To assist visual computing software developers in developing automotive driver assistance application, Fujitsu Semiconductor has made available object detection library for camera based driver safety systems to identify objects, so the vehicle can be steered to safety or alert the driver by using this software based object detection library.
The library generates the optical flow (optically detected movements) within the input video stream, applies detection-error reduction processing, and then groups objects with similar flows to identify moving objects.
This library is a proprietary technology from Fujitsu which can be implemented without a dedicated image processing semiconductor chip. Designed to support a parallel data processing. The Approaching Object Detection Library is available in an evaluation version in May 2014, when it will be shipped with an evaluation board that includes the company's graphics SoC, MB86R24, for testing functionality. The commercial product is going to be available in September. Fujitsu also plans to apply the technology it has developed for cars onto general SoC platforms, and to develop many new applications, such as for surveillance cameras and automatic controls.
Fujitsu going to demonstrate this technology and other solutions at the 2014 Automotive Engineering Exposition, running May 21–23 at the Pacifico Yokohama.
Hardware System Requirements:
CPU ARM Cortex-A9 533MHz
ROM 90 Kbytes
RAM 4 Mbytes (input image size: 720x480, detection area: 2 areas of 240 x160 pixels)