A semantic unit based event detection scheme in soccer videos is proposed in this paper.The scheme can be characterized as a three-layer framework. At the lowest layer, low-level featuresincluding color, texture, edge...A semantic unit based event detection scheme in soccer videos is proposed in this paper.The scheme can be characterized as a three-layer framework. At the lowest layer, low-level featuresincluding color, texture, edge, shape, and motion are extracted. High-level semantic events aredefined at the highest layer. In order to connect low-level features and high-level semantics, wedesign and define some semantic units at the intermediate layer. A semantic unit is composed of asequence of consecutives frames with the same cue that is deduced from low-level features. Based onsemantic units, a Bayesian network is used to reason the probabilities of events. The experiments forshoot and card event detection in soccer videos show that the proposed method has an encouragingperformance.展开更多
BACKGROUND: Airway management in intensive care unit(ICU) patients is challenging. The aim of this study was to compare the rate of successful first-pass intubation in the ICU by using the direct laryngoscopy(DL) and ...BACKGROUND: Airway management in intensive care unit(ICU) patients is challenging. The aim of this study was to compare the rate of successful first-pass intubation in the ICU by using the direct laryngoscopy(DL) and that by using the video laryngoscopy(VL).METHODS: A randomized, non-blinded trial comparing first-pass success rate of intubation between VL and DL was performed. Patients were recruited in the period from August 2014 to August 2016. All physicians working at ICU received hands-on training in the use of the video and direct laryngoscope. The primary outcome measure was the first-pass intubation success. RESULTS: A total of 163 ICU patients underwent intubation during the study period(81 patients in VL group and 82 in DL group). The rate of successful first-pass intubation was not significantly different between the VL and the DL group(67.9% vs. 69.5%, P=0.824). Moreover, the overall intubation success and total number of attempts to achieve intubation success did not differ between the two groups. In patients with successful first-pass intubation, the median duration of the intubation procedure did not differ between the two groups. The Cormack-Lehane grades and the percentage of glottic opening score were similar, and no significant differences were found between the two groups. There were no statistical differences between the VL and the DL group in intubation complications(all P>0.05). CONCLUSION: Among ICU patients requiring intubation, there was no significant difference in the rate of successful first-pass intubation between VL and DL.展开更多
In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. ...In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.展开更多
针对通用视频编码(versatile video coding,VVC)在编码单元(coding unit,CU)划分中引入了多类型树划分结构导致编码复杂度增加的问题,提出了一种基于CU子块方向特性与空间复杂度的快速划分算法。首先利用CU整体的纹理复杂度对当前CU进...针对通用视频编码(versatile video coding,VVC)在编码单元(coding unit,CU)划分中引入了多类型树划分结构导致编码复杂度增加的问题,提出了一种基于CU子块方向特性与空间复杂度的快速划分算法。首先利用CU整体的纹理复杂度对当前CU进行分类,筛选出不划分CU;然后利用子块不同划分方向的特性差异提前决策CU划分方向;最后利用CU中间区域与边缘区域的复杂度差异特征判断是否跳过三叉树(ternary tree,TT)划分,进一步减少候选列表划分模式数量。实验结果表明,与官方测试平台VTM10.0相比,编码器在平均输出比特率增加1.12%的代价下,编码时间减少了40.25%,说明该算法在通用视频编码中能以较小的质量损失实现更短的编码时间。展开更多
A non-photorealistic rendering technique is a method to show various effects different from those of realistic image generation.Of the various techniques,flow-based image abstraction displays the shape and color featu...A non-photorealistic rendering technique is a method to show various effects different from those of realistic image generation.Of the various techniques,flow-based image abstraction displays the shape and color features well and performs a stylistic visual abstraction.But real-time rendering is impossible when CPU is used because it applies various filtering and iteration methods.In this paper,we present real-time processing methods of video abstraction using open open computing language(OpenCL),technique of general-purpose computing on graphics processing units(GPGPU).Through the acceleration of general-purpose computing(GPU),16 frame-per-second(FPS)or greater is shown to process video abstraction.展开更多
目的系统评价视频探视在重症监护病房(ICU)中的应用效果。方法计算机检索中国知网、万方数据库、维普数据库、PubMed、EMbase、the Cochrane Library、Web of Science数据库中有关视频探视的随机对照研究、非随机对照研究与队列研究,检...目的系统评价视频探视在重症监护病房(ICU)中的应用效果。方法计算机检索中国知网、万方数据库、维普数据库、PubMed、EMbase、the Cochrane Library、Web of Science数据库中有关视频探视的随机对照研究、非随机对照研究与队列研究,检索时限为各数据库建库至2023年2月。由2名研究者依据纳入与排除标准独立筛选文献、提取数据并对纳入文献进行质量评价,采用RevMan5.4软件进行Meta分析。结果最终纳入13个研究。Meta分析结果显示,视频探视组探视后患者焦虑评分变化值(SMD=0.09,95%CI:-0.60~0.78,P=0.79)、患者焦虑发生率(RR=0.52,95%CI:0.11~2.45,P=0.40)、家属焦虑评分(SMD=-0.22,95%CI:-0.69~0.26,P=0.37)、家属焦虑发生率(RR=1.11,95%CI:0.75~1.65,P=0.60)、病房空气细菌培养合格率(RR=1.04,95%CI:0.95~1.14,P=0.39)与非视频探视组比较差异无统计学意义,患者满意率(RR=1.35,95%CI:1.11~1.63,P=0.002)、家属满意度评分(SMD=0.34,95%CI:0.22~0.46,P<0.001)、家属满意率(RR=1.29,95%CI:1.22~1.35,P<0.001)、病房物表采样细菌培养合格率(RR=4.18,95%CI:3.32~5.27,P<0.001)显著高于非视频探视组,患者谵妄发生率(RR=0.71,95%CI:0.54~0.95,P=0.02)、患者感染率(RR=0.35,95%CI:0.15~0.85,P=0.02)显著低于非视频探视组。结论现有证据表明,视频探视减缓ICU患者及家属焦虑情绪的效果与非视频探视相当;视频探视较非视频探视能显著提升ICU患者及家属满意率,显著降低ICU患者谵妄发生率及感染风险。展开更多
高效视频编码(High Efficiency Video Coding,HEVC)作为下一代新的视频编码标准,旨在有限网络带宽下传输高质量的网络视频。与现有的视频编码标准相比,高效视频编码具有更高的灵活性和压缩率。编码单元(Coding Unit,CU)是视频编码处理...高效视频编码(High Efficiency Video Coding,HEVC)作为下一代新的视频编码标准,旨在有限网络带宽下传输高质量的网络视频。与现有的视频编码标准相比,高效视频编码具有更高的灵活性和压缩率。编码单元(Coding Unit,CU)是视频编码处理的基本单元,原有的算法通过四叉树递归获取最佳CU深度,在提高视频压缩性能的同时引入了较高的计算复杂度。针对该问题,提出了一种快速编码深度选择算法,该算法利用相邻CU的深度信息计算一个深度预测特征值,通过该特征值进行深度选择,以避免不必要的计算,降低计算复杂度。实验结果表明,该算法在保证视频压缩效果的同时有效降低了计算复杂度。展开更多
文摘A semantic unit based event detection scheme in soccer videos is proposed in this paper.The scheme can be characterized as a three-layer framework. At the lowest layer, low-level featuresincluding color, texture, edge, shape, and motion are extracted. High-level semantic events aredefined at the highest layer. In order to connect low-level features and high-level semantics, wedesign and define some semantic units at the intermediate layer. A semantic unit is composed of asequence of consecutives frames with the same cue that is deduced from low-level features. Based onsemantic units, a Bayesian network is used to reason the probabilities of events. The experiments forshoot and card event detection in soccer videos show that the proposed method has an encouragingperformance.
文摘BACKGROUND: Airway management in intensive care unit(ICU) patients is challenging. The aim of this study was to compare the rate of successful first-pass intubation in the ICU by using the direct laryngoscopy(DL) and that by using the video laryngoscopy(VL).METHODS: A randomized, non-blinded trial comparing first-pass success rate of intubation between VL and DL was performed. Patients were recruited in the period from August 2014 to August 2016. All physicians working at ICU received hands-on training in the use of the video and direct laryngoscope. The primary outcome measure was the first-pass intubation success. RESULTS: A total of 163 ICU patients underwent intubation during the study period(81 patients in VL group and 82 in DL group). The rate of successful first-pass intubation was not significantly different between the VL and the DL group(67.9% vs. 69.5%, P=0.824). Moreover, the overall intubation success and total number of attempts to achieve intubation success did not differ between the two groups. In patients with successful first-pass intubation, the median duration of the intubation procedure did not differ between the two groups. The Cormack-Lehane grades and the percentage of glottic opening score were similar, and no significant differences were found between the two groups. There were no statistical differences between the VL and the DL group in intubation complications(all P>0.05). CONCLUSION: Among ICU patients requiring intubation, there was no significant difference in the rate of successful first-pass intubation between VL and DL.
基金This work was supported by Foundation of Technology Supporting the Creation of Digital Media Contents project (CREST, JST), Japan
文摘In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.
文摘针对通用视频编码(versatile video coding,VVC)在编码单元(coding unit,CU)划分中引入了多类型树划分结构导致编码复杂度增加的问题,提出了一种基于CU子块方向特性与空间复杂度的快速划分算法。首先利用CU整体的纹理复杂度对当前CU进行分类,筛选出不划分CU;然后利用子块不同划分方向的特性差异提前决策CU划分方向;最后利用CU中间区域与边缘区域的复杂度差异特征判断是否跳过三叉树(ternary tree,TT)划分,进一步减少候选列表划分模式数量。实验结果表明,与官方测试平台VTM10.0相比,编码器在平均输出比特率增加1.12%的代价下,编码时间减少了40.25%,说明该算法在通用视频编码中能以较小的质量损失实现更短的编码时间。
文摘A non-photorealistic rendering technique is a method to show various effects different from those of realistic image generation.Of the various techniques,flow-based image abstraction displays the shape and color features well and performs a stylistic visual abstraction.But real-time rendering is impossible when CPU is used because it applies various filtering and iteration methods.In this paper,we present real-time processing methods of video abstraction using open open computing language(OpenCL),technique of general-purpose computing on graphics processing units(GPGPU).Through the acceleration of general-purpose computing(GPU),16 frame-per-second(FPS)or greater is shown to process video abstraction.
文摘目的系统评价视频探视在重症监护病房(ICU)中的应用效果。方法计算机检索中国知网、万方数据库、维普数据库、PubMed、EMbase、the Cochrane Library、Web of Science数据库中有关视频探视的随机对照研究、非随机对照研究与队列研究,检索时限为各数据库建库至2023年2月。由2名研究者依据纳入与排除标准独立筛选文献、提取数据并对纳入文献进行质量评价,采用RevMan5.4软件进行Meta分析。结果最终纳入13个研究。Meta分析结果显示,视频探视组探视后患者焦虑评分变化值(SMD=0.09,95%CI:-0.60~0.78,P=0.79)、患者焦虑发生率(RR=0.52,95%CI:0.11~2.45,P=0.40)、家属焦虑评分(SMD=-0.22,95%CI:-0.69~0.26,P=0.37)、家属焦虑发生率(RR=1.11,95%CI:0.75~1.65,P=0.60)、病房空气细菌培养合格率(RR=1.04,95%CI:0.95~1.14,P=0.39)与非视频探视组比较差异无统计学意义,患者满意率(RR=1.35,95%CI:1.11~1.63,P=0.002)、家属满意度评分(SMD=0.34,95%CI:0.22~0.46,P<0.001)、家属满意率(RR=1.29,95%CI:1.22~1.35,P<0.001)、病房物表采样细菌培养合格率(RR=4.18,95%CI:3.32~5.27,P<0.001)显著高于非视频探视组,患者谵妄发生率(RR=0.71,95%CI:0.54~0.95,P=0.02)、患者感染率(RR=0.35,95%CI:0.15~0.85,P=0.02)显著低于非视频探视组。结论现有证据表明,视频探视减缓ICU患者及家属焦虑情绪的效果与非视频探视相当;视频探视较非视频探视能显著提升ICU患者及家属满意率,显著降低ICU患者谵妄发生率及感染风险。
文摘高效视频编码(High Efficiency Video Coding,HEVC)作为下一代新的视频编码标准,旨在有限网络带宽下传输高质量的网络视频。与现有的视频编码标准相比,高效视频编码具有更高的灵活性和压缩率。编码单元(Coding Unit,CU)是视频编码处理的基本单元,原有的算法通过四叉树递归获取最佳CU深度,在提高视频压缩性能的同时引入了较高的计算复杂度。针对该问题,提出了一种快速编码深度选择算法,该算法利用相邻CU的深度信息计算一个深度预测特征值,通过该特征值进行深度选择,以避免不必要的计算,降低计算复杂度。实验结果表明,该算法在保证视频压缩效果的同时有效降低了计算复杂度。
