How to Build a Occupancy Detection Dataset?

In the field of artificial intelligence, data is the key point to driving model learning and optimizing. Whether it is computer vision, natural language processing, or autonomous driving, datasets provide the necessary foundation for algorithms. high-quality data can not only improve the performance of algorithms, but also promote the whole industries innovation and development. By collecting and annotating large amounts of data, researchers can train out more accurate and intelligent models to achieve more efficient prediction and decision-making capabilities.

Euro NCAP announced that starting in 2022, it will start scoring child presence detection, “a feature that detects that a child is left alone in a car and alerts the owner or emergency services to avoid death from heat stroke.”

Compared with DMS, which focuses on the “monitoring” of the driver, OMS(Occupancy Monitoring System) provides more “detection” functions in the cabin. OMS perceives the passengers in the car through the smart cockpit and identifies whether the behavior of the passengers is safe. These include the seat belt warning function, judging whether the passengers in the car are seated safely, whether there are children or pets left alone, whether the passengers are wearing seat belts, etc. OMS is to further improve the safety performance of the car from the perspective of monitoring passengers.

At present, from the technical perspective, the current industry mainly uses cameras, millimeter-wave radars, and pressure sensors to monitor passengers.

1. Camera

OMS generally uses camera equipment to realize the perception of passengers through AI algorithms. However, simple cameras are easily deceived by photos. Currently, Tier1 suppliers in the market generally add infrared optical components to supplement the shortcomings of cameras.

2. Millimeter wave radar

Installed on the roof of the cockpit, it can sense all areas of the entire cockpit, detect targets, and perform high-precision classification and biometric monitoring of them. Radar provides depth perception through soft materials such as blankets and other similar coverings that cover children.

Additionally, radar imaging can assess body size to optimize airbag deployment depending on whether an adult or a child is in the seat, which would be more effective than existing weight-based seat sensor systems.

Nexdata has developed series of OMS and DMS training datasets, covering a variety of application scenarios, such as driver & passenger behavior recognition, gesture control, facial recognition and etc. All data is collected with proper authorization with the person being collected, and customers can use it with confidence.

● Passenger Behavior Recognition Data

The data includes multiple age groups, multiple time periods and multiple races (Caucasian, Black, Indian). The passenger behaviors include passenger normal behavior, passenger abnormal behavior(passenger carsick behavior, passenger sleepy behavior, passenger lost items behavior). In terms of device, binocular cameras of RGB and infrared channels were applied.

● Multi-race — Driver Behavior Collection Data

The data includes multiple ages, multiple time periods and multiple races (Caucasian, Black, Indian). The driver behaviors includes dangerous behavior, fatigue behavior and visual movement behavior. In terms of device, binocular cameras of RGB and infrared channels were applied.

● Driver Behavior Collection Data

The data includes multiple ages and multiple time periods. The driver behaviors includes Dangerous behavior, fatigue behavior and visual movement behavior. In terms of device, binocular cameras of RGB and infrared channels were applied.

● 18_Gestures Recognition Data

This data diversity includes multiple scenes, 18 gestures, 5 shooting angels, multiple ages and multiple light conditions. For annotation, gesture 21 landmarks (each landmark includes the attribute of visible and visible), gesture type and gesture attributes were annotated.

● 50 Types of Dynamic Gesture Recognition Data

The collecting scenes of this dataset include indoor scenes and outdoor scenes (natural scenery, street view, square, etc.). The data covers males and females (Chinese). The age distribution ranges from teenager to senior. The data diversity includes multiple scenes, 50 types of dynamic gestures, 5 photographic angles, multiple light conditions, different photographic distances.

End

If you need data services, please feel free to contact us at info@nexdata.ai.

With the rapid development of artificial intelligence, the importance of datasets has become prominent. By accurate data annotation and scientific data collection, we can improve the performance of AI model, which enable them to cope with real application challenges. In the future, all fields of data-driven innovation will continue to drive intelligence and achieve business results in high-value.