Human error is the main cause of road accidents. Modern vehicles are equipped with image sensing cameras to see their surroundings and help drivers make extremely time-sensitive decisions to avoid accidents in challenging road/weather conditions. Safety features such as lane keeping, traffic light recognition and pre-collision braking are available as built-in features in recent models.
Cameras are one of the key sensors required for autonomous driving, along with Lidar, radar, and ultrasonic sensors. One to two megapixels CMOS image sensors are commonly used in today’s ADAS systems. These sensors have evolved from ‘viewing only’ sensors to “viewing plus sensing.” The advancement in image sensing technology is not only helping the driver to see better, but is literally the eyes of autonomous vehicles (AV). The data collected by sensors relays a vital feed into the decision-making process of the car.
Why does high resolution matter to autonomous driving? Because perception is key. Higher resolution allows smaller objects to be detected and identified by the system. This allows objects and other hazards to be detected at a greater distance, allowing the vehicle to alert the driver and take action sooner, thereby enhancing road safety. This is being driven by the need for autonomous cars to see further and at the same time have the ability to detect objects of all sizes. Essentially, this gives the ability to increase the number of pixels per degree on the object making the job of self-driving algorithms more efficient with both object detection and classification. To give a perspective, the 8.3 MP AR0820AT sensor can perceive 100 times better than human vision.
High dynamic range (HDR) is a key and critical parameter of camera sensors. This is the ability of the sensor to see between the darkest part and brightest part of the scene in the same frame without over or under saturation. In other words, the sensor needs to be impervious to changing ambient light conditions, such as suddenly been exposed to a bright sunny angle or reflection, or driving in/out of a tunnel in daylight. The AR0820ATprovides the highest dynamic range for up to 185 meters for safe dependable use on AV applications.
For level 3 AVs and beyond, there is a heavy dependence on hardware and software to make decisions that would otherwise be taken by humans, which can also make vehicles more susceptible to cyber-attacks or hacking. This has prompted work on the development of numerous protection and security features including cybersecurity being added at the sensor level. The inbuilt cybersecurity ensures reliable and secure operation when multiple cameras around the vehicle are connected to a centralized system, in which data and commands must travel by wires between the sensor and the processor. This is an increasingly important issue as vehicles become connected to other vehicles and the environment around them.
With a scalable family of image sensors from onsemi, automotive OEMs are able to deploy the optimum sensor for each application within each vehicle they produce while leveraging software and algorithm development across all devices. This reduces both development time and diminishes design risk.
AVs are one of the most highly anticipated innovations with a potential impact on changing the lives of millions globally. The AR0820AT image sensors enable AVs to see further and at the same time have the ability to detect objects of challenging sizes. As this technology becomes accessible to the general public, it will surely change the way we drive and use transportation. But most significantly, we can keep drivers, passengers and vehicles safe on the road.
Be sure to join our upcoming technology webinar - Intelligent Image Sensing Technology Leads the Road from ADAS to Autonomous Vehicles - on September 15, 2021, at 11:00 a.m. Pacific Time, where you will learn about the underlying technology for the AR0820AT sensor and the far-reaching impact it has in the automotive world. Sign up to join us live or watch the on-demand video here.