Freescale employs parallel processing to identify pedestrians
Freescale plans to offer new processors that bring Image Cognition Processing to automotive cameras later this year. Towards this end, the chipmaker licensed CogniVue’s APEX IP to enable vehicle cameras to sense the environment – determining the presence of an object and identifying it.
Advanced driver assistance systems are becoming more and more sophisticated, said Ray Cornyn, vice president of Freescale’s Automotive MCU Division. He added that there is increasing demand to include them on mainstream vehicles. “Today’s collision avoidance systems are typically enabled by digital signal processors or field-programmable gate arrays. Freescale is taking a different approach by integrating CogniVue’s Image Cognition Processing IP into our processors, providing massively parallel processing in small packages and with very low power consumption.”
CogniVue offers parallel processing IP for intelligent imaging. Its products capture, analyze and render video and images for smart cameras used in automotive vision systems and smart video monitoring markets. In addition to capturing image and video information, the APEX technology enables extraction of application-specific information from a scene and interpreting the image data to make decisions or take actions based on the extracted data. With pattern recognition, detection and classification algorithms, smart cameras can detect objects and people around the vehicle and measure distance to alert the driver of an impending collision.
Front- and rear-facing cameras are integrated into a vehicle’s safety systems and help drivers avoid collisions. The growth of ADAS is, in part, being driven by legislation. According to the U.S. National Highway Traffic Safety Administration (NHTSA), 228 people die and about 17,000 people are injured annually in the United States due to backover accidents involving cars, trucks and sport utility vehicles (SUVs). Backover accidents are the most common cause of off-road deaths involving children and vehicles.
For this reason the NHTSA has proposed a rear-facing camera requirement to be phased in, with all vehicles having the feature by September 2014. Legislation for front-facing cameras, particularly with embedded pedestrian detection features, is likely to follow. European NCAP ratings are expected to be heavily influenced by pedestrian detection functionality.