CHEN RUI KE Electronic Company Limited

In the past, driving performance was a major factor in determining how well a model sold. Powerful engines, dynamic handling and low fuel consumption are selling points automakers use to attract customers. But times are changing, and consumers are increasingly looking for features and comfort similar to smartphones when shopping for a new car. In addition, increasing safety requirements from regulators are driving automakers to pay more attention to in-car design. The use of 3D data is a feature that will enable future in-car designs and allow automakers to stand out. An easy and cost-effective way to capture 3D data is to use a Time of flight (ToF) camera. This camera irradiates the region of interest by modulating infrared light, then detects the reflected light and compares it with the emitted signal. This results in a 2D grayscale image and, at the same time, the distance information of each pixel is obtained from the phase difference, thus obtaining the 3D information of the scene. The 2D grayscale image and 3D depth information are obtained by infrared light. This method is often referred to as indirect time-of-flight (IToF). Unlike conventional cameras, IToF provides highly reliable 3D data in all ambient light conditions (e.g., at night, under strong sunlight, and on roads with frequent altercountries of light and shadow) without the effects of shadows and overexposure. IToF offers additional advantages over other depth sensing technologies: the ToF camera module is designed to be simple and robust without any mechanical baseline; The camera is fast to calibrate and easy to reliably mass-produce. The computational load of the application processor is relatively small. Monitor the driver The ToF sensor can be used in the driver monitoring system (DMS) by placing it in the A-pillar, steering wheel, or combined meter. The TOF-based DMS is A cost-effective option. In this system, the same ToF camera used for the DMS function can be used to achieve secure, fraud-proof face verification, as is the case for many smartphones and smart door locks. The proposed algorithm uses 2D infrared images for face recognition and 3D data to avoid any type of spoofing attacks. Without 3D data, a simple photo is enough to fool facial recognition algorithms; 3D data can immediately deter such attempts. But why 3D face authentication in a car? As consumers become more accustomed to the convenience provided by smartphones, smart watches, smart TVS and other smart devices, they expect more and more convenience from their cars. This means that no matter where you are (even in a smart car), you can seamlessly access private data and cloud services like streaming music. These new services also require authentication, such as easy payment when charging an electric car at a public charging station. When there is a need to authenticate an operation, especially those sensitive transactions, it is necessary to have security, and this can be achieved with 3D data. But there are also less sensitive facial recognition applications. Take personalization, for example, which enables the car to detect which driver has just entered the vehicle and thus load the appropriate Settings. Safety and Convenience applications Once the car is on the road, 3D data can also be used to more accurately determine the position of the driver's eyes and head. This means that the projection of the head-up display will also be more adapted to the driver's situation. But DMS is not the only use for ToF cameras. A wide field of view ToF camera near the rear view mirror enables a complete occupant monitoring system (OMS) that supports all necessary tasks during autonomous driving, paving the way for hand-holding steering wheel detection and autonomous driving takeover behavior. When the vehicle takes over the driving, the driver can dramatically change his position, even lying down. To ensure driver safety, vehicle safety systems must adapt to the new driver posture. For example, smart airbags or seat belts need to know the precise position of the occupant. ToF cameras provide such information through accurate 3D body models and real-time body tracking. As a result, even if the driver enjoys more "freedom" in L3 and L4 autonomous driving, its passive safety is still guaranteed. The application of 3D sensing technology goes far beyond tracking motion, it can also easily enable occupant detection and classification. This provides accurate size and weight estimates that can replace existing seat weight measurement systems. Similarly, ToF also supports Child Presence Detection (CPD) systems, which are becoming a mandatory requirement.

How 3D cameras prevent Facial Recognition fraud Facial recognition algorithms are fairly mature at this point. Especially in smart phones, the technology is now widely used. But studies (for example: the study by the German magazine Computer Bild Q1/20) show that many smartphones are easily spoofed: 20 out of 25 smartphones can be unlocked with a simple printed photo. Only smartphones equipped with 3D depth sensors can distinguish between real faces and photos. This makes ToF an ideal technology to add secure face authentication to driver monitoring systems in cars. Infineon has partnered with Jungo Connectivity to demonstrate a driver monitoring system combined with robust anti-fraud facial authentication capabilities: the system is based on Jungo's AI in-vehicle sensing solution CoDriver and Infineon's REAL3TM ToF image sensor. ToF also opens up entirely new possibilities for the outside of the vehicle. As mentioned above, face authentication can be used to unlock a vehicle. To this end, we installed the ToF module in the B-pillar. Electric car doors, which open and close automatically, require sensors to ensure that no obstacles are in the way. For this, ToF sensors can provide the required high-precision data. For autonomous parking, ToF sensors provide accurate data on the location and size of objects such as curbs and posts. Of course, the ToF camera module is a complex system: it has to be customized for the respective vehicle and application, and each module has to be calibrated. The laser used must be protected both electrically and mechanically in order to ensure the eye safety of the occupant at all times. Data processing is equally important. In automotive applications, ToF modules, like all other components, must meet specific criteria. For example, smart airbag applications are required to comply with functional safety requirements including ISO 26262. The world's first ISO 26262-certified ToF sensor Infineon is the first company to offer a high-resolution vehicle-grade ToF image sensor that meets the ISO 26262 ASIL-B functional safety requirements. The ISO 26262 ASIL-B standard defines the state of the art in the field of functional safety. Any device in the vehicle that may affect occupant safety must meet this standard. The Infineon REAL3T" IRS2877A(S) ToF image sensor is one of the devices that have passed the standard. It is based on the fifth generation pixel technology and has been tested in smart phones (IRS2877C). With the new sensor, the lens size has been drastically reduced again, to a pixel circle of just 4mm (0.25 in), making it as small as a smartphone camera. It also has a system resolution of up to 640 ×480 pixels (VGA). It is a highly integrated solution with backlight suppression at each pixel (so, the image sensor is completely protected from sunlight), integrated safety circuitry to protect the human eye, and an optimized power supply design that facilitates an efficient (size and cost) ToF camera module design. The whole device is packaged in a standard optical spherical pin grid array (BGA) and is suitable for standard welding processes. Conclusion 3D depth data makes all the difference: ToF solutions show that compliance does not contradict innovation. Only one sensor can meet the relevant EU regulatory standards and functional requirements of the NCAP DMS (including head tracking, eye closure detection, and gaze region segmentation), while adding new features and services with secure 3D face authentication. This ushered in an era of seamless connectivity. In addition, TOF-based crew monitoring systems enable the vision of "the driver becoming a crew", for example, the driver can change posture or even lie down while the vehicle is autonomous. Infineon has a strong ecosystem of partners including: module manufacturers, Tier 1 customers and application software experts. The company also has a proven track record with ToF sensors for consumer, industrial, and iot applications. Together with development partner Pmdtechnologies, Infineon offers a complete solution that includes sophisticated depth algorithms, depth data artifact detection and correction, depth software support, and advanced, fast and heavily proven calibration and test seams. Infineon is the first company to offer a high-resolution vehicle-grade ToF image sensor that meets the ISO 26262 ASIL-B functional safety requirements. Infineon's ToF image sensor is the world's first 3D ToF image sensor certified to the ISO 26262 ASIL-B standard for current and future functional safety applications. Infineon is also a one-stop service provider in the area of in-vehicle sensors, offering other sensors such as millimeter wave radar and silicon microphones in addition to ToF sensors.