URBAN-i BOX V1
URBAN-i Box is an AI-embedded camera that generates synchronized data. As it watches, it learns how city systems interact to produce risk, proving actionable insights. When a person is riding a bike and has a near miss, URBAN-i sees the whole scene, from how he/she was cycling to what the weather was like and the conditions of the road surface to work out the most likely contributing factors. The core elements of URBAN-i are the computer vision algorithms and the sensor design.
- An 8 MB camera with wide-view and high-resolution (1296 X 972) calibrated sensor for video streaming while capturing single images with time and location reference. The camera algorithms rely on different AI models to detect different objects, classify scenes, and recognise instant actions.
- A Light Detection And Ranging (LiDAR) sensor that uses the direct flight time to measure the reflected light to a distance of up 12 metres for both indoor and outdoor. The sensor is calibrated to detect safe and unsafe distance for transport modes.
- A low powered screen to provide vital information to users such as Disk capacity, battery level, multi-sensor readings, and button interaction.
- A wide range of colour led to be utilised for user-interface and notification for the different tasks and scenarios.
- A GPS sensor
- An ultra-high-range luminosity sensor that relies on both infrared and full spectrum diodes to measure light temperature and intensity. It also detects different hand gestures that allow users to interface with URBAN-i box.
- An inertia measurement unit (IMU) sensor of 9 axes is used to provide precise data regarding acceleration, heading and gyroscope. The sensor algorithms comprise AI models to understand different actions in cities to add further features to the camera functions.
- A Li-po chargeable battery of 3800 mAh capacity is used to provide a long time for streaming up to 4 and half hours in a single charge.