Day 61 of 100DaysofML
Usage of ML in Google Maps. So a lot of the routing on google maps is done with the help of an application of AI which is used every time we are routed from point A to point B. So there are a number of factors that go into understanding routing on a map. These days, Google is coming out with new features that help us in mapping real world orientation and features on our phone using the power of AI and ML. There are obviously a number of factors to consider for the implementation of this feature and I just wanna go over the highlights of them.
Google Maps already maintains a concentrated network and can identify the traffic and width of almost each and every street using this. Along with this, google is also making use of complex models in order to deploy buildings on maps.
The flaw that was noticed before was the Google’s algorithm tried to predict whether a certain portion of the image was a building or not but the algorithm dint achieve a lot of success because of which the team at google tried to focus on a different approach whereby they tried to trace common building outlines manually, and then used this information to teach the machine learning algorithms which images correspond with building edges and shapes. This technique proved effective, enabling Google to map as many buildings in one year as they mapped in the previous ten years.
The advances in AI shows that Google Maps will soon create Street View-style visual guides for step-by-step directions overlaid onto the real world, as viewed through the smartphone camera. Going one step further, the company plans to integrate its Assistant, equipped with the computer vision platform Google Lens, into Maps. That way, you’ll be able to pan over a city street and see pop-ups highlighting restaurants and other locations in real time.
VERY IMPORTANT USAGE OF ML IN GOOGLE MAPS: Google has come up with a new way to keep people informed, in real-time, about the status of their bus rides. Google Maps will has predictive capabilities enabled through machine learning in order to inform passengers well ahead of time if their buses are going to encounter some obstacles. It now provides real-time tracking data, which can forecast delays in hundreds of cities worldwide.
One important application is that Google is implementing machine learning in order to identify car license plates and this is being done using Google’s own ML library-TensorFlow. The same technology is now being used in order to fetch information from street signs. Using this technology, Google aims to improve the location data of about one-third of the world’s addresses. The latest Machine Learning algorithms helped achieve 84.2 % accuracy when tested on several challenging street signs in France. These statistics significantly outperformed the previous state-of-the-art systems.
The whole point is that Google is using OCR and Deep Learning techniques in their street view whereby they try to identify number plates and street signs. You may ask how this is useful? The main application would be in order to locate each of these vehicles or even in order to identify the speed limits on each of these streets. I shall be doing a blog very soon for sign detection using OCR technology.
Just want to keep this blog brief. Shall be more consistent with the blogs here on. Thank you for the support. Keep Learning.
Cheers.
