In Hong Kong, parents are usually busy to work and difficult to take care of their babies in person. They often employ baby sitters and invite grandparents to take care of their babies. However, it is not convenient enough and the babies may not get enough care from the baby sitters. Nowadays, we have a lot of IP cam for 24×7 monitoring of babies. Parents can watch their babies through mobile app and the IP cam. We wish to improve this situation. This project is to insert AI into the IP cam and set alarms. It can detect babies and interpret babies’ emotions, hunger, or any other hidden dangers. First, we have an IP cam to livestream the babies’ situation to the online server. An AI algorithm is built to interpret babies different conditions and situations. Once in danger, their parents will be alerted immediately via SMS.
Previously, mechanical locks, number padlocks or keycards are used for the purpose of unlocking doors. However, our team aims to establish a trend of unlocking a door with the Internet of Things (IoT) in this project. The innovative method of AI facial recognition will be utilized to identify the person outside the room, where the device does the action of either unlocking the door or alert security organizations with an alarm if that person standing out of the door does not satisfy the facial recognition process. In addition, records are kept on the Cloud Server to keep track of the activity in front of the door, storing the faces of every person shown in the IP camera so that the owner can check whether there is any suspicious activity outside of the house. The owner will also be asked to give permission to the system to unlock the door.
The misplacement of sundries blocks the Emergency Corridor and locks the exit will cause obstruction of escape routes when fire hazard occurred. Cases of sundries blocked the Emergency Corridor and locking the exit can be found in some residential in Hong Kong. In addition, the accumulation of sundries may cause hygienic problem. As coronavirus has spread over the globe. Hygiene has become a vital concern in the public. To ensure the escape routes are unimpeded when fire hazard occurs and maintain hygiene, we propose a Smart Emergency Corridor Monitoring System to detect sundries along the corridor or staircase based on image processing and pattern recognition, then send a warning signal to notify security or people in charge of the monitoring room. To achieve this, the Smart Corridor Monitoring System needs to be able to differentiate background environment objects, people and sundries. Then if the sundries have stayed for a certain seconds, it is confirmed to be sundries. Then, it can send a warning signal to the management department. To achieve this, the Smart Corridor Monitoring System needs to be able to differentiate background environment objects, people and sundries. Then if the sundries have stayed for a certain seconds, it is confirmed to be sundries. Then, it can send a warning signal to the management department.
Aging population is coming. The government reckon that there are one third of the elderly in Hong Kong in 2040, and the phenomenon will be increasingly worse as the time goes by. Therefore, we come up with an idea of Smart Elderly ‘Watching U system’. The system includes 3 devices which are smart watch, the mobile app and the Smart Glasses. First, the heart rate function—if the detected heartbeat of the elderly is weird, it will send a message to their children immediately. Second, it has fall down detection. If the elderly fall down on the floor, once the watch detected it, it will send a message to their children for telling the situation. Furthermore, the watch has set the elderly leave their house 500m away, and it will send a message to their children. Of course, children can see the map through the mobile app. Third, we set up an alarm that can be set by their children in the mobile app to remind them. And the QR code function, the children of the elderly can choose the medicine that they need in the mobile app. The helper can simply get right medicine from the pharmacy.
There are around 18% of people who are suffering from Hearing Impairment (Hearing loss). Hearing Impairment can highly affect their daily life in work environment, family or social. Only loneliness and silent accompany them for their whole life…… This project is a real-time sign language translation application, SignChat. The project aims at helping sign language user to improve their quality of life. It will help them to communicate with other people, avoid misunderstanding and help them to “speak up” in a direct way. Technically, the application consists of hand tracking and sign language translation features. Its real-time, 3-dimensions hand tracking feature is powered by Google’s mediapipe framework. Then, the tracking data is further processed into textual message with the AI model built by the team using LSTM neural network. The application provides both AI training and AI translation features. That means the sign language database could be even extended for new signs. Now, the team designed and developed an application that translate sign language instantly. The team wishes to help them to break through themselves by technology. The team hopes these applications can break the barriers between sign language and words.
With the increasing popularity of information technology, the technology of virtual reality has become more and more mature in recent years, becoming a hot topic in the information industry. However, the team found that VR technology is struggled to reach the customers as VR solutions usually require game controllers or motion sensors to control the character to interact with the virtual objects in the VR world. There were somethings obstacle prevent the people go inside. Thus, the team developed a framework called Immersive. ImmersiveKit a development framework for Virtual Reality(VR) / Augmented Reality(AR) applications with AI-powered advanced human tracking technology. With ImmersiveKit, developers can build a VR/AR application more easily and quickly. It provides full-body tracking and full-body interaction in virtual reality application with just a mobile device with a single-lens camera which is generally available in the market. The framework also provides a streamlined procedure which allows developers to quickly adopt the framework in any existing 3D game with minimum modification. At this stage, the framework is supports 3D gaming framework SceneKit . In coming future, the supports will be extended to popular game engine likes Unity3D.
Staying connected with family, friends, and colleagues is easy for most people who live with or close to others. For educators who need to communicate lessons and schedules with their students, or businesses who communicate with new and existing customers, staying connected can be hard, especially in times of crisis and isolation. Specifically, we wanted to make remote communication between educators and students easier. Communicating time-sensitive information and confirming that students received messages can be hard; scaling communication from tens to thousands of students can make the problem more complex, impacting educator and student productivity, time, and overall experience. To meet this challenge, We developed Callouts, a simple, consistent, and scalable solution for educators to communicate with students using Cloud calling and chatbot services (Amazon Connect and Amazon Lex). In crisis times, such as a quarantine, this solution helps educators use an automated bot that calls students to communicate important messages, such as schedule changes, general announcements, and attendance confirmation.
“Non wearable AI elderly Home” is an automated AI system to help single elderly. What if an elderly suddenly falls due to a stroke or other health issue without anyone notice? In Hong Kong, there are so many tragedies that elderly results in death. We developed an automated monitoring solution “(Eng)Non-wearable AI Elderly Home” or “(中)無穿戴式(唔洗學)人工智能老人家”could detect such falls and call parents or contact emergency services in a timely manner. It is a combination of AI and robotics technology with the cloud computing to provide multifunctional watchdog system. In current market, the solution for fall detection or SOS functions required smart phones or smart watches. But tiny and touch screen is difficult for elderly, not to mention that they have to carry the device 24/7, after bathing they will always forgot to carry it back.
“All Screens” is an online learning platform that engages and educates students at scale. Because of the COVID-19 outbreak, our institution has moved to online teaching for a few months and now online teaching becomes the worldwide hottest topic for all schools! To be honest, none of the online teaching solutions meet the real need for running online lab sessions. All existing online teaching solutions are just for online-meeting or one direction broadcast! Teachers are 100% no way to know your students are really working on their exercise at home or they are just open the online-meeting apps, and then doing other stuff! “All Screens” provided an AI virtual tutor (Miss Ma) can answer the basic questions of the students at any time after digesting the uploaded teaching materials in cloud, which is produced by augmented reality (AR) and 3D animation design technology , which can enhance the learning atmosphere. The system has won an award in AWS AI Hackathon (Global IT Competition) and supports multiple languages. The latest version has been introduced in March this year and has been adopted by numerous overseas universities.
In the midst of the COVID-19 pandemic, the demand for hygiene and sanitation has never been higher. A sample taken from the rooftop ventilating pipe of the sewage system of Heng Tai House was tested positive for the virus, which proves that virus can be travelled up through the rooftop ventilating pipe, before a slow-moving wind sent it back down to the building. Hence a customized UV sterilizing device for ventilating pipe of drainage system is designed, which could be integrated to a current ventilating pipe system for reducing the risk of spreading virus through the system. The device is placed on the vent pipe outlet and serves two main functions. The first one is to use the ultraviolet light properties to sterilize the vent pipe internal surface. The second function is to use the antibacterial sanitizing solution in the spiral section, it makes the air contact the more solution to prevent the breeding of germs. The device does not jeopardize the performance of the ventilating pipes system as prescribed in the Building Regulations and shall comply with other allied regulations. It is easy-to-install and has extended benefits to improve safety and health of the built environment.