No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

Life cycle cost of conventional,battery electric,and fuel cell electric vehicles considering traffic and environmental policies in China

Electric vehicles (EVs) are considered a promising alternative to conventional vehicles (CVs) to alleviate the oil crisis and reduce urban air pollution and carbon emissions. Consumers usually focus on the tangible cost when choosing an EV or CV but overlook the time cost for restricting purchase or driving and the environmental cost from gas emissions, falling to have a comprehensive understanding of the economic competitiveness of CVs and EVs. In this study, a life cycle cost model for vehicles is conducted to express traffic and environmental policies in monetary terms, which are called intangible cost and external cost, respectively. Battery electric vehicles (BEVs), fuel cell electric vehicles (FCEVs), and CVs are compared in four first-tier, four new first-tier, and 4 s-tier and below cities in China. The comparison shows that BEVs and FCEVs in most cities are incomparable with CVs in terms of tangible cost. However, the prominent traffic and environmental policies in first-tier cities, especially in Beijing and Shanghai, greatly increase the intangible and external costs of CVs, making consumers more inclined to purchase BEVs and FCEVs. The main policy benefits of BEVs and FCEVs come from three aspects: government subsidies, purchase and driving restrictions, and environmental taxes. With the predictable reduction in government subsidies, traffic and environmental policies present important factors influencing the competitiveness of BEVs and FCEVs. In first-tier cities, BEVs and FCEVs already have a competitive foundation for large-scale promotion. In new first-tier and second-tier and below cities, stricter traffic and environmental policies need to be formulated to offset the negative impact of the reduction in government subsidies on the competitiveness of BEVs and FCEVs. Additionally, a sensitivity analysis reveals that increasing the mileage and reducing fuel prices can significantly improve the competitiveness of BEVs and FCEVs, respectively.     

Experimental investigation of supercapacitor based regenerative energy storage for a fuel cell vehicle equipped with an alternator

Recently, researchers have devoted more attention to supercapacitors (SCs) to integrate with batteries in energy storage systems (ESSs) for vehicle applications. In this study, we attempted to characterize the use of SCs in the ESS for a PEM fuel cell vehicle equipped with an alternator to maximize the performance of regenerative braking. We applied lithium-ion batteries (LIBs) and SCs as energy storage devices to examine their effect on ESS. Then we used a hysteresis brake to apply controllable braking force on the flywheel to form hybrid braking (HB) and made efforts to study its behavior to suggest a braking control strategy. We also ran the whole system over the rotational speed to cover the range of driving speed. At last, we sized the SCs for the most commonly used fuel cell electric vehicle (FCEV) in Korea, i.e., Hyundai NEXO, based on the results obtained from the above study by alternator efficiencies.     

基于词性特征的明喻识别及要素抽取方法

比喻是一种利用事物之间的相似点建立关系的修辞方式。明喻是比喻中最常见的形式,具有明显的喻词,例如"像",用于关联本体和喻体。近年来高考语文散文类鉴赏题中多有考查明喻句的试题,为了解答此类鉴赏题,需要识别比喻句中的本体和喻体要素。该文提出了基于词性特征的明喻识别及要素抽取方法。首先将句子中词向量化表示与词性特征向量化表示进行融合,将融合后的向量输入到BiLSTM中进行训练,然后利用CRF解码出全局最优标注序列;最后得到明喻识别和要素抽取的结果。公开数据集上的实验结果表明,该方法优于已有的单任务方法;同时也将该文方法应用于北京高考语文鉴赏题中比喻句的识别与要素抽取,验证了方法的可行性。     

Deep reinforcement learning-based cooperative interactions among heterogeneous vehicular networks

Most real-world vehicle nodes can be structured into an interconnected network of vehicles. Through structuring these services and vehicle device interactions into multiple types, such internet of vehicles becomes multidimensional heterogeneous overlay networks. The heterogeneousness of the overlays makes it difficult for the overlay networks to coordinate with each other to improve their performance. Therefore, it poses an interesting but critical challenge to the effective analysis of heterogeneous virtual vehicular networks. A variety of virtual vehicular networks can be easily deployed onto the native network by applying the concept of SDN (Software Defined Networking). These virtual networks reflect their heterogeneousness due to their different performance goals, and they compete for the same physical resources of the underlying network, so that a sub-optimal performance of the virtual networks may be achieved. Therefore, we propose a Deep Reinforcement Learning (DRL) approach to make the virtual networks cooperate with each other through the SDN controller. A cooperative solution based on the asymmetric Nash bargaining is proposed for co-existing virtual networks to improve their performance. Moreover, the Markov Chain model and DRL resolution are introduced to leverage the heterogeneous performance goals of virtual networks. The implementation of the approach is introduced, and simulation results confirm the performance improvement of the latency sensitive, loss-rate sensitive and throughput sensitive heterogeneous vehicular networks using our cooperative solution.     

A signal adaptive diffusion filter for video coding: Mathematical framework and complexity reductions

In this paper we combine video compression and modern image processing methods. We construct novel iterative filter methods for prediction signals based on Partial Differential Equation (PDE) based methods. The mathematical framework of the employed diffusion filter class is given and some desirable properties are stated. In particular, two types of diffusion filters are constructed: a uniform diffusion filter using a fixed filter mask and a signal adaptive diffusion filter that incorporates the structures of the underlying prediction signal. The latter has the advantage of not attenuating existing edges while the uniform filter is less complex. The filters are embedded into a software based on HEVC with additional QTBT (Quadtree plus Binary Tree) and MTT (Multi-Type-Tree) block structure. In this setting, several measures to reduce the coding complexity of the tool are introduced, discussed and tested thoroughly. The coding complexity is reduced by up to 70% while maintaining over 80% of the gain. Overall, the diffusion filter method achieves average bitrate savings of 2.27% for Random Access having an average encoder runtime complexity of 119% and 117% decoder runtime complexity. For individual test sequences, results of 7.36% for Random Access are accomplished.     

An agile model for the eco-design of electric vehicle Li-ion batteries

Numerous design choices need to be made at several levels when designing high-tech products: technology, processes, architecture, components, materials… and these choices need to be made in relation to the product life cycle with the corresponding experts for each stage of the life cycle. At the same time, to ensure product sustainability, a specific focus on the future potential environmental impacts is highly recommended. In this research, an agile model is proposed to help designers make decisions while monitoring environmental performance indicators of high-tech solutions. The concept of Critical Product Life Cycle Parameters had to be introduced to facilitate the eco-design of the final product. The approach is illustrated by the Electric Vehicle Li-Ion Batteries case study.     

基于多尺度双线性卷积神经网络的多角度下车型精细识别

针对多角度下车辆出现一定的尺度变化和形变导致很难被准确识别的问题，提出基于多尺度双线性卷积神经网络（MS-B-CNN）的车型精细识别模型。首先，对双线性卷积神经网络（B-CNN）算法进行改进，提出MS-B-CNN算法对不同卷积层的特征进行了多尺度融合，以提高特征表达能力；此外，还采用基于中心损失函数与Softmax损失函数联合学习的策略，在Softmax损失函数基础上分别对训练集每个类别在特征空间维护一个类中心，在训练过程中新增加样本时，网络会约束样本的分类中心距离，以提高多角度情况下的车型识别的能力。实验结果显示，该车型识别模型在CompCars数据集上的正确率达到了93.63%，验证了模型在多角度情况下的准确性和鲁棒性。     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.