Slashdot Mirror
Mitsubishi Electric Believes Its AI-enhanced Camera Systems Will Make Mirrors on Cars Obsolete (ieee.org)
In its annual R&D Open House on February 14, Mitsubishi Electric described the development of what it believes is the industry's highest-performance rendition of mirrorless car technology. From a report: According to the company, today's conventional camera-based systems featuring motion detection technology can detect objects up to about 30 meters away and identify them with a low accuracy of 14 percent. By comparison, Mitsubishi's new mirrorless technology extends the recognition distance to 100 meters with an 81 percent accuracy. "Motion detection can't see objects if they are a long distance away," says Kazuo Sugimoto, Senior Manager, at Mitsubishi Electric's Image Analytics and Processing Technology Group, Information Technology R&D Center in Kamakura, 55 km south of Tokyo. "So we have developed an AI-based object-recognition technology that can instantly detect objects up to about 100 meters away."
To achieve this, the Mitsubishi system uses two technology processes consecutively. A computational visual-cognition model first mimics how humans focus on relevant regions and extract object information from the background even when the objects are distant from the viewer. The extracted object data is then fed to Mitsubishi's compact deep learning AI technology dubbed Maisart. The AI has been taught to classify objects into distinct categories: trucks; cars; and other objects such as lane markings. The detected results are then superimposed onto video that appears on a monitor for the driver to view.
To achieve this, the Mitsubishi system uses two technology processes consecutively. A computational visual-cognition model first mimics how humans focus on relevant regions and extract object information from the background even when the objects are distant from the viewer. The extracted object data is then fed to Mitsubishi's compact deep learning AI technology dubbed Maisart. The AI has been taught to classify objects into distinct categories: trucks; cars; and other objects such as lane markings. The detected results are then superimposed onto video that appears on a monitor for the driver to view.
The vehicle driver is focussed at infinity when looking forwards. If you look at an actual mirror, you can remain focussed at infinity.
If you have to look at a monitor (let alone one that's got cartoons based on target classifications), you have to refocus to the monitor distance. So unless MItsu is planning to project their image to infinity-equivalent, this is NotAGoodIdea(TM) .
https://app.box.com/WitthoftResume Code: https://github.com/cellocgw
According to this article air resistance only accounts for 5% of energy output of a car. So if the mirror accounts for 7% of air resistance, that's 7% of 5%. So that means it's only 0.35% of fuel economy.
Until they figure out how to make 3D cameras and displays that are as reliable as mirrors in cars, they won't replace mirrors in functionality.
Cameras go wrong all the time. There are many fewer points of failure in a mirror, and they're a sight easier (and cheaper) to clean/adjust/replace when necessary too.