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.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Identification of digital technologies and digitalisation trends in the mining industry

Digitalisation in mining refers to the use of computerised or digital devices or systems and digitised data that are to reduce costs, improve business productivity, and transform mining practices. However, it remains increasingly difficult for mining companies to decide which digital technologies are most relevant to their needs and individual mines. This paper provides an overview of digital technologies currently relevant to mining companies as presented and discussed by mining journals, the media and insight reports of leading consultancy agencies. Relevant technologies were systematically identified using text-mining techniques, and network analyses established the relations between significant technologies. Results demonstrated that currently 107 different digital technologies are pursued in the mining sector. Also, an analysis of the actual implementation of digital technologies in 158 active surface and underground mines reveals a limited uptake of digital technologies in general and that the uptake increases with the run-of-mine production. Large-scale mining operations appear to select and apply digital technologies suitable to their needs, whereas operations with lower production rates do not implement the currently available digital technologies to the same extent. These minor producers may require other digital transformation solutions tailored to their capabilities and needs and applicable to their scale of operations.     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

Creating the brain and interacting with the brain: an integrated approach to understanding the brain

In the past two decades, brain science and robotics have made gigantic advances in their own fields, and their interactions have generated several interdisciplinary research fields. First, in the ‘understanding the brain by creating the brain’ approach, computational neuroscience models have been applied to many robotics problems. Second, such brain-motivated fields as cognitive robotics and developmental robotics have emerged as interdisciplinary areas among robotics, neuroscience and cognitive science with special emphasis on humanoid robots. Third, in brain–machine interface research, a brain and a robot are mutually connected within a closed loop. In this paper, we review the theoretical backgrounds of these three interdisciplinary fields and their recent progress. Then, we introduce recent efforts to reintegrate these research fields into a coherent perspective and propose a new direction that integrates brain science and robotics where the decoding of information from the brain, robot control based on the decoded information and multimodal feedback to the brain from the robot are carried out in real time and in a closed loop.     

Assessment of the effectiveness of steel fibre reinforcement for the punching resistance of flat slabs by experimental research and design approach

The present paper deals with the experimental assessment of the effectiveness of steel fibre reinforcement in terms of punching resistance of centrically loaded flat slabs, and to the development of an analytical model capable of predicting the punching behaviour of this type of structures. For this purpose, eight slabs of 2550 × 2550 × 150 mm³ dimensions were tested up to failure, by investigating the influence of the content of steel fibres (0, 60, 75 and 90 kg/m³) and concrete strength class (50 and 70 MPa). Two reference slabs without fibre reinforcement, one for each concrete strength class, and one slab for each fibre content and each strength class compose the experimental program. All slabs were flexurally reinforced with a grid of ribbed steel bars in a percentage to assure punching failure mode for the reference slabs. Hooked ends steel fibres provided the unique shear reinforcement. The results have revealed that steel fibres are very effective in converting brittle punching failure into ductile flexural failure, by increasing both the ultimate load and deflection, as long as adequate fibre reinforcement is assured. An analytical model was developed based on the most recent concepts proposed by the fib Mode Code 2010 for predicting the punching resistance of flat slabs and for the characterization of the behaviour of fibre reinforced concrete. The most refined version of this model was capable of predicting the punching resistance of the tested slabs with excellent accuracy and coefficient of variation of about 5%.     

掘进巷道快速过断层施工技术应用

基于四候煤矿3108回风顺槽过F3断层期间,顶板出现严重破碎、下沉现象,提出了俯斜台阶法施工工艺,并对断层破碎带顶板采取MF-2型化学材料注浆加固以及"钢筋锚索网+U29梯形棚"联合支护措施。支护效果检验结果表明,联合支护有效控制了断层破碎区顶板下沉、破碎现象,保证了巷道顶板稳定性。     

Animations showing Lego manipulative tasks: Three potential moderators of effectiveness

Evidence suggests that transient visual information, such as animations, may be more challenging to learn than static visualizations. However, when a procedural-manipulative task is involved, our evolved embodied cognition seems to reverse this transitory challenge. Hence, for object manipulative tasks, instructional animations may be more suitable than statics. We investigated this argument further by comparing animations with statics using a Lego task shown to university students, by examining three potential moderators of effectiveness: (a) the environment of manipulation (virtual or physical), (b) the quality of visual information (focused or unfocused), and (c) the presence of hands (no hands or with hands). In Experiment 1 we found an advantage of animation over statics, and no differences among the environments. In Experiment 2, we again observed an animation advantage, a small advantage of focused static information compared to unfocused static information, and a positive effect of not showing the hands.