Deep-Learning Vision Processing
Although many companies are currently developing deep learning solutions, THINCI states that its technique is superior to the alternatives due to the company’s “silicon architecture capable of processing extremely large amounts of data in the same amount of time a human would.”
Now, normally you would expect a computer to be able to process data much quicker than a human. But in the realm of vision processing, we have an evolutionary advantage over our silicon counterparts due to our naturally optimized visual cortex. So THINCI’s claim is actually more impressive than it might first sound.
THINCI’s technique involves processing entire images in parallel, which can enable pattern recognition akin to what humans do. The company claims that this approach reduces power consumption and boosts performance by eliminating the need for costly memory access.
Some of the automotive applications of THINCI’s technology include driver state analysis, road condition analysis, vehicle localization, environment perception and path planning. In addition, with its deep-learning technology, the company envisions distraction-free interaction between the driver and automobile. “Start playing chapter 2 in my last audiobook; Where is the next rest stop? Get me around this traffic jam; Help! I’m having a medical emergency…” are some examples of potential driver voice commands listed on THINCI’s website.
Autonomous Vehicles and Beyond
Though the company is still in the final phase of developing its technology, DENSO is clearly impressed.
"DENSO has been researching new developments in the area of computer vision processing,” said DENSO’s Tony Cannestra. “We strongly believe that THINCI's technology will soon become a key component of next generation autonomous driving systems that require advanced computing techniques combined with deep learning capabilities."
In addition to autonomous vehicle systems, deep-learning vision processing technology has the potential to transform a variety of other industries. These include personal electronics like smartphones and tablets, smart homes, smart cities, augmented reality and more. However, it seems like the automotive industry will be among the first to reap the benefits.
"We are thrilled DENSO is our lead investor," said THINCI CEO Dinakar Munagala. "The automotive industry is one of the earliest adopters of vision processing and deep learning technology. DENSO's investment in THINCI's trailblazing solution confirms our own belief that our innovation has much to offer, not only in the automobile but in the wide range of everyday products."
For more autonomous vehicle news, read OTTO Motors Receives Multi-Million-Dollar Investment for Self-Driving Vehicles.