While there are already apps that guide blind users to a bus stop’s approximate location, those people may unknowingly end up standing too far away from the actual stop. A new app addresses that shortcoming by letting the smartphone’s camera in on the act.

Known as All_Aboard, the AI-based app was developed by a team of scientists at the Harvard-affiliated Massachusetts Eye and Ear treatment and research center. It’s made to be used along with a third-party GPS-based online navigational (导航的) map.

Users start by using other apps to get to a bus stop’s location. They then open All _Aboard and proceed to hold their smartphone up so that its back camera can “see” the surrounding street. Drawing upon a deep learning neural network which was trained on around 10,000 images of bus stops within that city, the app is reportedly able to visually identify the target stop’s sign if it’s within a range of up to 15 meters away. Once the sign has been spotted, the app guides the user via sonar-like beeps (哔哔声) which change pitch and speed as the person gets closer to the bus stop.

In field tests, 24 legally blind volunteers used both online maps and All _Aboard to locate 20 bus stops—10 in an urban setting and 10 in a suburban environment.

When it came to getting close enough to those stops, online maps alone had a success rate of just 52%, whereas All _Aboard boosted the number to 93%. Additionally, while the average distance between the map’s endpoint and the actual bus stop was 6.62 meters with online maps, it was just 1.54 meters with All _Aboard.

“Our findings suggest that the All _Aboard app could help travelers with visual impairments (视力受损) in navigation by accurately detecting the bus stop, and therefore greatly reducing their chance of missing buses due to standing too far from the bus stops,” said Massachusetts Eye and Ear’s Assoc. Prof. Gang Luo. “This study indicates that computer vision-based object recognition capabilities can be used in a complementary (补充的) way and provide added benefit to purely mapping-based, macro-navigation services in real-world settings.”

Facial recognition cameras are everywhere, including in your smartphone. Many people rely on this technology to unlock their phones, open doors or make quick payments, but there is a problem: Everyone is wearing mask. What a hassle!

Now, tech companies have updated their software. Facial recognition technology can now identify people even if they are wearing a mask.

Beijing-based tech company Hanwang has announced a software which can correctly recognize 95 percent of people wearing masks, Engineering & Technology（E&T）reported. What's the secret? It's all about your eyes.

Marios Savvides, a professor at Carnegie Mellon University, US, studies facial recognition technology. “As we get older,” he said, “our faces change shape, but not the area around our eyes. It stays the same—even if we put on weight.”

Another company has also been working on this kind of software. Tech5 has AI that measures the shape of your face. It also scans your iris（the colored part of your eyes）. Tech5 hopes to ignore all of the face below the nose.

Facial recognition software is about more than just unlocking your phone. It's about public safety. Touchless verification（验证）has become extremely important due to the COVID-19. More than that，facial recognition can be used to fight crime（犯罪）. “It can detect crime suspects,” said Huang Lei, Hanwang's president. Hanwang's technology is used by police in high-security settings. This means places like government buildings, subway stations and airports. Huang admits one big weakness of this new technology: It fails when people wear both masks and sunglasses. “In this situation, all of the key facial information is lost, but I believe we can overcome the weakness in the future,” said Huang.

Over a cup of iced tea at the midtown Radiance Tea House&Books,whose noise is not much louder than a coffee machine's,Gregory Scott Farber,a non-practicing lawyer who works as a research analyst, described SoundPrint he created as"Yelp for noise". SoundPrint allows users to search for and grade restaurants and bars according to their sound level. "laces are getting louder,"Farber said. "People tell me thirty or forty years ago you could go somewhere to eat and expect to have a conversation. "

Farber suffers from permanent hearing loss,caused by meningitis(脑脊膜炎)which he contracted when he was a baby. Like so many great inventions,Farber's invention arose from a desire to find love-or,at least,a place to have a date. "When I was dating,I put a lot of efforts into trying to pick quiet spots,"he said. "I'd google' quiet restaurants'. Then I would show up,but it would be noisy. " His hearing aid helped,but not enough. "Out of curiosity,I started taking decibel(分贝)measurements. "He sent a list of his favorite quiet places to friends in the hearing-loss community,and soon found many requests from his normal-hearing friends.

SoundPrint includes a sound-level meter,so diners and drinkers can take measurements using their smartphones,and upload data to the database. Farber said that the app brings no profit. SoundPrint covers about two thousand cities,though only fifteen have a significant number of users. Farber recently analyzed the data from 2,376 Manhattan restaurants and bars,and the findings are not good for ears. More than 70%of the former and 90%of the latter were rated as"loud"-defined as between 76 and 80 decibels,or as noisy as an air-conditioner.