INTRODUCTION
Dozens of processors control every performance aspect of today's automobiles, and not a single feature of the "vehicle experience" remains untouched by technology. Whether it's climate control, engine control, or entertainment, there has been constant evolution of capabilities in manufacturer offerings over the last decade. One of the forces behind this evolution, the rapidly increasing performance-to-cost ratio of signal processors, is about to have a profound impact on another critical automotive component—the safety subsystem.
While most currently available safety features utilize a wide array of sensors—principally involving microwaves, infrared light, lasers, accelerometers, or position detection—only recently have processors been introduced that can meet the real-time computation requirements that allow video image processing to contribute substantially to safety technology. The Analog Devices Blackfin media-processor family offers attractive solutions for this growing market, with its high processing speeds, versatile data-movement features, and video-specific interfaces. This article will discuss the roles that Blackfin processors can play in the emerging field of video-based automotive safety.
VIDEO IN AUTOMOTIVE SAFETY SYSTEMS
In many ways, car safety can be greatly enhanced by video-based systems that use high-performance media processors. Because short response times are critical to saving lives, however, image processing and video filtering must be done deterministically in real time. There is a natural tendency to use the highest video frame rates and resolution that a processor can handle for a given application, since this provides the best data for decision making. In addition, the processor needs to compare vehicle speeds and relative vehicle-object distances against desired conditions—again in real time. Furthermore, the processor must interact with many vehicle subsystems (such as the engine, braking, steering, and airbag controllers), process sensor information from all these systems, and provide appropriate audiovisual output to the driver. Finally, the processor should be able to interface to navigation and telecommunication systems to react to and log malfunctions, accidents, and other problems.
Figure 1 shows the basic video operational elements of an automotive safety system, indicating where image sensors might be placed throughout a vehicle, and how a lane departure system might be integrated into the chassis. There are a few things worth noting. First, multiple sensors can be shared by different automotive safety functions. For example, the rear-facing sensors can be used when the vehicle is backing up, as well as to track lanes as the vehicle moves forward. In addition, the lane-departure system might accept feeds from any of a number of camera sources, choosing the appropriate inputs for a given situation. In a basic system, a video stream feeds its data to the embedded processor. In more advanced systems, the processor receives other sensor information, such as position data from GPS receivers.
Figure 1. Basic camera-placement regions for automotive safety applications.
Smart Airbags
An emerging use of media processors in automotive safety is for "intelligent airbag systems," which base deployment decisions on who is sitting in the seat affected by the airbag. At present, weight-based systems are in widest use, but video sensing will become popular within five years. Either thermal or regular cameras may be used, at rates up to 200 frames per second, and more than one might be employed—to provide a stereo image of each occupant. The goal is to characterize the position and posture of the occupants—not just their size. In the event of a collision, the system must choose whether to restrict deployment entirely, deploy with a lower force, or deploy fully. In helping to determine body position, image-processing algorithms must be able to differentiate between a person's head and other body parts.
In this system, the media processor must acquire multiple image streams at high frame rates, process the images to profile the size and position of each occupant under all types of lighting conditions, and constantly monitor all the crash sensors, located throughout the car, in order to make the best deployment decision possible in a matter of milliseconds.
