Search

Creating realistic characters that can react to the users’ or another character’s movement can benefit computer graphics, games and virtual reality hugely. However, synthesizing such reactive motions in human–human interactions is a challenging task due to the many different ways two humans can interact. While there are a number of successful researches in adapting the generative adversarial network (GAN) in synthesizing single human actions, there are very few on modeling human–human interactions. In this paper, we propose a semi-supervised GAN system that synthesizes the reactive motion of a character given the active motion from another character. Our key insights are two-fold. First, to effectively encode the complicated spatial–temporal information of a human motion, we empower the generator with a part-based long short-term memory (LSTM) module, such that the temporal movement of different limbs can be effectively modeled. We further include an attention module such that the temporal significance of the interaction can be learned, which enhances the temporal alignment of the active–reactive motion pair. Second, as the reactive motion of different types of interactions can be significantly different, we introduce a discriminator that not only tells if the generated movement is realistic or not, but also tells the class label of the interaction. This allows the use of such labels in supervising the training of the generator. We experiment with the SBU, the HHOI and the 2C datasets. The high quality of the synthetic motion demonstrates the effective design of our generator, and the discriminability of the synthesis also demonstrates the strength of our discriminator.

Recurrent neural network (RNN) has become popular for human motion prediction thanks to its ability to capture temporal dependencies. However, it has limited capacity in modeling the complex spatial relationship in the human skeletal structure. In this work, we present a novel diffusion convolutional recurrent predictor for spatial and temporal movement forecasting, with multi-step random walks traversing bidirectionally along an adaptive graph to model interdependency among body joints. In the temporal domain, existing methods rely on a single forward predictor with the produced motion deflecting to the drift route, which leads to error accumulations over time. We propose to supplement the forward predictor with a forward discriminator to alleviate such motion drift in the long term under adversarial training. The solution is further enhanced by a backward predictor and a backward discriminator to effectively reduce the error, such that the system can also look into the past to improve the prediction at early frames. The two-way spatial diffusion convolutions and two-way temporal predictors together form a quadruple network.\ud \ud Furthermore, we train our framework by modeling the velocity from observed motion dynamics instead of static poses to predict future movements that effectively reduces the discontinuity problem at early prediction. Our method outperforms the state of the arts on both 3D and 2D datasets, including the Human3.6M, CMU Motion Capture and Penn Action datasets. The results also show that our method correctly predicts both high-dynamic and low-dynamic moving trends with less motion drift.

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods., Journal of Medical Systems

Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by learning a natural motion manifold using deep learning to address the shortcomings of traditional data-driven approaches. However, previous methods can be sub-optimal for two reasons. First, the skeletal information has not been fully utilized for feature extraction. Unlike images, it is difficult to define spatial proximity in skeletal motions in the way that deep networks can be applied. Second, motion is time-series data with strong multi-modal temporal correlations. A frame could be followed by several candidate frames leading to different motions; long-range dependencies exist where a number of frames in the beginning correlate to a number of frames later. Ineffective modeling would either under-estimate the multi-modality and variance, resulting in featureless mean motion or over-estimate them resulting in jittery motions. In this paper, we propose a new deep network to tackle these challenges by creating a natural motion manifold that is versatile for many applications. The network has a new spatial component for feature extraction. It is also equipped with a new batch prediction model that predicts a large number of frames at once, such that long-term temporally-based objective functions can be employed to correctly learn the motion multi-modality and variances. With our system, long-duration motions can be predicted/synthesized using an open-loop setup where the motion retains the dynamics accurately. It can also be used for denoising corrupted motions and synthesizing new motions with given control signals. We demonstrate that our system can create superior results comparing to existing work in multiple applications., 12 pages, Accepted in IEEE Transaction on Visualization and Computer Graphics

In this work, we proposed a novel method, called Local Modified Zernike Moment per unit Mass (LMZMPM), for face recognition, which is invariant to illumination, scaling, noise, in-plane rotation, and translation, along with other orthogonal and inherent properties of the Zernike Moments (ZMs). The proposed LMZMPM is computed for each pixel in a neighborhood of size $3\times 3$ , and then considers the complex tuple that contains both the phase and magnitude coefficients of LMZMPM as the extracted features. As it contains both the phase and the magnitude components of the complex feature, it has more information about the image and thus preserves both the edge and structural information. We also propose a hybrid similarity measure, combining the Jaccard Similarity with the L1 distance, and applied to the extracted feature set for classification. The feasibility of the proposed LMZMPM technique on varying illumination has been evaluated on the CMU-PIE and the extended Yale B databases with an average Rank-1 Recognition (R1R) accuracy of 99.8% and 98.66% respectively. To assess the reliability of the method with variations in noise, rotation, scaling, and translation, we evaluate it on the AR database and obtain an average R1R higher than that of recent state-of-the-art methods. The proposed method shows a very high recognition rate on Heterogeneous Face Recognition as well, with 100% on CUFS, and 98.80% on CASIA-HFB.

PurposeA core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In our pilot study published in, Sakkos:SKIMA 2019, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly but also features semantic transformations of illumination which enhance the generalisation of the model.Design/methodology/approachIn our pilot study published in SKIMA 2019, the proposed framework successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. In this paper, we further enhance the data augmentation framework by proposing new variations in image appearance both locally and globally.FindingsExperimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place.Originality/valueSuch data augmentation allows us to effectively train an illumination-invariant deep learning model for BGS. We further propose a post-processing method that removes noise from the output binary map of segmentation, resulting in a cleaner, more accurate segmentation map that can generalise to multiple scenes of different conditions. We show that it is possible to train deep learning models even with very limited training samples. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation

Traditional methods for motion comparison consider features from individual characters. However, the semantic meaning of many human activities is usually defined by the interaction between them, such as a high-five interaction of two characters. There is little success in adapting interaction-based features in activity comparison, as they either do not have a fixed topology or are in high dimensional. In this paper, we propose a unified framework for activity comparison from the interaction point of view. Our new metric evaluates the similarity of interaction by adapting the Earth Mover’s Distance onto a customized geometric mesh structure that represents spatial-temporal interactions. This allows us to compare different classes of interactions and discover their intrinsic semantic similarity. We created five interaction databases of different natures, covering both two characters (synthetic and real-people) and character-object interactions, which are open for public uses. We demonstrate how the proposed metric aligns well with the semantic meaning of the interaction. We also apply the metric in interaction retrieval and show how it outperforms existing ones. The proposed method can be used for unsupervised activity detection in monitoring systems and activity retrieval in smart animation systems.

3D car models are heavily used in computer games, visual effects, and even automotive designs. As a result, producing such models with minimal labour costs is increasingly more important. To tackle the challenge, we propose a novel system to reconstruct a 3D car using a single sketch image. The system learns from a synthetic database of 3D car models and their corresponding 2D contour sketches and segmentation masks, allowing effective training with minimal data collection cost. The core of the system is a machine learning pipeline that combines the use of a generative adversarial network (GAN) and lazy learning. GAN, being a deep learning method, is capable of modelling complicated data distributions, enabling the effective modelling of a large variety of cars. Its major weakness is that as a global method, modelling the fine details in the local region is challenging. Lazy learning works well to preserve local features by generating a local subspace with relevant data samples. We demonstrate that the combined use of GAN and lazy learning produces is able to produce high-quality results, in which different types of cars with complicated local features can be generated effectively with a single sketch. Our method outperforms existing ones using other machine learning structures such as the variational autoencoder.

Synthesizing multi-character interactions is a challenging task due to the complex and varied interactions between the characters. In particular, precise spatiotemporal alignment between characters is required in generating close interactions such as dancing and fighting. Existing work in generating multi-character interactions focuses on generating a single type of reactive motion for a given sequence which results in a lack of variety of the resultant motions. In this paper, we propose a novel way to create realistic human reactive motions which are not presented in the given dataset by mixing and matching different types of close interactions. We propose a Conditional Hierarchical Generative Adversarial Network with Multi-Hot Class Embedding to generate the Mix and Match reactive motions of the follower from a given motion sequence of the leader. Experiments are conducted on both noisy (depth-based) and high-quality (MoCap-based) interaction datasets. The quantitative and qualitative results show that our approach outperforms the state-of-the-art methods on the given datasets. We also provide an augmented dataset with realistic reactive motions to stimulate future research in this area. The code is available at https://github.com/Aman-Goel1/IMM, Comment: Accepted to SCA 2022 (will be published in CGF)

Motion control algorithms in the presence of pedestrians are critical for the development of safe and reliable Autonomous Vehicles (AVs). Traditional motion control algorithms rely on manually designed decision-making policies which neglect the mutual interactions between AVs and pedestrians. On the other hand, recent advances in Deep Reinforcement Learning allow for the automatic learning of policies without manual designs. To tackle the problem of decision-making in the presence of pedestrians, the authors introduce a framework based on Social Value Orientation and Deep Reinforcement Learning (DRL) that is capable of generating decision-making policies with different driving styles. The policy is trained using stateof- the-art DRL algorithms in a simulated environment. A novel computationally-efficient pedestrian model that is suitable for DRL training is also introduced. We perform experiments to validate our framework and we conduct a comparative analysis of the policies obtained with two different model-free Deep Reinforcement Learning Algorithms. Simulations results show how the developed model exhibits natural driving behaviours, such as short-stopping, to facilitate the pedestrian’s crossing.

Millions of people throughout the world have been harmed by plastic pollution. There are microscopic pieces of plastic in the food we eat, the water we drink, and even the air we breathe. Every year, the average human consumes 74,000 microplastics, which has a significant impact on their health. This pollution must be addressed before it has a significant negative influence on the population. This research benchmarks six state-of-the-art convolutional neural network models pre-trained on the ImageNet Dataset. The models Resnet-50, ResNeXt, MobileNet_v2, DenseNet, SchuffleNet and AlexNet were tested and evaluated on the WaDaBa plastic dataset, to classify plastic types based on their resin codes by integrating the power of transfer learning. The accuracy and training time for each model has been compared in this research. Due to the imbalance in the data, the under-sampling approach has been used. The ResNeXt model attains the highest accuracy in fourteen minutes.

As Autonomous Vehicles (AV) are becoming a reality, the design of efficient motion control algorithms will have to deal with the unpredictable and interactive nature of other road users. Current AV motion planning algorithms suffer from the freezing robot problem, as they often tend to overestimate collision risks. To tackle this problem and design AV that behave human-like, we integrate a concept from Psychology called Social Value Orientation into the Reinforcement Learning (RL) framework. The addition of a social term in the reward function design allows us to tune the AV behaviour towards the pedestrian from a more reckless to an extremely prudent one. We train the vehicle agent with a state of the art RL algorithm and show that Social Value Orientation is an effective tool to obtain pro-social AV behaviour.

The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In our previous work, we explored the feasibility of extracting pose-based features from video sequences to automatically classify infant body movement into two categories, normal and abnormal. The classification was based upon the GMA, which was carried out on the video data by an independent expert reviewer. In this paper we extend our previous work by extracting the normalised pose-based feature sets, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for use in new deep learning architectures. We explore the viability of using these pose-based feature sets for automated classification within a deep learning framework by carrying out extensive experiments on five new deep learning architectures. Experimental results show that the proposed fully connected neural network FCNet performed robustly across different feature sets. Furthermore, the proposed convolutional neural network architectures demonstrated excellent performance in handling features in higher dimensionality. We make the code, extracted features and associated GMA labels publicly available.

We introduce a data-driven method to generate a large number of plausible, closely interacting 3D human pose-pairs, for a given motion category, e.g., wrestling or salsa dance. With much difficulty in acquiring close interactions using 3D sensors, our approach utilizes abundant existing video data which cover many human activities. Instead of treating the data generation problem as one of reconstruction, either through 3D acquisition or direct 2D-to-3D data lifting from video annotations, we present a solution based on Markov Chain Monte Carlo (MCMC) sampling. Given a motion category and a set of video frames depicting the motion with the 2D pose-pair in each frame annotated, we start the sampling with one or few seed 3D pose-pairs which are manually created based on the target motion category. The initial set is then augmented by MCMC sampling around the seeds, via the Metropolis-Hastings algorithm and guided by a probability density function (PDF) that is defined by two terms to bias the sampling towards 3D pose-pairs that are physically valid and plausible for the motion category. With a focus on efficient sampling over the space of close interactions, rather than pose spaces, we develop a novel representation called interaction coordinates (IC) to encode both poses and their interactions in an integrated manner. Plausibility of a 3D pose-pair is then defined based on the IC and with respect to the annotated 2D pose-pairs from video. We show that our sampling-based approach is able to efficiently synthesize a large volume of plausible, closely interacting 3D pose-pairs which provide a good coverage of the input 2D pose-pairs.

Providing early diagnosis of cerebral palsy (CP) is key to enhancing the developmental outcomes for those affected. Diagnostic tools such as the General Movements Assessment (GMA), have produced promising results in early diagnosis, however these manual methods can be laborious. In this paper, we propose a new framework for the automated classification of infant body movements, based upon the GMA, which unlike previous methods, also incorporates a visualization framework to aid with interpretability. Our proposed framework segments extracted features to detect the presence of Fidgety Movements (FMs) associated with the GMA spatiotemporally. These features are then used to identify the body-parts with the greatest contribution towards a classification decision and highlight the related body-part segment providing visual feedback to the user. We quantitatively compare the proposed framework's classification performance with several other methods from the literature and qualitatively evaluate the visualization's veracity. Our experimental results show that the proposed method performs more robustly than comparable techniques in this setting whilst simultaneously providing relevant visual interpretability., Comment: Proceedings of the 2021 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), accepted, 2021

Knowledge about individual body shape has numerous applications in various domains such as healthcare, fashion and personalized entertainment. Most of the depth based whole body scanners need multiple cameras surrounding the user and requiring the user to keep a canonical pose strictly during capturing depth images. These scanning devices are expensive and need professional knowledge for operation. In order to make 3D scanning as easy-to-use and fast as possible, there is a great demand to simplify the process and to reduce the hardware requirements. In this paper, we propose a deep learning algorithm,\ud dubbed 3DBodyNet, to rapidly reconstruct the 3D shape of human bodies using a single commodity depth camera. As easy-to-use as taking a photo using a mobile phone, our algorithm only needs two depth images of the front-facing and back-facing bodies. The proposed algorithm has strong operability since it is insensitive to the pose and the pose variations between the two depth images. It can also reconstruct an accurate body shape for users under tight/loose clothing. Another advantage of our method is the ability to generate an animatable human body model. Extensive experimental results show that the proposed method enables robust and easy-to-use animatable human body\ud reconstruction, and outperforms the state-of-the-art methods with respect to running time and accuracy.

This paper addresses the problem of recognizing human-human interaction from skeletal sequences. Existing methods are mainly designed to classify single human action. Many of them simply stack the movement features of two characters to deal with human interaction, while neglecting the abundant relationships between characters. In this paper, we propose a novel two-stream recurrent neural network by adopting the geometric features from both single actions and interactions to describe the spatial correlations with different discriminative abilities. The first stream is constructed under pairwise joint distance (PJD) in a fully-connected mesh to categorize the interactions with explicit distance patterns. To better distinguish similar interactions, in the second stream, we combine PJD with the spatial features from individual joint positions using graph convolutions to detect the implicit correlations among joints, where the joint connections in the graph are adaptive for flexible correlations. After spatial modeling, each stream is fed to a bi-directional LSTM to encode two-way temporal properties. To take advantage of the diverse discriminative power of the two streams, we come up with a late fusion algorithm to combine their output predictions concerning information entropy. Experimental results show that the proposed framework achieves state-of-the-art performance on 3D and comparable performance on 2D interaction datasets. Moreover, the late fusion results demonstrate the effectiveness of improving the recognition accuracy compared with single streams.

Facial makeup style transfer is an extremely challenging sub-field of image-to-image-translation. Due to this difficulty, state-of-the-art results are mostly reliant on the Face Parsing Algorithm, which segments a face into parts in order to easily extract makeup features. However, this algorithm can only work well on high-definition images where facial features can be accurately extracted. Faces in many real-world photos, such as those including a large background or multiple people, are typically of low-resolution, which considerably hinders state-of-the-art algorithms. In this paper, we propose an end-to-end holistic approach to effectively transfer makeup styles between two low-resolution images. The idea is built upon a novel weighted multi-scale spatial attention module, which identifies salient pixel regions on low-resolution images in multiple scales, and uses channel attention to determine the most effective attention map. This design provides two benefits: low-resolution images are usually blurry to different extents, so a multi-scale architecture can select the most effective convolution kernel size to implement spatial attention; makeup is applied on both a macro-level (foundation, fake tan) and a micro-level (eyeliner, lipstick) so different scales can excel in extracting different makeup features. We develop an Augmented CycleGAN network that embeds our attention modules at selected layers to most effectively transfer makeup. Our system is tested with the FBD data set, which consists of many low-resolution facial images, and demonstrate that it outperforms state-of-the-art methods, particularly in transferring makeup for blurry images and partially occluded images.

Early prediction of cerebral palsy is essential as it leads to early treatment and monitoring. Deep learning has shown promising results in biomedical engineering thanks to its capacity of modelling complicated data with its non-linear architecture. However, due to their complex structure, deep learning models are generally not interpretable by humans, making it difficult for clinicians to rely on the findings. In this paper, we propose a channel attention module for deep learning models to predict cerebral palsy from infants' body movements, which highlights the key features (i.e. body joints) the model identifies as important, thereby indicating why certain diagnostic results are found. To highlight the capacity of the deep network in modelling input features, we utilize raw joint positions instead of hand-crafted features. We validate our system with a real-world infant movement dataset. Our proposed channel attention module enables the visualization of the vital joints to this disease that the network considers. Our system achieves 91.67% accuracy, suppressing other state-of-the-art deep learning methods.

Facial symmetry is a key component in quantifying the perception of beauty. In this paper, we propose a set of facial features computed from facial landmarks which can be extracted at a low computational cost. We quantitatively evaluated the proposed features for predicting perceived attractiveness from human portraits on four benchmark datasets (SCUT-FBP, SCUT-FBP5500, FACES and Chicago Face Database). Experimental results showed that the performance of the proposed features is comparable to those extracted from a set with much denser facial landmarks. The computation of facial features was also implemented as an augmented reality (AR) app developed on Android OS. The app overlays four types of measurements and guidelines over a live video stream, while the facial measurements are computed from the tracked facial landmarks at run time. The developed app can be used to assist plastic surgeons in assessing facial symmetry when planning reconstructive facial surgeries.

Electrocardiograph (ECG) is employed as a primary tool for diagnosing cardiovascular diseases (CVD) in the hospital, which often helps in the early detection of such ailments. ECG signals provide a framework to probe the underlying properties and enhance the initial diagnosis obtained via traditional tools and patient-doctor dialogues. It provides cardiologists with inferences regarding more serious cases. Notwithstanding its proven utility, deciphering large datasets to determine appropriate information remains a challenge in ECG-based CVD diagnosis and treatment. Our study presents a deep neural network (DNN) strategy to ameliorate the aforementioned difficulties. Our strategy consists of a learning stage where classification accuracy is improved via a robust feature extraction. This is followed using a genetic algorithm (GA) process to aggregate the best combination of feature extraction and classification. The MIT-BIH Arrhythmia was employed in the validation to identify five arrhythmia categories based on the association for the advancement of medical instrumentation (AAMI) standard. The performance of the proposed technique alongside state-of-the-art in the area shows an increase of 0.94 and 0.953 in terms of average accuracy and F1 score, respectively. The proposed model could serve as an analytic module to alert users and/or medical experts when anomalies are detected in the acquired ECG data in a smart healthcare framework.

Recent advancements in deep learning have significantly improved the accuracy of multi-person pose estimation from RGB images. However, these deep learning methods typically rely on a large number of deep refinement modules to refine the features of body joints and limbs, which hugely reduce the run-time speed and therefore limit the application domain. In this paper, we propose a feature transfer framework to capture the concurrent correlations between body joint and limb features. The concurrent correlations of these features form a complementary structural relationship, which mutually strengthens the network’s inferences and reduces the needs of refinement modules. The transfer sub-network is implemented with multiple convolutional layers, and is merged with the body part detection network to form an end-to-end system. The transfer relationship is automatically learned from ground-truth data instead of being manually encoded, resulting in a more general and efficient design. The proposed framework is validated on the multiple popular multi-person pose estimation benchmarks - MPII, COCO 2018 and PoseTrack 2017 and 2018. Experimental results show that our method not only significantly increases the inference speed to 73.8 frame per second (FPS), but also attains comparable state-of-the-art performance.

State-of-the-art intelligent versatile applications provoke the usage of full 3D, depth-based streams, especially in the scenarios of intelligent remote control and communications, where virtual and augmented reality will soon become outdated and are forecasted to be replaced by point cloud streams providing explorable 3D environments of communication and industrial data. One of the most novel approaches employed in modern object reconstruction methods is to use a priori knowledge of the objects that are being reconstructed. Our approach is different as we strive to reconstruct a 3D object within much more difficult scenarios of limited data availability. Data stream is often limited by insufficient depth camera coverage and, as a result, the objects are occluded and data is lost. Our proposed hybrid artificial neural network modifications have improved the reconstruction results by 8.53% which allows us for much more precise filling of occluded object sides and reduction of noise during the process. Furthermore, the addition of object segmentation masks and the individual object instance classification is a leap forward towards a general-purpose scene reconstruction as opposed to a single object reconstruction task due to the ability to mask out overlapping object instances and using only masked object area in the reconstruction process.

Person and vehicle re-identification (re-ID) are important challenges for the analysis of the burgeoning collection of urban surveillance videos. To efficiently evaluate such videos, which are populated with both vehicles and pedestrians, it would be preferable to have one unified framework with effective performance across both domains. Unfortunately, due to the contrasting composition of humans and vehicles, no architecture has yet been established that can adequately perform both tasks. We release a Person and Vehicle Unified Data Set (PVUD) comprising of both pedestrians and vehicles from popular existing re-ID data sets, in order to better model the data that we would expect to find in the real world. We exploit the generalisation ability of metric learning to propose a re-ID framework that can learn to re-identify humans and vehicles simultaneously. We design our network, MidTriNet, to harness the power of mid-level features to develop better representations for the re-ID tasks. We help the system to handle mixed data by appending unification terms with additional hard negative and hard positive mining to MidTriNet. We attain comparable accuracy training on PVUD to training on the comprising data sets separately, supporting the system's generalisation power. To further demonstrate the effectiveness of our framework, we also obtain results better than, or competitive with, the state-of-the-art on each of the Market-1501, CUHK03, VehicleID and VeRi data sets.

Emotion is considered to be a core element in performances. In computer animation, both body motions and facial expressions are two popular mediums for a character to express the emotion. However, there has been limited research in studying how to effectively synthesize these two types of character movements using different levels of emotion strength with intuitive control, which is difficult to be modeled effectively. In this work, we explore a common model that can be used to represent the emotion for the applications of body motions and facial expressions synthesis. Unlike previous work that encode emotions into discrete motion style descriptors, we propose a continuous control indicator called emotion strength by controlling which a data‐driven approach is presented to synthesize motions with fine control over emotions. Rather than interpolating motion features to synthesize new motion as in existing work, our method explicitly learns a model mapping low‐level motion features to the emotion strength. Because the motion synthesis model is learned in the training stage, the computation time required for synthesizing motions at run time is very low. We further demonstrate the generality of our proposed framework by editing 2D face images using relative emotion strength. As a result, our method can be applied to interactive applications such as computer games, image editing tools, and virtual reality applications, as well as offline applications such as animation and movie production.

Efficient car shape design is a challenging problem in both the automotive industry and the computer animation/games industry. In this paper, we present a system to reconstruct the 3D car shape from a single 2D sketch image. To learn the correlation between 2D sketches and 3D cars, we propose a Variational Autoencoder deep neural network that takes a 2D sketch and generates a set of multi-view depth & mask images, which are more effective representation comparing to 3D mesh, and can be combined to form the 3D car shape. To ensure the volume and diversity of the training data, we propose a feature-preserving car mesh augmentation pipeline for data augmentation. Since deep learning has limited capacity to reconstruct fine-detail features, we propose a lazy learning approach that constructs a small subspace based on a few relevant car samples in the database. Due to the small size of such a subspace, fine details can be represented effectively with a small number of parameters. With a low-cost optimization process, a high-quality car with detailed features is created. Experimental results show that the system performs consistently to create highly realistic cars of substantially different shape and topology, with a very low computational cost.

We propose a novel end-to-end deep learning framework, capable of 3D human shape reconstruction from a 2D image without the need of a 3D prior parametric model. We employ a “prior-less” representation of the human shape using unordered point clouds. Due to the lack of prior information, comparing the generated and ground truth point clouds to evaluate the reconstruction error is challenging. We solve this problem by proposing an Earth Mover’s Distance (EMD) function to find the optimal mapping between point clouds. Our experimental results show that we are able to obtain a visually accurate estimation of the 3D human shape from a single 2D image, with some inaccuracy for heavily occluded parts.

With the rapid increase in individuals participating in resistance training activities, the number of injuries pertaining to these activities has also grown just as aggressively. Diagnosing the causes of injuries and discomfort requires a large amount of resources from highly experienced physiotherapists. In this paper, we propose a new framework to analyse and visualize movement patterns during performance of four major compound lifts. The analysis generated will be used to efficiently determine whether the exercises are being performed correctly, ensuring anatomy remains within its functional range of motion, in order to prevent strain or discomfort that may lead to injury.

With the development of e-shopping, there is a significant growth in clothing purchases online. However, the virtual clothing fit evaluation is still under-researched. In the literature, the thickness of the air layer between the human body and clothes is a dominant geometric indicator to evaluate the clothing fit. However, such an approach has only been applied to the stationary positions of the mannequin/human body. Physical indicators such as the pressure/tension of a virtual garment fitted on the virtual body in a continuous motion are also proposed for clothing fit evaluation. Neither geometric nor physical evaluations consider the interaction of the garment with the body, e.g., the sliding of the garment along the human body. In this study, a new framework was proposed to automatically determine the dynamic air gap thickness. First, the dynamic dressed character sequence was simulated in three-dimensional (3D) clothing software via importing the body parameters, cloth parameters, and a walking motion. Second, a cost function was defined to convert the garment in the previous frame to the local coordinate of the next frame. The dynamic air gap thickness between clothes and the human body was determined. Third, a new metric, the 3D garment vector field was proposed to represent the movement flow of the dynamic virtual garment, whose directional changes are calculated by cosine similarity. Experimental results show that our method is more sensitive to the small air gap thickness changes compared with state-of-the-art methods, allowing it to more effectively evaluate clothing fit in a virtual environment.

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask that is randomly generated. Such data allows us to effectively train an illumination-invariant deep learning model for BGS. Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation., SKIMA 2019 - Best Paper Award

The pursuit of early diagnosis of cerebral palsy has been an active research area with some very promising results using tools such as the General Movements Assessment (GMA). In this paper, we conducted a pilot study on extracting important information from video sequences to classify the body movement into two categories, normal and abnormal, and compared the results provided by an independent expert reviewer based on GMA. We present two new pose-based features, Histograms of Joint Orientation 2D (HOJO2D) and Histograms of Joint Displacement 2D (HOJD2D), for the pose-based analysis and classification of infant body movement from video footage. We extract the 2D skeletal joint locations from 2D RGB images using Cao et al.’s method [1]. Using the MINI-RGBD dataset [2], we further segment the body into local regions to extract part specific features. As a result, the pose and the degree of displacement are represented by histograms of normalised data. To demonstrate the effectiveness of the proposed features, we trained several classifiers using combinations of HOJO2D and HOJD2D features and conducted a series of experiments to classify the body movement into categories. The classification algorithms used included k-Nearest Neighbour (kNN, k=1 and k=3), Linear Discriminant Analysis (LDA) and the Ensemble classifier. Encouraging results were attained, with high accuracy (91.67%) obtained using the Ensemble classifier.

In this paper, a new method for robot path rolling planning in a static and unknown environment based on grid modelling is proposed. In an unknown scene, a local navigation optimization path for the robot is generated intelligently by ant colony optimization (ACO) combined with the environment information of robot’s local view and target information. The robot plans a new navigation path dynamically after certain steps along the previous local navigation path, and always moves along the optimized navigation path which is dynamically modified. The robot will move forward to the target point directly along the local optimization path when the target is within the current view of the robot. This method presents a more intelligent sub-goal mapping method comparing to the traditional rolling window approach. Besides, the path that is part of the generated local path based on the ACO between the current position and the next position of the robot is further optimized using particle swarm optimization (PSO), which resulted in a hybrid metaheuristic algorithm that incorporates ACO and PSO. Simulation results show that the robot can reach the target grid along a global optimization path without collision.

Given the complexity of the human facial anatomy, animating facial expressions and lip movements for speech is a very time-consuming and tedious task. In this paper, a new text-to-animation framework for facial animation synthesis is proposed. The core idea is to improve the expressiveness of lip-sync animation by incorporating facial expressions in 3D animated characters. This idea is realized as a plug-in in Autodesk Maya, one of the most popular animation platforms in the industry, such that professional animators can effectively apply the method in their existing work. We evaluate the proposed system by conducting two sets of surveys, in which both novice and experienced users participate in the user study to provide feedback and evaluations from different perspectives. The results of the survey highlights the effectiveness of creating realistic facial animations with the use of emotion expressions. Video demos of the synthesized animations are available online at https://git.io/fx5U3

Musculoskeletal and neurological disorders are common devastating companions of ageing, leading to a reduction in quality of life and increased mortality. Gait analysis is a popular method for diagnosing these disorders. However, manually analyzing the motion data is a labor-intensive task, and the quality of the results depends on the experience of the doctors. In this paper, we propose an automatic framework for classifying musculoskeletal and neurological disorders among older people based on 3D motion data. We also propose two new features to capture the relationship between joints across frames, known as 3D Relative Joint Displacement (3DRJDP) and 6D Symmetric Relative Joint Displacement (6DSymRJDP), such that the relative movement between joints can be analyzed. To optimize the classification performance, we adapt feature selection methods to choose an optimal feature set from the raw feature input. Experimental results show that we achieve a classification accuracy of 84.29% using the proposed relative joint features, outperforming existing features that focus on the movement of individual joints. Considering the limited open motion database for gait analysis focusing on such disorders, we construct a comprehensive, openly accessible 3D full-body motion database from 45 subjects.

Connecting network cables to network switches is a time-consuming and inefficient task, and requires extensive documentation and preparation beforehand to ensure no service faults are encountered by the users. In this paper, a new AR smartphone application that overlays network switch information over the user’s vision is designed and developed for real working environment to increase user’s efficiency in working with a network switch. Specifically, the prototype of the AR App is developed on the Android platform using both the Unity game engine and Vuforia AR library and connecting to the network switch to retrieve network information through telnet. By using the camera on the smartphone for capturing the visual information from the working environment, i.e. the network switch in this App, the network switch information such as speed, types, etc. will be overlaid on each port on the smartphone screen. A user study was conducted to evaluate the effectiveness of the AR App to assist users in performing network tasks. In particular, participants were tasked with connecting switchports to a patch panel to match up corresponding configurations. After three tests, it was found that the times for completion and mistakes made were reduced in the final test when compared to the first. This highlights the positive effects of the application in improving the user’s efficiency.

Network intrusion is a growing threat with potentially severe impacts, which can be damaging in multiple ways to network infrastructures and digital/intellectual assets in the cyberspace. The approach most commonly employed to combat network intrusion is the development of attack detection systems via machine learning and data mining techniques. These systems can identify and disconnect malicious network traffic, thereby helping to protect networks. This chapter systematically reviews two groups of common intrusion detection systems using fuzzy logic and artificial neural networks, and evaluates them by utilizing the widely used KDD 99 benchmark dataset. Based on the findings, the key challenges and opportunities in addressing cyberattacks using artificial intelligence techniques are summarized and future work suggested.

The recent advancement of motion recognition using Microsoft Kinect stimulates many new ideas in motion capture and virtual reality applications. Utilizing a pattern recognition algorithm, Kinect can determine the positions of different body parts from the user. However, due to the use of a single-depth camera, recognition accuracy drops significantly when the parts are occluded. This hugely limits the usability of applications that involve interaction with external objects, such as sport training or exercising systems. The problem becomes more critical when Kinect incorrectly perceives body parts. This is because applications have limited information about the recognition correctness, and using those parts to synthesize body postures would result in serious visual artifacts. In this paper, we propose a new method to reconstruct valid movement from incomplete and noisy postures captured by Kinect. We first design a set of measurements that objectively evaluates the degree of reliability on each tracked body part. By incorporating the reliability estimation into a motion database query during run time, we obtain a set of similar postures that are kinematically valid. These postures are used to construct a latent space, which is known as the natural posture space in our system, with local principle component analysis. We finally apply frame-based optimization in the space to synthesize a new posture that closely resembles the true user posture while satisfying kinematic constraints. Experimental results show that our method can significantly improve the quality of the recognized posture under severely occluded environments, such as a person exercising with a basketball or moving in a small room.

This article presents a new framework for synthesizing motion of a virtual character in response to the actions performed by a user-controlled character in real time. In particular, the proposed method can handle scenes in which the characters are closely interacting with each other such as those in partner dancing and fighting. In such interactions, coordinating the virtual characters with the human player automatically is extremely difficult because the system has to predict the intention of the player character. In addition, the style variations from different users affect the accuracy in recognizing the movements of the player character when determining the responses of the virtual character. To solve these problems, our framework makes use of the spatial relationship-based representation of the body parts called interaction mesh, which has been proven effective for motion adaptation. The method is computationally efficient, enabling real-time character control for interactive applications. We demonstrate its effectiveness and versatility in synthesizing a wide variety of motions with close interactions.

Motion analysis and visualization are crucial in sports science for sports training and performance evaluation. While primitive computational methods have been proposed for simple analysis such as postures and movements, few can evaluate the high-level quality of sports players such as their skill levels and strategies. We propose a visualization tool to help visualizing boxers' motions and assess their skill levels. Our system automatically builds a graph-based representation from motion capture data and reduces the dimension of the graph onto a 3D space so that it can be easily visualized and understood. In particular, our system allows easy understanding of the boxer's boxing behaviours, preferred actions, potential strength and weakness. We demonstrate the effectiveness of our system on different boxers' motions. Our system not only serves as a tool for visualization, it also provides intuitive motion analysis that can be further used beyond sports science.