
Security・Safety
We are using AI to enable automated explanation in videos and for evacuation guidance during emergencies.
AI visual recognition technologies of surveillance protect safety of our society.
AI technology is playing important roles to keeping safety, security, and prosperity of our society. Video recognition and video explanation technologies provide accurate and ceaseless observation, which are required to keep safety in factories, hospitals, streets, and other locations in our society.
Our research of video-to-text translation with high precision visual recognition will be applied for smart vigilance cameras. Most of conventional methods cannot achieve accurate recognition, because they processed video information as a set of still images, not as a continuous time-series of images. Applying deep learning, our system is able to understand objects in videos and events occurring in videos accurately. In this way, AI’s power of visual observation will provide support in various fields.
In addition, we are also applying technologies of large-scale pedestrian tracking and simulation to support safe guidance in crowded area and evacuation planning in emergencies. These technologies enable tracking of pedestrians by integrating numerous sensors and simulating behaviors of the pedestrians even in the case of a large event attended by 100,000 people or public spaces such as train stations or airport in real time. This is referred to as sensing and simulation technology. AI is becoming an indispensable technology for safety of social systems.
Our research of video-to-text translation with high precision visual recognition will be applied for smart vigilance cameras. Most of conventional methods cannot achieve accurate recognition, because they processed video information as a set of still images, not as a continuous time-series of images. Applying deep learning, our system is able to understand objects in videos and events occurring in videos accurately. In this way, AI’s power of visual observation will provide support in various fields.
In addition, we are also applying technologies of large-scale pedestrian tracking and simulation to support safe guidance in crowded area and evacuation planning in emergencies. These technologies enable tracking of pedestrians by integrating numerous sensors and simulating behaviors of the pedestrians even in the case of a large event attended by 100,000 people or public spaces such as train stations or airport in real time. This is referred to as sensing and simulation technology. AI is becoming an indispensable technology for safety of social systems.
-
Theme1Video-to-text translation
Our AI system with deep learning technology generates sentences that explain the content and meaning of videos. Deep learning is utilized for recognition of objects and actions in video. Thanks to recurrent neural network (RNN), the system produces natural sentences for explanation. -
-
Theme2Evacuation guidance support using AI
We were able to achieve visualization of the overall movements of a large number of pedestrians using real time pedestrian tracking technology and multi-agent simulation technology. Such visualization offers engineering techniques to design evacuation guidance, especially in cases of large numbers of people, whose overall movements have been difficult to recognize and have been controlled in ad-hoc ways. -
Future prospects
- Connecting video explanation technology to specific applications in engineering, healthcare, and crime prevention
- Promoting societal use of pedestrian simulation