬件实现的特点。