Editing 3D models on smart devices

This study proposes a 3D CAD system available on smart devices, which are now a part of everyday life and which are widely applied in various domains, such as education and robot industry. If an engineer has a new idea while traveling or on the move, or in the case of collaboration between more than two engineers, this 3D CAD system allows modeling to be performed in a rapid and simple manner on a smart device. This 3D CAD system uses the common multi-touch gestures associated with smart devices to keep the modeling operations simple and easy for users. However, it is difficult to input the precise geometric information to generate 3D CAD models by such gestures. It is also impractical to provide a full set of modeling operations on a smart device due to hardware limitations. For this reason, the system excludes several complicated modeling operations. This work provides a scheme to regenerate a parametric 3D model on a PC-based CAD system via a macro-parametrics approach by transferring the 3D model created on a smart device in an editable form to a PC-based CAD system. If fine editing is needed, the user can perform additional work on a PC after reconstruction. Through the developed system, it is possible to produce a 3D editable model swiftly and simply in the smart device environment, allowing for reduced design time while also facilitating collaboration. This paper discusses the first-ever system design of a 3D CAD system on a smart device, the selection of the modeling operations, the assignment of gestures to these operations, and use of operation modes. This is followed by an introduction of the implementation methods, and finally a demonstration of case studies using a prototype system with examples.     

表情与姿态——城市建筑的个性表现

由于文明的进步带来的社会多样化,建筑的个性表现成为业界关注的重要问题。该文提出了基于实用性的建筑个性表达方式分类方法,将建筑造型方法分为表情表现与姿态表现,借鉴绘画与雕塑的差异性来理解建筑造型方法的艺术性,并试图通过二维与三维造型方法来研究建筑个性的整合问题。该文就表情表现和姿态表现在当代建筑造型设计中的趋势进行了有针对性的分析。认识到当代城市中城市建筑个性的张扬与城市的混乱所产生的冲突,作者最后提出以城市设计来控制城市建筑的个性表现以获得有序化的城市。     

Recognition of occupational therapy exercises and detection of compensation mistakes for Cerebral Palsy

Depth camera-based virtual rehabilitation systems are gaining attention in occupational therapy for cerebral palsy patients. When developing such a system, domain-specific exercise recognition is vital. To design such a gesture recognition method, some obstacles need to be overcome: detection of gestures not related to the defined exercise set and recognition of incorrect exercises performed by the patients to compensate for their lack of ability. We propose a framework based on hidden Markov models for the recognition of upper extremity functional exercises. We determine critical compensation mistakes together with restrictions for classifying these mistakes with the help of occupational therapists. We first eliminate undefined gestures by evaluating two models that produce adaptive threshold values. Then we utilize specific negative models based on feature thresholding and train them for each exercise to detect compensation mistakes. We perform various tests using our method in a laboratory environment under the supervision of occupational therapists.     

Nrityabodha: Towards understanding Indian classical dance using a deep learning approach

Indian classical dance has existed since over 5000 years and is widely practised and performed all over the world. However, the semantic meaning of the dance gestures and body postures as well as the intricate steps accompanied by music and recital of poems is only understood fully by the connoisseur. The common masses who watch a concert rarely appreciate or understand the ideas conveyed by the dancer. Can machine learning algorithms aid a novice to understand the semantic intricacies being expertly conveyed by the dancer? In this work, we aim to address this highly challenging problem and propose deep learning based algorithms to identify body postures and hand gestures in order to comprehend the intended meaning of the dance performance. Specifically, we propose a convolutional neural network and validate its performance on standard datasets for poses and hand gestures as well as on constrained and real-world datasets of classical dance. We use transfer learning to show that the pre-trained deep networks can reduce the time taken during training and also improve accuracy. Interestingly, we show with experiments performed using Kinect in constrained laboratory settings and data from Youtube that it is possible to identify body poses and hand gestures of the performer to understand the semantic meaning of the enacted dance piece.     

User interface based on natural interaction design for seniors

With world population ageing, how to help seniors to adapt to technology life is an important issue. Technology is becoming life rather than resistance, because many of the technology applications are often accompanied by a lot of information to process. This makes the user interface to become an important bridge between human computer interactions. Especially the inconvenience caused by human ageing, these related issues from the cognitive and operational of products are derived. This study proposes a study of user interface design based on natural interaction to increase seniors’ usage intention. In the proposed contents, the Kinect sensor is used to retrieve seniors’ in-depth information in movements, thus the user interface of system can be operated by the gesture intuitively. In the framework of the system, in the first all, the morphology is applied to identify the features of a hand from depth values obtained from the sensor. Gesture is used to recognize operating behavior of users to implement the interactive action, and collision detection is applied to confirm effectiveness of operation. On the other hand, through interpretive structural model (ISM), each design element of interactive interface can be decomposed and realized, and the solution for target and direction of design problem is also proposed. At the meanwhile, the concept of affordance is conducted to the development of interface for graphic users that proposed in this study, and the design achievement contains operation and usability of intuition can further be acquired. Finally, based on the proposed methodology, an intuitive user interface of digital devices is constructed by Java programming language that allows for verifying the feasibility of user interface for seniors. Besides, the proposed method can be widely used to develop the user interface for various products.     

Towards subject independent continuous sign language recognition: A segment and merge approach

This paper presents a segment-based probabilistic approach to robustly recognize continuous sign language sentences. The recognition strategy is based on a two-layer conditional random field (CRF) model, where the lower layer processes the component channels and provides outputs to the upper layer for sign recognition. The continuously signed sentences are first segmented, and the sub-segments are labeled SIGN or ME (movement epenthesis) by a Bayesian network (BN) which fuses the outputs of independent CRF and support vector machine (SVM) classifiers. The sub-segments labeled as ME are discarded and the remaining SIGN sub-segments are merged and recognized by the two-layer CRF classifier; for this we have proposed a new algorithm based on the semi-Markov CRF decoding scheme. With eight signers, we obtained a recall rate of 95.7% and a precision of 96.6% for unseen samples from seen signers, and a recall rate of 86.6% and a precision of 89.9% for unseen signers.     

Classification of hand postures against complex backgrounds using elastic graph matching

A system for person-independent classification of hand postures against complex backgrounds in video images is presented. The system employs elastic graph matching, which has already been successfully applied for object and face recognition. We use the bunch graph technique to model variance in hand posture appearance between different subjects and variance in backgrounds. Our system does not need a separate segmentation stage but closely integrates finding the object boundaries with posture classification.     

基于无线传感器网络的动态手势识别算法及动态演示

与语言文字一样,手势是人类沟通交流的重要方式。在计算机技术高速发展的现在,手势识别技术的出现,能大大提高用户与机器设备、计算机部件之间的交流效率。现在采用摄像头跟踪进行手势识别的技术已经使用一段时间,但是其对硬件的要求高、分析的数据大,使得其产品相对昂贵或者识别能力不够强。与摄像头跟踪技术相比,基于无线传感器网络的手势识别速度更快,价格更便宜并且实用。通过对移动终端设计一套手势识别的算法,利用无线传感器网络实现用手机终端操作计算机的终端的一系列复杂命令。实验证明,该算法适用于大型游戏操作和平台展示,使用户不用通过购买相关硬件直接安装使用。     

"穿地龙"机器人的控制系统研究

介绍了“穿地龙”机器人的用途和工作原理.从机器人的姿态检测、控制等几个方面进行了机器人控制系统的软硬件设计.实验结果验证了“穿地龙”机器人总体方案和控制系统方案的可行性,同时也为改进“穿地龙”机器人试验样机的设计打下了一定的基础,并为设计“穿地龙”机器人工作用机和进行“穿地龙”机器人的应用分析提供了条件.目前已完成了实验样机的研制.