One of the primary concerns that we’ve raised with Autonomous Vehicles (AVs or “driver-less vehicles”) has been the ability of the on board computers to distinguish between various “real world” objects like deer, motorcycles, raccoons, small children chasing a ball, and so on.
The heart of the issue is whether the computer will take evasive action (endangering the occupants with a potential rollover) or make some other calculated move to minimize the odds of a crash (such as sacrificing a wild animal to save the occupants of the car from injury or death).
Tech companies are working on these object detection systems right now. They’re testing and cataloging “real world” images so that they can “teach” a computer how to recognize a car from a group of pedestrians.
In a recent article published at “GIZMAG” (Click HERE) we have learned that Fujitsu is building what it calls an “Approaching Object Detection Library” to help both AV systems and live drivers recognize and react to the driving environment.
From the article:
When it comes to driver awareness, we all know how hard it can be to keep an eye on every pedestrian and moving vehicle in our vicinity, particularly when driving in a busy city area…To help in this regard, Fujitsu Semiconductor Limited is set to introduce software that assists in detecting and identifying cars, people, and other moving objects and alerts the driver of their position and direction of travel.
This is achieved by using elements built into the Approaching Object Detection Library, where vehicle camera images are analyzed in conjunction with a detection algorithm that identifies approaching objects. These are then run with detection-error reduction processing to eliminate false positives. The resulting image is overlaid on real-time images collected through the vehicle’s on-board cameras, and displayed on a dashboard monitor, providing vital information for the driver about the objects moving around them.
It is very exciting to see what technology can bring to the table for increasing driver safety on the highways. Better than a simple camera system, this technology (when fully tested and developed) could help provide meaningful alerts for drivers who may be ill, sleepy or momentarily distracted by passengers, or other simple inattention scenarios.