Yicheng Bai

Accuracy of food portion size estimation from digital pictures acquired by a chest-worn camera

OBJECTIVE Accurate estimation of food portion size is of paramount importance in dietary studies. We have developed a small, chest-worn electronic device called eButton which automatically takes pictures of consumed foods for objective dietary assessment. From the acquired pictures, the food portion size can be calculated semi-automatically with the help of computer software. The aim of the present study is to evaluate the accuracy of the calculated food portion size (volumes) from eButton pictures. DESIGN Participants wore an eButton during their lunch. The volume of food in each eButton picture was calculated using software. For comparison, three raters estimated the food volume by viewing the same picture. The actual volume was determined by physical measurement using seed displacement. SETTING Dining room and offices in a research laboratory. SUBJECTS Seven lab member volunteers. RESULTS Images of 100 food samples (fifty Western and fifty Asian foods) were collected and each food volume was estimated from these images using software. The mean relative error between the estimated volume and the actual volume over all the samples was -2·8 % (95 % CI -6·8 %, 1·2 %) with sd of 20·4 %. For eighty-five samples, the food volumes determined by computer differed by no more than 30 % from the results of actual physical measurements. When the volume estimates by the computer and raters were compared, the computer estimates showed much less bias and variability. CONCLUSIONS From the same eButton pictures, the computer-based method provides more objective and accurate estimates of food volume than the visual estimation method.

eButton: A Wearable Computer for Health Monitoring and Personal Assistance

Recent advances in mobile devices have made profound changes in peoples daily lives. In particular, the impact of easy access of information by the smartphone has been tremendous. However, the impact of mobile devices on healthcare has been limited. Diagnosis and treatment of diseases are still initiated by occurrences of symptoms, and technologies and devices that emphasize on disease prevention and early detection outside hospitals are under-developed. Besides healthcare, mobile devices have not yet been designed to fully benefit people with special needs, such as the elderly and those suffering from certain disabilities, such blindness. In this paper, an overview of our research on a new wearable computer called eButton is presented. The concepts of its design and electronic implementation are described. Several applications of the eButton are described, including evaluating diet and physical activity, studying sedentary behavior, assisting the blind and visually impaired people, and monitoring older adults suffering from dementia.

Designing a wearable computer for lifestyle evaluation

A wearable computer, called eButton, has been developed for evaluation of the human lifestyle. This ARM-based device acquires multimodal data from a camera module, a motion sensor, an orientation sensor, a light sensor and a GPS receiver. Its performance has been tested both in our laboratory and by human subjects in free-living conditions. Our results indicate that eButton can record real-world data reliably, providing a powerful tool for the evaluation of lifestyle for a broad range of applications.

Helping the blind to find the floor of destination in multistory buildings using a barometer

Propelled by rapid technological advances in smart phones and other mobile devices, indoor navigation for the blind and visually impaired individuals has become an active field of research. A reliable positioning and navigation system will reduce suffering of these individuals, help them live more independently, and promote their employment. Although much progress has been made, localization of the floor level in a multistory building is largely an unsolved problem despite its high significance in helping the blind to find their ways. In this paper, we present a novel approach using a miniature barometer in the form of a low-cost MEMS chip. The relationships among the atmospheric pressure, the absolute height, and the floor location are described along with a real-time calibration method and a hardware platform design. Our experiments in a building of twelve floors have shown high performance of our approach.

Estimation of heart rate from a chest-worn inertial measurement unit

Recently, wearable devices for measuring cardiovascular functions have attracted increasing research attention. However, these devices must use electrodes or other sensors attached to the human body, which makes the wearer uncomfortable for long-term use. In this study, we demonstrated the feasibility of using a chest-worn device, called eButton, to measure heart rate without any skin-attachments. Instead of measuring electrical or optical signals, we use a 9-axis Inertial Measurement Unit (IMU) which contains a 3-axis gyroscope, a 3-axis accelerometer, and a 3-axis magnetometer to detect the mechanical vibration of chest due to heart movement. The signal acquired is called the ballistocardiogram (BCG). From an experiment with ten normal research participants, we have found that the BCG waveform is more observable in the output of the gyroscope than the output of the accelerometer. An algorithm is developed to estimate the heart rate from the gyroscope-acquired BCG.

Automatic eating detection using a proximity sensor

Eating detection is a critical component in a wearable dietary monitoring device called eButton under our investigation. Once an eating activity is detected, a camera within the device is activated to take pictures of food automatically which is then processed to measure intakes of calories and nutrients. In this paper, we address the eating detection problem using a proximity sensor within the eButton. The repetitive movements of the arm during eating are monitored by a proximity sensor within a fan-shaped region. An infrared light emitter and a photo receiver produce signals when the infrared light is blocked. Our test results show that eating activity can be detected and distinguished from other activities. In addition, our method is unobtrusive, low power, and of a small size, suitable to be used in wearable devices.

Landmark-based indoor positioning for visually impaired individuals

Position localization is essential for visually impaired individuals to live independently. Comparing with outdoor environment in which the global positioning system (GPS) can be utilized, indoor positioning is more difficult due to the absence of the GPS signal and complex or unfamiliar building structure. In this paper, a novel landmark-based assistive system is presented for indoor positioning. Our preliminary tests in several buildings indicate that this system can provide accurate indoor location information.

Learning based particle filtering object tracking for visible-light systems

We propose a novel object tracking framework based on online learning scheme that can work robustly in challenging scenarios. Firstly, a learning-based particle filter is proposed with color and edge-based features. We train a. support vector machine (SVM) classifier with object and background information and map the outputs into probabilities, then the weight of particles in a particle filter can be calculated by the probabilistic outputs to estimate the state of the object. Secondly, the tracking loop starts with Lucas-Kanade (LK) affine template matching and follows by learning-based particle filter tracking. Lucas-Kanade method estimates errors and updates object template in the positive samples dataset, and learning-based particle filter tracker will start if the LK tracker loses the object. Finally, SVM classifier evaluates every tracked appearance to update the training set or restart the tracking loop if necessary. Experimental results show that our method is robust to challenging light, scale and pose changing, and test on eButton image sequence also achieves satisfactory tracking performance.

Eating Event Detection by Magnetic Proximity Sensing

Eating event detection is an important problem in automatic dietary study using a wearable computer, such as the eButton. In this work, we approach this detection problem based on the use of a small magnet marker attached to a finger and a miniature magnetometer installed within the eButton. Our experimental results indicate that our magnetic approach is effective when the distance between the marker and the wearable computer is within 12cm, and the range of detection is approximately 15cm. We also found that the proximity signal patterns corresponding to eating and other daily activities are different, which can be used to reduce the false detection rate. In addition, our approach is convenient, low-cost and energy efficient, suitable for practical applications.

A Novel Binocular Vision System for Wearable Devices.

We present a novel binocular imaging system for wearable devices incorporating the biology knowledge of the human eyes. Unlike the camera system in smartphones, two fish-eye lenses with a larger angle of view are used, the visual field of the new system is larger, and the central resolution of output images is higher. This design leads to more effective image acquisition, facilitating computer vision tasks such as target recognition, navigation and object tracking.