Search

Reinforcement Learning (RL) based control algorithms can learn the control strategies for nonlinear and uncertain environment during interacting with it. Guided by the rewards generated by environment, a RL agent can learn the control strategy directly in a model-free way instead of investigating the dynamic model of the environment. In the paper, we propose the sampled-data RL control strategy to reduce the computational demand. In the sampled-data control strategy, the whole control system is of a hybrid structure, in which the plant is of continuous structure while the controller (RL agent) adopts a discrete structure. Given that the continuous states of the plant will be the input of the agent, the state–action value function is approximated by the fully connected feed-forward neural networks (FCFFNN). Instead of learning the controller at every step during the interaction with the environment, the learning and acting stages are decoupled to learn the control strategy more effectively through experience replay. In the acting stage, the most effective experience obtained during the interaction with the environment will be stored and during the learning stage, the stored experience will be replayed to customized times, which helps enhance the experience replay process. The effectiveness of proposed approach will be verified by simulation examples.

Optical microrobots have a wide range of applications in biomedical research for both in vitro and in vivo studies. In most microrobotic systems, the video captured by a monocular camera is the only way for visualizing the movements of microrobots, and only planar motion, in general, can be captured by a monocular camera system. Accurate depth estimation is essential for 3D reconstruction or autofocusing of microplatforms, while the pose and depth estimation are necessary to enhance the 3D perception of the microrobotic systems to enable dexterous micromanipulation and other tasks. In this paper, we propose a data-driven method for pose and depth estimation in an optically manipulated microrobotic system. Focus measurement is used to obtain features for Gaussian Process Regression (GPR), which enables precise depth estimation. For mobile microrobots with varying poses, a novel method is developed based on a deep residual neural network with the incorporation of prior domain knowledge about the optical microrobots encoded via GPR. The method can simultaneously track microrobots with complex shapes and estimate the pose and depth values of the optical microrobots. Cross-validation has been conducted to demonstrate the submicron accuracy of the proposed method and precise pose and depth perception for microrobots. We further demonstrate the generalizability of the method by adapting it to microrobots of different shapes using transfer learning with few-shot calibration. Intuitive visualization is provided to facilitate effective human-robot interaction during micromanipulation based on pose and depth estimation results.

Electroencephalographic (EEG) signals have been widely used in medical applications, yet the use of EEG signals as user identification systems for healthcare and Internet of Things (IoT) systems has only gained interests in the last few years. The advantages of EEG-based user identification systems lie in its dynamic property and uniqueness among different individuals. However, it is for this reason that manually designed features are not always adapted to the needs. Therefore, a novel approach based on 1D Convolutional Long Short-term Memory Neural Network (1D-Convolutional LSTM) for EEG-based user identification system is proposed in this paper. The performance of the proposed approach was validated with a public database consists of EEG data of 109 subjects. The experimental results showed that the proposed network has a very high averaged accuracy of 99.58%, when using only 16 channels of EEG signals, which outperforms the state-of-the-art EEG-based user identification methods. The combined use of CNNs and LSTMs in the proposed 1D-Convolutional LSTM can greatly improve the accuracy of user identification systems by utilizing the spatiotemporal features of the EEG signals with LSTM, and lowering cost of the systems by reducing the number of EEG electrodes used in the systems.

Camera-based passive dietary intake monitoring is able to continuously capture the eating episodes of a subject, recording rich visual information, such as the type and volume of food being consumed, as well as the eating behaviors of the subject. However, there currently is no method that is able to incorporate these visual clues and provide a comprehensive context of dietary intake from passive recording (e.g., is the subject sharing food with others, what food the subject is eating, and how much food is left in the bowl). On the other hand, privacy is a major concern while egocentric wearable cameras are used for capturing. In this article, we propose a privacy-preserved secure solution (i.e., egocentric image captioning) for dietary assessment with passive monitoring, which unifies food recognition, volume estimation, and scene understanding. By converting images into rich text descriptions, nutritionists can assess individual dietary intake based on the captions instead of the original images, reducing the risk of privacy leakage from images. To this end, an egocentric dietary image captioning dataset has been built, which consists of in-the-wild images captured by head-worn and chest-worn cameras in field studies in Ghana. A novel transformer-based architecture is designed to caption egocentric dietary images. Comprehensive experiments have been conducted to evaluate the effectiveness and to justify the design of the proposed architecture for egocentric dietary image captioning. To the best of our knowledge, this is the first work that applies image captioning for dietary intake assessment in real-life settings.

Research on generating or processing point clouds has become an increasingly popular domain in robotic research due to its extensive applications, such as robotic grasping, augmented reality and autonomous vehicle navigation. In this paper, we explore a new research area on point clouds - Learning to rank 3D models captured from a single depth image. In the Learning To Rank (LTR) task, we aim at optimizing the order of a list of 3D models according to the given query. Inspired by the recent advances in Natural Language Processing (NLP), we propose a novel framework, namely Deep3DRanker, for ranking 3D models by leveraging graph-based encoding and self-attention mechanisms. Comprehensive experiments are conducted to validate our methods on publicly available YCB synthetic and YCB video datasets. The promising results have shown that our proposed framework is generic enough to be applicable with any combinations of randomly positioned, oriented, and unseen object items with accuracy ranging from 59.2% to 94.9%, which shows great potentials of the proposed framework for robotic applications, in particular, for making decisions under different circumstances.

In this paper, we address the problem of forecasting the trajectory of an egocentric camera wearer (ego-person) in crowded spaces. The trajectory forecasting ability learned from the data of different camera wearers walking around in the real world can be transferred to assist visually impaired people in navigation, as well as to instill human navigation behaviours in mobile robots, enabling better human-robot interactions. To this end, a novel egocentric human trajectory forecasting dataset was constructed, containing real trajectories of people navigating in crowded spaces wearing a camera, as well as extracted rich contextual data. We extract and utilize three different modalities to forecast the trajectory of the camera wearer, i.e., his/her past trajectory, the past trajectories of nearby people, and the environment such as the scene semantics or the depth of the scene. A Transformer-based encoder-decoder neural network model, integrated with a novel cascaded cross-attention mechanism that fuses multiple modalities, has been designed to predict the future trajectory of the camera wearer. Extensive experiments have been conducted, with results showing that our model outperforms the state-of-the-art methods in egocentric human trajectory forecasting.

Accurate prediction of future person location and movement trajectory from an egocentric wearable camera can benefit a wide range of applications, such as assisting visually impaired people in navigation, and the development of mobility assistance for people with disability. In this work, a new egocentric dataset was constructed using a wearable camera, with 8,250 short clips of a targeted person either walking 1) toward, 2) away, or 3) across the camera wearer in indoor environments, or 4) staying still in the scene, and 13,817 person bounding boxes were manually labelled. Apart from the bounding boxes, the dataset also contains the estimated pose of the targeted person as well as the IMU signal of the wearable camera at each time point. An LSTM-based encoder-decoder framework was designed to predict the future location and movement trajectory of the targeted person in this egocentric setting. Extensive experiments have been conducted on the new dataset, and have shown that the proposed method is able to reliably and better predict future person location and trajectory in egocentric videos captured by the wearable camera compared to three baselines., Comment: accepted as conference paper in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Food sharing and communal eating are very common in some countries. To assess individual dietary intake in food sharing scenarios, this work proposes a vision-based approach to first capturing the food sharing scenario with a 360-degree camera, and then using a neural network to infer different eating states of each individual based on their body pose and relative positions to the dishes. The number of bites each individual has taken of each dish is then deduced by analyzing the inferred eating states. A new dataset with 14 panoramic food sharing videos was constructed to validate our approach. The results show that our approach is able to reliably predict different eating states as well as individual’s bite count with respect to each dish in food sharing scenarios.

Assessing dietary intake in epidemiological studies are predominantly based on self-reports, which are subjective, inefficient, and also prone to error. Technological approaches are therefore emerging to provide objective dietary assessments. Using only egocentric dietary intake videos, this work aims to provide accurate estimation on individual dietary intake through recognizing consumed food items and counting the number of bites taken. This is different from previous studies that rely on inertial sensing to count bites, and also previous studies that only recognize visible food items but not consumed ones. As a subject may not consume all food items visible in a meal, recognizing those consumed food items is more valuable. A new dataset that has 1,022 dietary intake video clips was constructed to validate our concept of bite counting and consumed food item recognition from egocentric videos. 12 subjects participated and 52 meals were captured. A total of 66 unique food items, including food ingredients and drinks, were labelled in the dataset along with a total of 2,039 labelled bites. Deep neural networks were used to perform bite counting and food item recognition in an end-to-end manner. Experiments have shown that counting bites directly from video clips can reach 74.15% top-1 accuracy (classifying between 0-4 bites in 20-second clips), and a MSE value of 0.312 (when using regression). Our experiments on video-based food recognition also show that recognizing consumed food items is indeed harder than recognizing visible ones, with a drop of 25% in F1 score.

A daily dietary assessment method named 24-hour dietary recall has commonly been used in nutritional epidemiology studies to capture detailed information of the food eaten by the participants to help understand their dietary behaviour. However, in this self-reporting technique, the food types and the portion size reported highly depends on users’ subjective judgement which may lead to a biased and inaccurate dietary analysis result. As a result, a variety of visual-based dietary assessment approaches have been proposed recently. While these methods show promises in tackling issues in nutritional epidemiology studies, several challenges and forthcoming opportunities, as detailed in this study, still exist. This study provides an overview of computing algorithms, mathematical models and methodologies used in the field of image-based dietary assessment. It also provides a comprehensive comparison of the state of the art approaches in food recognition and volume/weight estimation in terms of their processing speed, model accuracy, efficiency and constraints. It will be followed by a discussion on deep learning method and its efficacy in dietary assessment. After a comprehensive exploration, we found that integrated dietary assessment systems combining with different approaches could be the potential solution to tackling the challenges in accurate dietary intake assessment.

Dietary assessment is an important tool for nutritional epidemiology studies. To assess the dietary intake, the common approach is to carry out 24-h dietary recall (24HR), a structured interview conducted by experienced dietitians. Due to the unconscious biases in such self-reporting methods, many research works have proposed the use of vision-based approaches to provide accurate and objective assessments. In this article, a novel vision-based method based on real-time three-dimensional (3-D) reconstruction and deep learning view synthesis is proposed to enable accurate portion size estimation of food items consumed. A point completion neural network is developed to complete partial point cloud of food items based on a single depth image or video captured from any convenient viewing position. Once 3-D models of food items are reconstructed, the food volume can be estimated through meshing. Compared to previous methods, our method has addressed several major challenges in vision-based dietary assessment, such as view occlusion and scale ambiguity, and it outperforms previous approaches in accurate portion size estimation.

Extracting human attributes, such as gender and age, from biometrics have received much attention in recent years. Gender and age recognition can provide crucial information for applications such as security, healthcare, and gaming. In this paper, a novel deep learning approach on gender and age recognition using a single inertial sensors is proposed. The proposed approach is tested using the largest available inertial sensor-based gait database with data collected from more than 700 subjects. To demonstrate the robustness and effectiveness of the proposed approach, 10 trials of inter-subject Monte-Carlo cross validation were conducted, and the results show that the proposed approach can achieve an averaged accuracy of 86.6%±2.4% for distinguishing two age groups: teen and adult, and recognizing gender with averaged accuracies of 88.6%±2.5 % and 73.9% ±2.8 % for adults and teens respectively.

A novel vision-based approach for estimating individual dietary intake in food sharing scenarios is proposed in this paper, which incorporates food detection, face recognition and hand tracking techniques. The method is validated using panoramic videos which capture subjects' eating episodes. The results demonstrate that the proposed approach is able to reliably estimate food intake of each individual as well as the food eating sequence. To identify the food items ingested by the subject, a transfer learning approach is designed. 4, 200 food images with segmentation masks, among which 1,500 are newly annotated, are used to fine-tune the deep neural network for the targeted food intake application. In addition, a method for associating detected hands with subjects is developed and the outcomes of face recognition are refined to enable the quantification of individual dietary intake in communal eating settings.

A novel depth estimation technique based on a single close-up image is proposed in this paper for better understanding of the geometry of an unknown scene. Previous works focus mainly on depth estimation from global view information. Our technique, which is designed based on a deep neural network framework, utilizes monocular color images with volumetric annotations to train a two-stage neural network to estimate the depth information from close-up images. RGBVOL, a database of RGB images with volumetric annotations, has also been constructed by our group to validate the proposed methodology. Compared to previous depth estimation techniques, our method improves the accuracy of depth estimation under the condition that global cues of the scene are not available due to viewing angle and distance constraints.

Dietary assessment system has proven as an effective tool to evaluate the eating behavior of patients suffering from diabetes and obesity. To assess the dietary intake, the traditional method is to carry out a 24-hour dietary recall (24HR), a structured interview aimed at capturing information on food items and portion size consumed by participants. However, unconscious biases are developed easily due to individual's subjective perception in this self-reporting technique which may lead to inaccuracy. Thus, this paper proposed a novel vision-based approach for estimating the volume of food items based on deep learning view synthesis and depth sensing techniques. In this paper, a point completion network is applied to perform 3D reconstruction of food items using a single depth image captured from any convenient viewing angle. Compared to previous approaches, the proposed method has addressed several key challenges in vision-based dietary assessment, such as view occlusion and scale ambiguity. Experiments have been carried out to examine this approach and showed the feasibility of the algorithm in accurate estimation of food volume.

A novel food volume measurement technique is proposed in this paper for accurate quantification of the daily dietary intake of the user. The technique is based on simul- taneous localisation and mapping (SLAM), a modified version of convex hull algorithm, and a 3D mesh object reconstruction technique. This paper explores the feasibility of applying SLAM techniques for continuous food volume measurement with a monocular wearable camera. A sparse map will be generated by SLAM after capturing the images of the food item with the camera and the multiple convex hull algorithm is applied to form a 3D mesh object. The volume of the target object can then be computed based on the mesh object. Compared to previous volume measurement techniques, the proposed method can measure the food volume continuously with no prior information such as pre-defined food shape model. Experiments have been carried out to evaluate this new technique and showed the feasibility and accuracy of the proposed algorithm in measuring food volume.

Continuous blood pressure measurement based on pulse transit time (PTT) is a deeply research topic over recent decades. Advanced algorithms have been proposed by scholars to give satisfactory estimation in stationary position. Nevertheless, pulse transit time (PTT) is shown to be strongly affected by hand movement and the estimation of blood pressure is no longer accurate under strenuous exercise. Because of this, a novel algorithm called Periodic Component Factorization (PCF), which is an extension of Independent Component Analysis (ICA), for better removal of motion artifact (MA) from photoplethysmography (PPG) signals is proposed in this paper. Compared to FastICA algorithm based on nongaussianity such as kurtosis and skewness, PCF is able to extract dependent source components from noisy signals when the PPG signal shows quasi-periodicity or periodicity. This newly proposed algorithm undoubtedly shows its practicality and effectiveness in removing motion artifact of PPG signals.

A novel sensor placement method for better removal of motion artifacts (MA) from photoplethysmography (PPG) signal using Fast Independent Component Analysis (ICA) is proposed in this paper. The method enhances the determination of pulse transit time (PTT) of PPG signals. The design makes use of double reflectance mode based PPG probes, which are placed complementary to each other and on the two sides of a single finger. Furthermore, a novel indicator denoted as Separating Factor is proposed as well. It helps evaluating the performance of ICA with different sensors configuration. This paper then addresses the effectiveness of FastICA in motion artifacts reduction by using the novel method and normal sensors placement method to capture PPG. Results indicate that better independent source separation can be achieved and morphology of PPG signal is perfectly restored when using the method proposed in this paper.