Data of Drones

Neu Robotics
Dec 8, 2017 · 4 min read

With countries revolutionizing how data is collected and used, some using it to generate quotas, while others using it to develop Social Credit Systems we see a huge influx of data collection becoming the new norm. So how do you collect such data and segregate it accordingly.

From the eyes of Neu Robotics Platform

Why data is important ?

Ability to detect faces and their distances for close warehouse drones

Imagine a world where many of your daily activities were constantly monitored and evaluated: what you buy at the shops and online; where you are at any given time; who your friends are and how you interact with them; how many hours you spend watching content or playing video games; and what bills and taxes you pay (or not). It’s not hard to picture, because most of that already happens, thanks to all those data-collecting behemoths like Google, Facebook and Instagram or health-tracking apps such as Fitbit.

But this same idea of intrusion which is applied to personal products if applied to commercial applications it can help evaluate a company and its process better.

Now imagine a way of storing every tiny detail about every asset, customer requests or services for your business, segregating it and then appointing it to the various patterns of change happening in your business. If you do imagine such a future for your company, you have already done step 1, that is be living in this generation.

How to data is collected?

Neu Robotics Inc AoX collecting data over construction sites

Data can collection is a sole function of the utility of the data. Data can vary from being just crunched numbers to complete recognition of objects to actual determination of their actions over time. What drones enable us to do is to collect such vast amounts of data that humans haven't been able to tap into and convert it all into models usable. But that’s not the only data which can be recorded by a drone, 3-d data is collection is the new norm to ensure integrity.

Operating at various construction site, here at Neu Robotics Inc we follow a dedicated process of how we work with since we make sure our customers are getting familiarized with the entire process . Our survey process constitutes of 3 steps:

1.Preemptive Calculations:

Once a client consults us and gives us all the information about the survey details, we input it into our system and compute the optimum height of flight and speed of flight and make sure with our app that the survey area is permitted for unmanned flights.

2.Survey Flight with Ground Control Points:

On the scheduled day of survey, the Pilot-In-Command(PIC — FAA 107 Pilot) and Visual Observer check the site for any kind of obstructions or any kind of violations before the flight after laying down the GCPs according to their GPS locations. The flight plan is programmed into the drone as per the requirements of the topology and geometry of the survey plot.

3.Post Processing of Data:

Once the flight is done then data is stored on the hard drive on board which can either be manually connected or downloaded into our cloud once there the 3-d regenerated models accurate up to an inch ready to be imported into your legacy programs for GIS or Civil based calculations.

How is this data utilized?

Metadata is data that describes other data. Metadata summarizes basic information about data, which can make finding and working with particular instances of data easier. The data collected by the drone is images and location of points. Once this data is processed by our cloud, it can be used differently for different purposes and that is the real beauty of this data.

We have supplied clients with 3-d models of the terrain for different reasoning from being just for marketing purposes of the property to architects who want to develop additional floors upon buildings to make the view more scenic for its customers.

This amount of detail and fluidity of such information enables companies and contractors to move with greater efficiency and plan out moves strategically.

Calculating volume fills with our 3d generated models with AutoDesk Infraworks

Apart from construction based data we have also experimented with various machine learning programs like tensor flow where we manage to teach our platform how to identify new objects, teaching how to count. One of the major experiments with AoX is for it to start identifying cars by their make and start identifying number plates to understand traffic patterns for many cities and helping them optimize their traffic algorithms.

Since the platform has ability to traverse indoors, we operate it to understand assets in-house thus helping a initiative for asset tracking for a lot of companies. I hope that this article made sense to you with respect of drones and their data, and how by tiny steps we are ensuring that companies are running at their full efficiency.

— Nitesh Panchal

Chief Technical Officer at Neu Robotics Inc

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade