Microsoft Kinect Applications

In this paper  we introduce the current  results of an ongoing three-year research and development project on automatic annotation of
human nonverbal behavior.  The present  output of the project is a
tool  that  provides algorithms and  graphical user interface  for the
generation  of ground-truth data  about  the subset of  facial and
body activities.  These data are essential for  the  experts who are
committed to unraveling  the  complexity  of  the  linkage  between
the  psychophysiological  state  and  the  nonverbal behavior  of a
human.  Our work relied on a Kinect sensor, which  computes
depth maps  together  with the coordinates of the  body  joints and
facial points.  Local binary patterns are  then  extracted from the
regions  of interests of  a  facial  video, which are  either  spatio-temporally aligned  with  the  depth maps  or  calculated  using  the
Active Shape Model. Another key idea of the proposed tool is that
the extracted feature vector is  semantically  associated with
ontological  concepts  in perspective  providing  annotations  for
most of the nonverbal activities.

Parkinson's disease (PD) is a progressive neurodegenerative movement disorder where motor dysfunction gradually increases as the disease progress. In addition to administering dopaminergic PD-specific drugs, attending neurologists strongly recommend regular exercise combined with physiotherapy. However, because of the long-term nature of the disease, patients following traditional rehabilitation programs may get bored, lose interest and eventually drop out as a direct result of the repeatability and predictability of the prescribed exercises. Technology supported opportunities to liven up a daily exercise schedule have appeared in the form of character-based, virtual reality games which promote physical training in a non-linear and looser fashion and provide an experience that varies from one game loop the next. Such “exergames”, a word that results from the amalgamation of the words “exercise” and “game” challenge patients into performing movements of varying complexity in a playful and immersive virtual environment. Today’s game consoles such as Nintendo’s Wii, Sony PlayStation Eye and Microsoft’s Kinect sensor present new opportunities to infuse motivation and variety to an otherwise mundane physiotherapy routine. In this paper we present some of these approaches, discuss their suitability for these PD patients, mainly on the basis of demands made on balance, agility and gesture precision, and present design principles that exergame platforms must comply with in order to be suitable for PD patients.

Hoy en día las TIC (tecnologías de la información y la comunicación) son tan
usuales en la vida cotidiana que las encontramos en casi todos los aspectos,
desde mandar un simple SMS, hasta realizar una videoconferencia por internet a
través de un dispositivo móvil. Estas tecnologías han cambiado la forma en que
las personas llevan a cabo sus actividades, que él no contar con nociones básicas
de cómo utilizar un dispositivo electrónico (computadora, celular, tableta, etc.)
podría limitar las posibilidades de desarrollo y/o interacción social de las mismas.

Tomatoes are best known grown fruits in greenhouses. In order to decrease the high labor cost and increase the efficiency, recently many researches have tried to harvest tomatoes automatically. To help the harvesting robot picking the fruit precisely, the main challenges are to identify and localize red mature tomato fruit accurately. In this paper, we presented a robust and effective method for challenging task of segmentation and localization of on-plant tomatoes in the greenhouse, for automatic tomato harvesting purpose. A low-cost RGB-D Kinect V2 camera was used to accomplish the task. Color images and depth images of tomatoes on-plants in the greenhouse were captured in day time using Kinect V2 camera. Along with color and depth images, the corresponding color coordinates, depth coordinates, and camera coordinates were also saved. The proposed method was divided into two stages: fruit segmentation and fruit localization. At the first stage, an improved HSV algorithm and watershed algorithm were used to segment mature fruits from a complex background. An improved HSV algorithm was used to enhance the feature of red mature fruits. After that, Otsu method and morphological operations were used to segment mature fruits from the background and then watershed was implemented to further separate touched fruits. Subsequently, each detected fruit was separately labeled to calculate the pixel coordinates values in color image. At the second stage, a fusion of color and depth information was carried out on the basis of the mapping relationship between color, depth and camera coordinates, to map the obtained fruit pixel coordinates in color image with acquired 3D point cloud data. Then the corresponding point cloud data of each labeled fruit were generated. To remove the noise in the cloud data, a filtration process was performed, and the final point cloud was generated. To verify the proposed method, 18 pairs of images were experimented containing the different numbers of measured fruits with measuring distance, ranging from 0.58 to 1.50 m. The average fruit localization error rate was 1.2 cm for depth distance and 1.9 cm for ground distance. Final results showed that the proposed method has good performance and robustness for segmentation and localization and have good potential to be implemented on the tomato harvesting robot in the greenhouse.

Showcases have been used to attract and arouse the interest of consumers for thousands of years, but it happens passively; interaction is necessary to engage the client. On the other hand, natural user interfaces allow this interaction to happen in a natural and transparent way. In November 2010, Microsoft launched Kinect, a sensor which is able to recognize movements more precisely than standard cameras. This project uses the language C Sharp and the Kinect SDK to build a WPF application that permits users to interact with a showcase using only gestures, to navigate through the available products. Tests have shown that Kinect can recognize gestures very accurately, as long as it is not under direct sunlight. In addition, the application had a very high acceptance level, being used by people of all ages and backgrounds without difficulties. This research offers great potential for further works, since knowledge about Kinect and natural user interfaces that now has been exposed can be used in projects that belong to a wide range of areas, from entertainment and productivity to robotics and medicine. These areas will likely be explored in the future by other academics

This mixed-methods study investigated the ability of motion-based video games (MBVG) to motivate adoption of authentic wall/rock climbing. The study also explored participants’ perceptions of MBVG and authentic wall/rock climbing. University students (n = 24) with no previous climbing experience were randomly assigned into the game-first (GF) or wall-first (WF) group. Both groups completed an initial questionnaire and two 30minute sessions of their initial activity. Afterwards, both groups completed the same questionnaire and switched activities. After finishing the second activity, participants completed a post-assessment and twelve weeks later completed a follow-up questionnaire. Two one-hour focus groups were also conducted after the second activity. Findings indicated that the MBVG did not motivate participants to pursue future wall/rock climbing; rather, the authentic experience motivated future activity. The participants did not have accurate perceptions of the mental or physi...

This paper presents an overview of the viability of gesture manipulation of a theatre head by making use of various gesture control movements. Gesture based user interfaces are not a common feature in theatre lighting. The major aim of this study was to build a system that will allow movement of the light in a particular direction using hand gestures. The Microsoft Kinect for windows was used as the input device to capture the image of the subject. DMX messages were sent using a DMX cable to relay control instructions to the light head for movements. A user was be able intuitively use directional pointing to move the light head to a desired position with the right hand. Results obtained showed that the user was able to select tilt and pan angle movements using the right hand.

A number of review or survey articles have previously appeared on human action recognition where either vision sensors or inertial sensors are used individually. Considering that each sensor modality has its own limitations, in a number of previously published papers, it has been shown that the fusion of vision and inertial sensor data improves the accuracy of recognition. This survey article provides an overview of the recent investigations where both vision and inertial sensors are used together and simultaneously to perform human action recognition more effectively. The thrust of this survey is on the utilization of depth cameras and inertial sensors as these two types of sensors are cost-effective, commercially available, and more significantly they both provide 3D human action data. An overview of the components necessary to achieve fusion of data from depth and inertial sensors is provided. In addition, a review of the publicly available datasets that include depth and inertial data which are simultaneously captured via depth and inertial sensors is presented.

Technology is part of everyday life, with more and more features and facilities. The educational environment does not seem to follow this trend, though as the technology used in classrooms is still very restricted, either for lack of resources or resistance on the part of educators. With the use of computational tools, the lessons become more attractive, efficient and participatory. However, they must be easy to use and meet the needs and expectations of its users so that picture can be changed. This study proposed an approach based on Natural User Interfaces tool that uses the Microsoft Kinect device to improve the user experience of digital presentations in the classroom. Finally, we performed some usability tests that confirmed that natural gestures provide better results and more efficiency.

In this study, the functionality of an autonomous mobile robot is improved by interfacing it with Microsoft Kinect for finding and tracking a previously identified human target while avoiding obstacles both while searching and tracking.  A suitable platform for fixing Microsoft Kinect and a laptop on a mobile robot is designed considering simplicity and practicality. The human identification and tracking methodology and algorithm is analysed for real life scenarios. The developed algorithm is applied to the mobile robot using robotics software and evaluated through real life scenarios achieving pleasing results. The mobile robot is able to identify humans, search for them and track them while avoiding static obstacles both while searching and tracking at indoor environments where no direct sunlight is present.

""The use of Visual Reality technologies in developing tools for various tasks such as for rehabilitation purposes has recently attained huge interests in a physical therapy arena. This paper describes motion-comparison between live-gestures performed by a user and recorded-gestures displayed on the screen using Microsoft Kinect. While user performs live-movement, corrections at real-time are shown on the screen so that user may self-learn the sequence of the movement by following on-screen instructions. At the end, summary is printed out on the screen which shows user’ progresses that may be used by examiners such as physiotherapists to assess user’s performance.

The approach that has been used for comparison is Kinematic of human motion using vectors – vector of lines, vector of planes, trajectories, angle formed between those vectors with respect to their directions.

However, data has been collected for testing under various conditions such as different persons with different bone lengths, different positions with respect to the Kinect, different elevation angles from the Kinect, presence of more than one objects and still it was able to give us promising results.
""

Human action recognition has a wide range of applications in-cluding biometrics, surveillance, and human computer interaction. The use of multimodal sensors for human action recognition is steadily increasing. However, there are limited publicly available datasets where depth camera and inertial sensor data are captured at the same time. This paper describes a freely available dataset, named UTD-MHAD, which consists of four temporally synchronized data modalities. These modalities include RGB videos, depth videos, skeleton positions, and inertial signals from a Kinect camera and a wearable inertial sensor for a comprehensive set of 27 human actions. Experimental results are provided to show how this database can be used to study fusion approaches that involve using both depth camera data and inertial sensor data. This public domain dataset is of benefit to multimodality research activities being conducted for human action recognition by various research groups. The dataset can be downloaded from http://www.utdallas.edu/~kehtar/UTD-MHAD.html

With the emergence of smart TVs, set-top boxes and public information screens over the last few years, there is an increasing demand to no longer use these appliances only for passive output. These devices can also be used to do text-based web search as well as other tasks which require some form of text input. However, the design of text entry interfaces for efficient input on such appliances represents a major challenge. With current virtual keyboard solutions we only achieve an average text input rate of 5.79 words per minute (WPM) while the average typing speed on a traditional keyboard is 38 WPM. Furthermore, so-called controller-free appliances such as Samsung's Smart TV or Microsoft's Xbox Kinect result in even lower average text input rates. We present SpeeG2, a multimodal text entry solution combining speech recognition with gesture-based error correction. Four innovative prototypes for the efficient controller-free text entry have been developed and evaluated. A quantitative evaluation of our SpeeG2 text entry solution revealed that the best of our four prototypes achieves an average input rate of 21.04 WPM (without errors), outperforming current state-of-the-art solutions for controller-free text input.

A video about the system can be found at: https://www.academia.edu/11590838/SpeeG2

Human activity recognition in everyday environments is a critical, but challenging task in Ambient Intelligence applications to achieve proper Ambient Assisted Living, and key challenges still remain to be dealt with to realize robust methods. One of the major limitations of the Ambient Intelligence systems today is the lack of semantic models of those activities on the environment, so that the system can recognize the specific activity being performed by the user(s) and act accordingly. In this context, this thesis addresses the general problem of knowledge representation in Smart Spaces. The main objective is to develop knowledge-based models, equipped with semantics to learn, infer and monitor human behaviours in Smart Spaces. Moreover, it is easy to recognize that some aspects of this problem have a high degree of uncertainty, and therefore, the developed models must be equipped with mechanisms to manage this type of information.
A fuzzy ontology and a semantic hybrid system are presented to allow modelling and recognition of a set of complex real-life scenarios where vagueness and uncertainty are inherent to the human nature of the users that perform it. The handling of uncertain, incomplete and vague data (i.e., missing sensor readings and activity execution variations, since human behaviour is non-deterministic) is approached for the first time through a fuzzy ontology validated on real-time settings within a hybrid data-driven and knowledge-based architecture. The semantics of activities, sub-activities and real-time object interaction are taken into consideration. The proposed framework consists of two main modules: the low-level sub-activity recognizer and the high-level activity recognizer. The rst module detects sub-activities (i.e., actions or basic activities) that take input data directly from a depth sensor (Kinect). The main contribution of this thesis tackles the second component of the hybrid system, which lays on top of the previous one, in a superior level of abstraction, and acquires the input data from the first module's output, and executes ontological inference to provide users, activities and their influence in the environment, with semantics. This component is thus knowledge-based, and a fuzzy ontology was designed to model the high-level activities. Since activity recognition requires context-awareness and the ability to discriminate among activities in different environments, the semantic framework allows for modelling common-sense knowledge in the form of a rule-based system that supports expressions close to natural language in the form of fuzzy linguistic labels. The framework advantages have been evaluated with a challenging and new public dataset, CAD-120, achieving an accuracy of 90.1% and 91.1% respectively for low and high-level activities. This entails an improvement over both, entirely data-driven approaches, and merely ontology-based approaches.
As an added value, for the system to be sufficiently simple and
flexible to be managed by non-expert users, and thus, facilitate the transfer of research to industry, a development framework composed by a programming toolbox, a hybrid crisp and fuzzy architecture, and graphical models to represent and configure human behaviour in Smart Spaces, were developed in order to provide the framework with more usability in the final application. As a result, human behaviour recognition can help assisting people with special needs such as in healthcare, independent elderly living, in remote rehabilitation monitoring, industrial process guideline control, and many other cases. This thesis shows use cases in these areas.

This article deals with the philosophical idea of worldmaking pursued through techné, meaning the fusion of the technical means of artistic creation, theorizing, and analysis, but specifically occurring in a feedback loop involving introspection and computation (cybernetic phenomenology). The discussion ranges over a wide variety of topics, including (1) the history of music theory from Ancient Greece to the present (including a rebuttal to Daniel Chua’s (2001) account of music history); (2) emergent properties in music arising from self-organization (explored through the Ancient Chinese abstract strategy board game go); (3) the ontology of musical qualities (properties) and categories (including their relation to visual, tactile, and olfactory qualities and categories). 
Various repertoires, artists, and philosophies are referenced. The essay analyzes aspects of Ligeti’s Violin Concerto, Carter’s String Quartet No. 5, and Lachenmann’s Kinderspiel.  Connections to the author’s own previous analytical and theoretical work are also discussed in relation to his interactive algorithmic audio-visual works (such as Fluxations and FluxNOISations). The techné of these is discussed in terms of logistics as well as aesthetic influences, including Wagner, Liszt, Stravinsky, Schoenberg, Crawford, Babbitt, Carter, Xenakis, Parker, Reich, Ligeti, Truax, Oliveros, Kandinsky, Miro, Pollock, Pollock, Hofmann, Rothko, Louis, Frankenthaler, Moholy-Nagy, Newman, Richter, and Brakhage.  The essay touches on philosophical ideas of Bergson, Whitehead, Deleuze, Harman, and Bogost, and more fully engages the philosophies of Nelson Goodman and Hannah Arendt in connection with artistic creation as relating to the theorizing and analysis of artistic works.     

Contact the author at jmailman@alumni.uchicago.edu
Download the article through JSTOR: http://www.jstor.org/stable/10.7757/persnewmusi.54.1.0005
or http://tinyurl.com/zdvkllr

Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D Histograms of Texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared to the existing boosting frameworks, we add a new multi-class constraint into the objective function, which helps to maintain a better margin distribution by maximizing the mean of margin whereas still minimizing the variance of margin. Experiments on the MSRAction3D, MSRGesture3D, MSRActivity3D and UTD-MHAD datasets demonstrate that the proposed system combining 3DHoTs and MBC is superior to the state-of-the-art.

Human action recognition based on skeletons has wide applications in human-computer interaction and intelligent surveillance. However, view variations and noisy data bring challenges to this task. What's more, it remains a problem to effectively represent spatio-temporal skeleton sequences. To solve these problems in one goal, this work presents an enhanced skeleton visualization method for view invariant human action recognition. Our method consists of three stages. First, a sequence-based view invariant transform is developed to eliminate the effect of view variations on spatio-temporal locations of skeleton joints. Second, the transformed skeletons are visualized as a series of color images, which implicitly encode the spatio-temporal information of skeleton joints. Furthermore, visual and motion enhancement methods are applied on color images to enhance their local patterns. Third, a convolutional neural networks-based model is adopted to extract robust and discriminative features from color images. The final action class scores are generated by decision level fusion of deep features. Extensive experiments on four challenging datasets consistently demonstrate the superiority of our method.

Tomato is well known fruit since it has many essential and beneficial nutrients like antioxidant, vitamin C and A for human daily diet. Tomato picking by hand is both labor and time consuming. Therefore, to overcome these issues, tomato needs to be picked up automatically with the help of harvesting robot. Recently automation of fruit harvesting gains great popularity. To guide the harvesting robot to pick up the fruit correctly, it is important to correctly detect and find the location of the red mature fruit. In this study, a new mature tomato detection algorithm based on the improved HSV (Hue, Saturation, Value) color space and the improved watershed segmentation was proposed, by using a cheap and easily accessible RGB camera for guiding a robot to pick up red tomatoes automatically. For that purpose, the color images of tomato plants were captured under natural light. At the first stage, improved HSV transform was used to remove background and to detect only red tomatoes. Then the morphological operations were applied to modify the detected fruit. The second step was the separation of connected fruits, so that the harvesting robot can pick up fruit correctly. To achieve this task, the improved watershed algorithm was applied. As a result, the detection of separated red mature tomato was done by using the improved HSV and watershed, with uneven illumination and complex background. The overall red fruit detection accuracy was up to 81.6%, and it shows good potential to be used on harvesting robot.

The lightweight and low-cost 3-dimensional depth sensors have gained much attention in the computer vision and gaming industry. While its performance has been proven successful in the gaming industry, these sensors have not been utilized successfully for assistive devices. Leveraging on this gap, this paper presents the design, implementation, and evaluation of a depth sensor based navigation assistive device for the visually impaired. The proposed portable embedded system interprets the field-of-view, converts it into depth matrix, processes the information, to recognize objects, humans, and provide relevant haptic feedback for navigation of the visually impaired. Through design and evaluation, the proposed system has shown to successfully identify, detect, and track closest objects, humans, and perform real-time distance measurements.

The field of interactive music systems (IMSs), beginning in the 1980s, is still relatively young and fast moving. The field of music theory-analysis, during the same period (since 1980), has undergone a major transformation in terms of technological innovations, flexibility, and breadth. The two fields have not really caught up with each other. It will be interesting to see what arises as they do — especially as both fields have become more concerned with the role of the body and embodied cognition. Framed in terms of contrasting epistemological orientations, this essay considers some relevant developments in IMSs, music cognition, and music theory and analysis, leading up to the present.  The most popular approaches to music cognition and to IMS design are rationalist (Ashby 2010), exploiting the ‘correct’ embodiments of music (Godøy 2004, Leman 2007, Paine 2009) based on affordances (Gibson 1977, Kelso 1998). This essay, however, advocates a pragmatist (Ashby 2010) approach inspired by music analysis and exploiting the potential of kinesthetic learning (associative learning). Prompted by a progressive approach to music analysis, theory, perception, and cognition (Dubiel 1999, Mailman 2007), interactive music technology can also be constructive, flexible, and progressive, by exploiting kinesthetic learning from immersion in new and unusual motion-to-sound mappings derived from dynamic formal processes in analysed music. In this way, immersive interactive systems offer an opportunity systematically to learn new associations based on principles theorised in response to analysis. Experience of these systems essentially ‘rewires the brain’, thereby exemplifying what Korsyn (2004) has attributed to Lewin’s (1986, 1987) approach to music perception: the ironist approach, as formulated by Rorty (1989). Thus a pragmatist ironist experimental (PIE) approach is articulated. Rather than committing to any particular ways music is already embodied, this approach acknowledges the flexible nature of embodied musical experience. It forges and uses interactive music technologies continually to redescribe and therefore reform how music is embodied, thereby disembodying to re-embody music, expanding how music is heard, contemplated and experienced.

Gesture recognition is a technology often used
in human-computer interaction applications. Dynamic
time warping (DTW) is one of the techniques used in
gesture recognition to find an optimal alignment between
two sequences. Oftentimes a pre-processing of
sequences is required to remove variations due to different
camera or body orientations or due to different
skeleton sizes between the reference gesture sequences
and the test gesture sequences. We discuss a set of
pre-processing methods to make the gesture recognition
mechanism robust to these variations. DTW computes
a dissimilarity measure by time-warping the sequences
on a per sample basis by using the distance between the
current reference and test sequences. However, all body
joints involved in a gesture are not equally important
in computing the distance between two sequence samples.
We propose a weighted DTW method that weights
joints by optimizing a discriminant ratio. Finally, we
demonstrate the performance of our pre-processing and
the weighted DTW method and compare our results
with the conventional DTW and state-of-the-art.

Moving 3D modeling is widely used in many areas such as cinema, gaming, robot control and training. Kinect is a system that can detect human movements and send them to computers. It was developed by Microsoft to play games for the Xbox game console and is being used over time for applications in other areas. This work aims to create a 3D human model using kinect.

This study was designed to test the relationship between matching and mirroring (MM) and homophilous perceptions (PHM) in leadership socialization. Elevated PHM levels were hypothesized to affect workplace acceptance levels. The need for testing leadership socialization skills was magnified with the current demographic shift known as the leadership succession crisis, creating problems with onboarding strategies. The theoretical foundations of the study were based on the social identity theory, the social presence theory, the leader-member exchange theory, and the similarity-attraction paradigm. The study conducted at Workforce Solutions North Texas in Wichita Falls, Texas was sampled based on the calculated strength of the effect in a pilot study. Test group participants engaged in MM enhanced social conversation with a coached candidate and control group participants conversed with an uncoached participant from the general population engaging in normal conversation. MM processes were differentiated from natural synchronic tendencies using specialized software and Kinect® sensors. A contrasted group, quasi-experiment was examined with an analysis of covariance. No statistically significant difference was found between groups on PHM levels, correcting for age, gender, ethnicity, height, glasses, hobbies, and professions. However, PHM and coworker acceptance were statistically significant but with no difference between groups. Further research is needed to test PHM as a metric for rapport in socialization strategies. Nevertheless, the homophily lens rather than the rapport lens can help organizational development and human resource professionals quantify and develop more effective socialization strategies aimed at solving problems associated with the leadership succession crisis.

This study proposes an approach to segment human object from a depth image based on histogram of depth values. The region of interest is first extracted based on a predefined threshold for histogram regions. A region growing process is then employed to separate multiple human bodies with the same depth interval. Our contribution is the identification of an adaptive growth threshold based on the detected histogram region. To demonstrate the effectiveness of the proposed method, an application in driver distraction detection was introduced. After successfully extracting the driver's position inside the car, we came up with a simple solution to track the driver motion. With the analysis of the difference between initial and current frame, a change of cluster position or depth value in the interested region, which cross the preset threshold, is considered as a distracted activity. The experiment results demonstrated the success of the algorithm in detecting typical distracted driving activities such as using phone for calling or texting, adjusting internal devices and drinking in real time.

The purpose of this study was to compare the similarities and differences of three common tennis strokes (i.e., forehand, backhand, and serve) performed by National Collegiate Athletic Association Division I tennis players in an authentic and motion-based video game (MBVG) environment. Moreover, through qualitative focus groups, the perceived effectiveness of using MBVGs as a pedagogical tool was also
examined. Video and statistical analyses revealed several positives and negatives of utilizing MBVGs when teaching sports skills, particularly in reference to beginner and experienced tennis athletes. Implications of these findings for physical educators, sport coaches, and sport video game developers are discussed.

In this paper I describe the development and evaluation of iMorphia, a prototype projective performance system. The system has been created as part of a practice led PhD investigating Multimodal Performance and Improvisation. Using a combination of body projection and body tracking, iMorphia creates the illusion of an embodied three dimensional character simultaneously visible to both performer and audience.

Agricultural soil roughness is pertinent to important agricultural phenomena, such as evaporation, infiltration or compression. Monitoring roughness variations would make possible the improvement of tillage operations. In the present work, implementation of the Microsoft KinectTM RGB-depth camera for dynamic characterization of soil microrelief is proposed and discussed. The metrological performance and the effect of the operating conditions on three-dimensional reconstruction was analyzed considering both laboratory tests on calibrated reference surfaces and field tests on different agricultural soil surfaces. Data set analysis was made on the basis of surface roughness parameters, as defined by ISO 25178 (2012) series: average roughness, root mean square roughness, skewness and kurtosis. Correlation between different tillage conditions and roughness parameters describing soil morphology was finally discussed.

Mocap (motion capture) techniques applied to music are now very widespread. More than two decades after the earliest experiments (1), there are many scientists and musicians working in this field, as shown by the large number of papers and the technological equipment used in many research centres around the world. Despite this popularity, however, there is little evidence of musical productions using the mocap technique, with the excep- tion of a few that have been able to rely upon very high budgets and very complex equipment. The following arti- cle aims to describe the implementation of "Neyma, for 2 performers, motion capture and live electronics (2012)," (2) an interactive multimedia performance that used a low budget mocap system, performed as part of the 56 th Biennale Musica di Venezia.

It is widely known the fact that traditional Interactive Whiteboard (IWB) are very expensive. At University of Trento there are different teams which work to possible new solutions to this problem examining new technologies and new paradigms of interaction such as the projects we will see in 2.3. 3 and 2.3. 4. These projects are based on the introduction of gaming devices as a concrete tool to support teaching and learning activities. They can be considered the forerunners in this type of approach to the problem. They constitute the ...

This paper presents a framework for spotting and recognizing continuous human gestures. Skeleton based features are extracted from normalized human body coordinates to represent gestures. These features are then used to construct spatio-temporal template based Random Decision Forest models. Finally, predictions from different models are fused at decision-level to improve overall recognition performance. Our method has shown competitive results on the ChaLearn 2014 Looking at People: Gesture Recognition dataset. Trained on a dataset of 20 gesture vocabulary and 7754 gesture samples, our method achieved a Jaccard Index of 0.74663 on the test set, reaching 7th place among contenders. Among methods that exclusively used skeleton based features, our method obtained the highest recognition performance.

This paper presents a human action recognition system that runs in real-time and uses a depth camera and an inertial sensor simultaneously based on a previously developed sensor fusion method. Computationally efficient depth image features and inertial signals features are fed into two computationally efficient collaborative representative classifiers. A decision-level fusion is then performed. The developed real-time system is evaluated using a publicly available multimodal human action recognition dataset by considering a comprehensive set of human actions. The overall classification rate of the developed real-time system is shown to be more than 97% which is at least 9% higher than when each sensing modality is used individually. The results from both offline and real-time experimentations demonstrate the effectiveness of the system and its real-time throughputs.

This paper presents a computationally efficient method
for action recognition from depth video sequences. It employs the so called depth motion maps (DMMs) from three
projection views (front, side and top) to capture motion
cues and uses local binary patterns (LBPs) to gain a compact feature representation. Two types of fusion consisting
of feature-level fusion and decision-level fusion are considered. In the feature-level fusion, LBP features from
three DMMs are merged before classification while in the
decision-level fusion, a soft decision-fusion rule is used
to combine the classification outcomes. The introduced
method is evaluated on two standard datasets and is also
compared with the existing methods. The results indicate
that it outperforms the existing methods and is able to process depth video sequences in real-time.

In this paper, we present a project aiming at designing a low-cost technological setup for translating real-life lectures into a 3D virtual world. We present the design of the first prototype where we record the voice of a lecturer, presentation slides, and use a motion-capture technique to grasp gestures. Based on these data, we create a scene in a 3D virtual world, display the slides, play the recorded sound, and animate the lecturer’s avatar. We discuss evaluation results and discovered limitations, and outline solutions. In addition, we propose the major types of learning scenarios for the use of the designed system.