可见光波段虚拟伪装场景的创建

提出基于Vue和Python的可见光波段虚拟伪装场景概念,重点阐述了不同探测方位、不同天气时段的虚拟伪装场景和动态虚拟伪装场景的创建流程,分析了该方法存在的问题并对下一步的工作进行了展望.基于Vue和Python的虚拟伪装场景在可见光波段伪装效果评估方面具有较好的应用前景和推广价值.     

基于MultiGen的虚拟场景真实感研究

虚拟校园是数字城市的缩影。以北京交通大学的真实校园场景为研究对象,采用模块化、层次结构和纹理映射技术相融合的方法,通过运用实时可视化三维建模软件系统MultiGen Creator进行建模,创建了较为逼真的校园虚拟场景模型,并从数据库结构和组成模型的面片数两方面对其进行了优化,最后利用仿真系统Vega实现了校园虚拟场景的驱动显示。对于校园虚拟现实系统关键技术的研究与实现成为完成逼真合理的大规模虚拟场景的基础。     

基于双向出行链的电动汽车平抑电网波动策略

针对电动汽车(electric vehicle,EV)时空转移随机性造成的电网波动问题,计及车主的性别差异、车主实时出行目的地不同和车辆双向行驶,提出了一种基于出行随机性双向出行链的EV充放电调度策略。考虑车主实际出行过程,建立EV双向出行链模型;考虑到男女车主出行过程中的性别差异,确定男女实时出行概率模型;以降低电网的波动为目标函数,考虑车主实时出行需求和EV实时荷电状态(state of change,SOC)建立调度模型,并依据所建立模型对EV进行充放电调度。在约280 m²的区域进行仿真分析,结果表明：双向出行链模型更接近用户实际出行规律,其调度策略能够在满足用户实际出行需求的同时,更好地抑制电网波动性。     

Blind omnidirectional image quality assessment with representative features and viewport oriented statistical features

With the development of information technologies, various types of streaming images are generated, such as videos, graphics, Virtual Reality (VR)/omnidirectional images (OIs), etc. Among them, the OIs usually have a broader view and a higher resolution, which provides human an immersive visual experience in a head-mounted display. However, the current image quality assessment works cannot achieve good performance without considering representative human visual features and visual viewing characteristics of OIs, which limited OIs’ further development. Motivated by the above problem, this work proposes a blind omnidirectional image quality assessment (BOIQA) model based on representative features and viewport oriented statistical features. Specifically, we apply the local binary pattern operator to encoder the cross-channel color information, and apply the weighted LBP to extract the structural features. Then the local natural scene statistics (NSS) features are extracted by using the viewport sampling to boost the performance. Finally, we apply support vector regression to predict the OIs’ quality score, and experimental results on CVIQD2018 and OIQA2018 Databases prove that the proposed model achieves better performance than state-of-the-art OIQA models.     

用于行人轨迹预测的场景限制时空图卷积网络

目的 针对行人轨迹预测问题,已有的几种结合场景信息的方法基于合并操作通过神经网络隐式学习场景与行人运动的关联,无法直观地解释场景对单个行人运动的调节作用。除此之外,基于图注意力机制的时空图神经网络旨在学习全局模式下行人之间的社会交互,在人群拥挤场景下精度不佳。鉴于此,本文提出一种场景限制时空图卷积神经网络（scene-constrained spatial-temporal graph convolutional neural network,Scene-STGCNN）。方法 Scene-STGCNN由运动模块、基于场景的微调模块、时空卷积和时空外推卷积组成。运动模块以时空图卷积提取局部行人时空特征,避免了时空图神经网络在全局模式下学习交互的局限性。基于场景的微调模块将场景信息嵌入为掩模矩阵,用来调节运动模块生成的中间运动特征,具备实际场景下的物理解释性。通过最小化核密度估计下真实轨迹的负对数似然,增强Scene-STGCNN输出的多模态性,减少预测误差。结果 实验在公开数据集ETH （包含ETH和HOTEL）和UCY （包含UNIV、ZARA1和ZARA2）上与其他7种主流方法进行比较,就平均值而言,相对于性能第2的模型,平均位移误差（average displacement error,ADE）值减少了12%,最终位移误差（final displacement error,FDE）值减少了9%。在同样的数据集上进行了消融实验以验证基于场景的微调模块的有效性,结果表明基于场景的微调模块能有效建模场景对行人轨迹的调节作用,从而减小算法的预测误差。结论 本文提出的场景限制时空图卷积网络能有效融合场景和行人运动,在学习局部模式下行人交互的同时基于场景特征对轨迹特征做实时性调节,相比于其他主流方法,具有更优的性能。     

Label distribution learning for scene text detection

Recently, segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved texts. However, existing methods usually need complex post-processing stages to process ambiguous labels, i.e., the labels of the pixels near the text boundary, which may belong to the text or background. In this paper, we present a framework for segmentation-based scene text detection by learning from ambiguous labels. We use the label distribution learning method to process the label ambiguity of text annotation, which achieves a good performance without using additional post-processing stage. Experiments on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.     

孪生网络框架下融合显著性和干扰在线学习的航拍目标跟踪算法

针对一般跟踪算法不能很好地解决航拍视频下目标分辨率低、视场大、视角变化多等特殊难点,该文提出一种融合目标显著性和在线学习干扰因子的无人机(UAV)跟踪算法.通用模型预训练的深层特征无法有效地识别航拍目标,该文跟踪算法能根据反向传播梯度识别每个卷积滤波器的重要性来更好地选择目标显著性特征,以此凸显航拍目标特性.另外充分利用连续视频丰富的上下文信息,通过引导目标外观模型与当前帧尽可能相似地来在线学习动态目标的干扰因子,从而实现可靠的自适应匹配跟踪.实验证明:该算法在跟踪难点更多的UAV123数据集上跟踪成功率和准确率分别比孪生网络基准算法高5.3%和3.6%,同时速度达到平均28.7帧/s,基本满足航拍目标跟踪准确性和实时性需求.     

基于学习主动中心轮廓模型的场景文本检测

在场景文本检测领域,存在由于文本尺寸波动较大导致的小文本漏检、大文本欠检测和多尺度文本边界检测错误的情况。针对上述问题,提出一种基于学习主动中心轮廓模型的场景文本检测网络。在残差网络ResNet的基础上构建多尺度特征权重融合模型,对输入的场景文本图片进行多尺度特征提取和权重融合,并计算出最终的特征融合图,适应场景文本长宽比变化较大的情况。在此基础上,将融合后的特征图输入到学习主动中心轮廓模型预测文本框的中心点和边界,该模型为场景文本检测提供丰富先验知识,以解决多尺度文本检测框包含过多背景或部分包围文本造成的边界检测错误问题。在MSRA-TD500、IC13、IC15和IC17MLT数据集上的实验结果表明,该网络能够提高多尺度场景文本检测的准确率,其中在MSRA-TD50数据集上F-measure为0.83,相较于MSR方法提升1%,在IC13数据集上F-measure为0.91,相较于PixelLink网络提升2%,在IC15数据集上F-measure值为0.87,相较于PSENet网络提升1%,在IC17MLT数据集上F-measure值为0.74,相较于TridentNet网络提升1%。     

结合外部知识库与适应性推理的场景图生成模型

为在场景图生成网络中获得重要的上下文信息,同时减少数据集偏差对场景图生成性能的影响,构建一种基于外部知识库与适应性推理的场景图生成模型。利用结合外部知识库的目标检测模块引入语言先验知识,提高实体对关系类别检测的准确性。设计基于Transformer架构的上下文信息提取模块,采用两个Transformer编码层对候选框和实体对关系类别进行处理,并利用自注意力机制分阶段实现上下文信息合并,获取重要的全局上下文信息。构建特征特殊融合的适应性推理模块,通过软化分布并根据实体对的视觉外观进行适应性推理关系分类,缓解实体对关系频率的长尾分布问题,提升模型推理能力。在VG数据集上的实验结果表明,与MOTIFS模型相比,该模型在谓词分类、场景图分类和场景图生成子任务上的Top-100召回率分别提升了1.4、4.3、7.1个百分点,对于多数关系类别具有更好的场景图生成效果。     

Travel time models for deep-lane unit-load autonomous vehicle storage and retrieval system (AVS/RS)

Autonomous vehicle storage and retrieval systems use vehicles that move horizontally along rails within the storage racks, while vertical movements are provided by lifts. The solution proposed in this paper addresses a particular system configuration that works with multiple deep storage lanes that are widely used in the food and beverage industry, characterised by large volumes of products of limited variety. The generic deep lane is single item, i.e. one stock keeping unit, and single batch, i.e. one production lot, thereby affecting the performance of the system in terms of storage capacity utilisation and throughput. Determining the number and depth of the lanes is crucial to aid the design and control of such a storage system. The aim of this paper was to support the design of AVS/RSs though a set of original analytic models for the determination of the travelled distance and time for single-command and dual-command cycles given alternative layout configurations. The models are validated by simulation and exemplified with a real-warehousing case study. The paper presents useful guidelines for the configuration of the system layout including the determination of the optimal shape ratio and the length of the lanes.