Archives for 2017

Today I read a paper titled “Android Note Manager Application for People with Visual Impairment”

The abstract is:
With the outburst of smart-phones today, the market is exploding with various mobile applications.

This paper proposes an application using which visually impaired people can type a note in Grade 1 Braille and save it in the external memory of their smart-phone.

The application also shows intelligence by activating reminders and/or calling certain contacts based on the content in the notes.

Today I read a paper titled “Are Game Platforms suitable for Parkinson Disease patients?”

The abstract is:
Parkinson’s Disease (PD) is a progressive neurodegenerative movement disorder that affects more that 6 million people worldwide.

Motor dysfunction gradually increases as the disease progress.

It is usually mild in the early stages of the disease but it relentlessly progresses to a severe or very severe disability that is characterized by increasing degrees of bradykinesia, hypokinesia, muscle rigidity, loss of postural reflexes and balance control as well as freezing of gait.

In addition to a line of treatment based on dopaminergic PD-specific drugs, attending neurologists strongly recommend regular exercise combined with physiotherapy.

However, the routine of traditional rehabilitation often create boredom and loss of interest.

Opportunities to liven up a daily exercise schedule may well take the form of character-based virtual reality games which engage the player to physically train in a non-linear and looser fashion, providing 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.

In fact, today’s game consoles using controllers like Nintendo’s Wii, Sony PlayStation Eye and the Microsoft Kinect sensor present new opportunities to infuse motivation and variety to an otherwise mundane physiotherapy routine.

But are these controllers and the games built for them appropriate for PD patients? In this paper we present some of these approaches and discuss their suitability for these patients mainly on the basis of demands made on balance, agility and gesture precision.

Today I read a paper titled “Recognition of Emotions using Kinects”

The abstract is:
Psychological studies indicate that emotional states are expressed in the way people walk and the human gait is investigated in terms of its ability to reveal a person’s emotional state.

And Microsoft Kinect is a rapidly developing, inexpensive, portable and no-marker motion capture system.

This paper gives a new referable method to do emotion recognition, by using Microsoft Kinect to do gait pattern analysis, which has not been reported.

$59$ subjects are recruited in this study and their gait patterns are record by two Kinect cameras.

Significant joints selecting, Coordinate system transforming, Slider window gauss filter, Differential operation, and Data segmentation are used in data preprocessing.

Feature extracting is based on Fourier transformation.

By using the NaiveBayes, RandomForests, libSVM and SMO classification, the recognition rate of natural and unnatural emotions can reach above 70%.It is concluded that using the Kinect system can be a new method in recognition of emotions.

Today I read a paper titled “Are Elephants Bigger than Butterflies? Reasoning about Sizes of Objects”

The abstract is:
Human vision greatly benefits from the information about sizes of objects.

The role of size in several visual reasoning tasks has been thoroughly explored in human perception and cognition.

However, the impact of the information about sizes of objects is yet to be determined in AI.

We postulate that this is mainly attributed to the lack of a comprehensive repository of size information.

In this paper, we introduce a method to automatically infer object sizes, leveraging visual and textual information from web.

By maximizing the joint likelihood of textual and visual observations, our method learns reliable relative size estimates, with no explicit human supervision.

We introduce the relative size dataset and show that our method outperforms competitive textual and visual baselines in reasoning about size comparisons.

Today I read a paper titled “Vision Based Navigation for a Mobile Robot with Different Field of Views”

The abstract is:
The basic idea behind evolutionary robotics is to evolve a set of neural controllers for a particular task at hand.

It involves use of various input parameters such as infrared sensors, light sensors and vision based methods.

This paper aims to explore the evolution of vision based navigation in a mobile robot.

It discusses in detail the effect of different field of views for a mobile robot.

The individuals have been evolved using different FOV values and the results have been recorded and analyzed.The optimum values for FOV have been proposed after evaluating more than 100 different values.

It has been observed that the optimum FOV value requires lesser number of generations for evolution and the mobile robot trained with that particular value is able to navigate well in the environment.

Today I read a paper titled “Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems”

The abstract is:
This paper proposes an approach that predicts the road course from camera sensors leveraging deep learning techniques.

Road pixels are identified by training a multi-scale convolutional neural network on a large number of full-scene-labeled night-time road images including adverse weather conditions.

A framework is presented that applies the proposed approach to longer distance road course estimation, which is the basis for an augmented reality navigation application.

In this framework long range sensor data (radar) and data from a map database are fused with short range sensor data (camera) to produce a precise longitudinal and lateral localization and road course estimation.

The proposed approach reliably detects roads with and without lane markings and thus increases the robustness and availability of road course estimations and augmented reality navigation.

Evaluations on an extensive set of high precision ground truth data taken from a differential GPS and an inertial measurement unit show that the proposed approach reaches state-of-the-art performance without the limitation of requiring existing lane markings.

Today I read a paper titled “Dictionary Learning for Robotic Grasp Recognition and Detection”

The abstract is:
The ability to grasp ordinary and potentially never-seen objects is an important feature in both domestic and industrial robotics.

For a system to accomplish this, it must autonomously identify grasping locations by using information from various sensors, such as Microsoft Kinect 3D camera.

Despite numerous progress, significant work still remains to be done in this field.

To this effect, we propose a dictionary learning and sparse representation (DLSR) framework for representing RGBD images from 3D sensors in the context of determining such good grasping locations.

In contrast to previously proposed approaches that relied on sophisticated regularization or very large datasets, the derived perception system has a fast training phase and can work with small datasets.

It is also theoretically founded for dealing with masked-out entries, which are common with 3D sensors.

We contribute by presenting a comparative study of several DLSR approach combinations for recognizing and detecting grasp candidates on the standard Cornell dataset.

Importantly, experimental results show a performance improvement of 1.69% in detection and 3.16% in recognition over current state-of-the-art convolutional neural network (CNN).

Even though nowadays most popular vision-based approach is CNN, this suggests that DLSR is also a viable alternative with interesting advantages that CNN has not.

Today I read a paper titled “An artificial intelligence tool for heterogeneous team formation in the classroom”

The abstract is:
Nowadays, there is increasing interest in the development of teamwork skills in the educational context.

This growing interest is motivated by its pedagogical effectiveness and the fact that, in labour contexts, enterprises organize their employees in teams to carry out complex projects.

Despite its crucial importance in the classroom and industry, there is a lack of support for the team formation process.

Not only do many factors influence team performance, but the problem becomes exponentially costly if teams are to be optimized.

In this article, we propose a tool whose aim it is to cover such a gap.

It combines artificial intelligence techniques such as coalition structure generation, Bayesian learning, and Belbin’s role theory to facilitate the generation of working groups in an educational context.

This tool improves current state of the art proposals in three ways: i) it takes into account the feedback of other teammates in order to establish the most predominant role of a student instead of self-perception questionnaires; ii) it handles uncertainty with regard to each student’s predominant team role; iii) it is iterative since it considers information from several interactions in order to improve the estimation of role assignments.

We tested the performance of the proposed tool in an experiment involving students that took part in three different team activities.

The experiments suggest that the proposed tool is able to improve different teamwork aspects such as team dynamics and student satisfaction.

Today I read a paper titled “Auditory Brain-Computer Interface Paradigm with Head Related Impulse Response-based Spatial Cues”

The abstract is:
The aim of this study is to provide a comprehensive test of head related impulse response (HRIR) for an auditory spatial speller brain-computer interface (BCI) paradigm.

The study is conducted with six users in an experimental set up based on five Japanese hiragana vowels.

Auditory evoked potentials resulted with encouragingly good and stable “aha-” or P300-responses in real-world online BCI experiments.

Our case study indicated that the auditory HRIR spatial sound reproduction paradigm could be a viable alternative to the established multi-loudspeaker surround sound BCI-speller applications, as far as healthy pilot study users are concerned.

Today I read a paper titled “Real-Time Human Motion Capture with Multiple Depth Cameras”

The abstract is:
Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras.

In this work we present an efficient and inexpensive solution to markerless motion capture using only a few Kinect sensors.

Unlike the previous work on 3d pose estimation using a single depth camera, we relax constraints on the camera location and do not assume a co-operative user.

We apply recent image segmentation techniques to depth images and use curriculum learning to train our system on purely synthetic data.

Our method accurately localizes body parts without requiring an explicit shape model.

The body joint locations are then recovered by combining evidence from multiple views in real-time.

We also introduce a dataset of ~6 million synthetic depth frames for pose estimation from multiple cameras and exceed state-of-the-art results on the Berkeley MHAD dataset.

Today I read a paper titled “Graph-based compression of dynamic 3D point cloud sequences”

The abstract is:
This paper addresses the problem of compression of 3D point cloud sequences that are characterized by moving 3D positions and color attributes.

As temporally successive point cloud frames are similar, motion estimation is key to effective compression of these sequences.

It however remains a challenging problem as the point cloud frames have varying numbers of points without explicit correspondence information.

We represent the time-varying geometry of these sequences with a set of graphs, and consider 3D positions and color attributes of the points clouds as signals on the vertices of the graphs.

We then cast motion estimation as a feature matching problem between successive graphs.

The motion is estimated on a sparse set of representative vertices using new spectral graph wavelet descriptors.

A dense motion field is eventually interpolated by solving a graph-based regularization problem.

The estimated motion is finally used for removing the temporal redundancy in the predictive coding of the 3D positions and the color characteristics of the point cloud sequences.

Experimental results demonstrate that our method is able to accurately estimate the motion between consecutive frames.

Moreover, motion estimation is shown to bring significant improvement in terms of the overall compression performance of the sequence.

To the best of our knowledge, this is the first paper that exploits both the spatial correlation inside each frame (through the graph) and the temporal correlation between the frames (through the motion estimation) to compress the color and the geometry of 3D point cloud sequences in an efficient way.

Today I read a paper titled “InAR:Inverse Augmented Reality”

The abstract is:
Augmented reality is the art to seamlessly fuse virtual objects into real ones.

In this short note, we address the opposite problem, the inverse augmented reality, that is, given a perfectly augmented reality scene where human is unable to distinguish real objects from virtual ones, how the machine could help do the job.

We show by structure from motion (SFM), a simple 3D reconstruction technique from images in computer vision, the real and virtual objects can be easily separated in the reconstructed 3D scene.

Today I read a paper titled “Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation”

The abstract is:
Recently, mid-level features have shown promising performance in computer vision.

Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features.

In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition.

Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints.

Secondly, limbs are combined into parts and the limb’s states are mapped into part states.

Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames.

These parts are referred to as Frequent Local Parts or FLPs.

The FLPs allow us to build powerful bag-of-FLP-based action representation.

This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.

Today I read a paper titled “Ownership and Agency of an Independent Supernumerary Hand Induced by an Imitation Brain-Computer Interface”

The abstract is:
To study body ownership and control, illusions that elicit these feelings in non-body objects are widely used.

Classically introduced with the Rubber Hand Illusion, these illusions have been replicated more recently in virtual reality and by using brain-computer interfaces.

Traditionally these illusions investigate the replacement of a body part by an artificial counterpart, however as brain-computer interface research develops it offers us the possibility to explore the case where non-body objects are controlled in addition to movements of our own limbs.

Therefore we propose a new illusion designed to test the feeling of ownership and control of an independent supernumerary hand.

Subjects are under the impression they control a virtual reality hand via a brain-computer interface, but in reality there is no causal connection between brain activity and virtual hand movement but correct movements are observed with 80% probability.

These imitation brain-computer interface trials are interspersed with movements in both the subjects’ real hands, which are in view throughout the experiment.

We show that subjects develop strong feelings of ownership and control over the third hand, despite only receiving visual feedback with no causal link to the actual brain signals.

Our illusion is crucially different from previously reported studies as we demonstrate independent ownership and control of the third hand without loss of ownership in the real hands.

Today I read a paper titled “Interactive 3D Face Stylization Using Sculptural Abstraction”

The abstract is:
Sculptors often deviate from geometric accuracy in order to enhance the appearance of their sculpture.

These subtle stylizations may emphasize anatomy, draw the viewer’s focus to characteristic features of the subject, or symbolize textures that might not be accurately reproduced in a particular sculptural medium, while still retaining fidelity to the unique proportions of an individual.

In this work we demonstrate an interactive system for enhancing face geometry using a class of stylizations based on visual decomposition into abstract semantic regions, which we call sculptural abstraction.

We propose an interactive two-scale optimization framework for stylization based on sculptural abstraction, allowing real-time adjustment of both global and local parameters.

We demonstrate this system’s effectiveness in enhancing physical 3D prints of scans from various sources.

Today I read a paper titled “A New Generation of Brain-Computer Interface Based on Riemannian Geometry”

The abstract is:
Based on the cumulated experience over the past 25 years in the field of Brain-Computer Interface (BCI) we can now envision a new generation of BCI.

Such BCIs will not require training; instead they will be smartly initialized using remote massive databases and will adapt to the user fast and effectively in the first minute of use.

They will be reliable, robust and will maintain good performances within and across sessions.

A general classification framework based on recent advances in Riemannian geometry and possessing these characteristics is presented.

It applies equally well to BCI based on event-related potentials (ERP), sensorimotor (mu) rhythms and steady-state evoked potential (SSEP).

The framework is very simple, both algorithmically and computationally.

Due to its simplicity, its ability to learn rapidly (with little training data) and its good across-subject and across-session generalization, this strategy a very good candidate for building a new generation of BCIs, thus we hereby propose it as a benchmark method for the field.

Today I read a paper titled “Facial Expression Cloning with Elastic and Muscle Models”

The abstract is:
Expression cloning plays an important role in facial expression synthesis.

In this paper, a novel algorithm is proposed for facial expression cloning.

The proposed algorithm first introduces a new elastic model to balance the global and local warping effects, such that the impacts from facial feature diversity among people can be minimized, and thus more effective geometric warping results can be achieved.

Furthermore, a muscle-distribution-based (MD) model is proposed, which utilizes the muscle distribution of the human face and results in more accurate facial illumination details.

In addition, we also propose a new distance-based metric to automatically select the optimal parameters such that the global and local warping effects in the elastic model can be suitably balanced.

Experimental results show that our proposed algorithm outperforms the existing methods.

Today I read a paper titled “An Evolved Neural Controller for Bipdedal Walking with Dynamic Balance”

The abstract is:
We successfully evolved a neural network controller that produces dynamic walking in a simulated bipedal robot with compliant actuators, a difficult control problem.

The evolutionary evaluation uses a detailed software simulation of a physical robot.

We describe: 1) a novel theoretical method to encourage populations to evolve “around” local optima, which employs multiple demes and fitness functions of progressively increasing difficulty, and 2) the novel genetic representation of the neural controller.