LISTEN HERE OR WHEREVER YOU GET YOUR PODCASTS
Every building has its own geomagnetic fingerprint and by mapping that fingerprint against a floorplan of the building IndoorAtlas is able to provide accurate location and navigation inside. The genius of this system is that it takes advantage of an existing geomagnetic infrastructure.
IndoorAtlas’ approach to indoor positioning stems from academic research about the geomagnetic fingerprint of a building. Although the geomagnetic field from the earth is present everywhere, which means also when a person is inside of a building, its metal structures will interact with the geomagnetic field, therefore creating a unique fingerprint. IndoorAtlas’ technology uses the compass of mobile phone to detect minute variations in the geomagnetic field due to the presence of a building’s metal structures. That information is then used to create an indoor map of these geomagnetic variations, which forms the basis for indoor positioning, where the geomagnetic variations around a person inside a building are compared in real-time with the earlier created geomagnetic map.
While the geomagnetic positioning is used as the founding position in IndoorAtlas’ technology, over the years the company has added many other algorithms on top of the geomagnetic field. This is done using other sensors that are available in modern smartphones, such as the accelerometer, radio, and the gyroscope. By taking advantage of all the sensors from a mobile phone and combining them, it becomes possible to create an indoor positioning estimate with an accuracy of 1-2m that can be put on a map to provide a similar experience to what people are accustomed to with outdoor GPS.
To be able to use IndoorAtlas’ technology, several prerequisites need to be met. First, a digital floor plan is needed of the building that will be mapped indoors. Second, physical access to the premises is required to be able to correct the geomagnetic fingerprint. Recording this fingerprint is done onsite using an Android phone with the IndoorAtlas map creator application installed, which requires online registration. After uploading the digital floor plans to an IndoorAtlas developer account, these need to be placed and scaled on a world map so that the uploaded floor plans will have the right size and orientation.
After the setup phase, the user can go to the premises to start what is called the “fingerprinting” process or creating the geomagnetic fingerprint of a building. This is done with the aid of a set of waypoints, which are easy to spot objects or places in both the real world and inside the floor plan. The user is required to click on the corresponding waypoint inside the mobile application when present near such a physical waypoint. This “fingerprinting” process provides the basis for the indoor positioning.
IndoorAtlas’ app requires an Android phone for the fingerprinting process. When performing the actual indoor positioning, an Android phone does not require any support infrastructure, as opposed to iOS phones that do, since Apple phones are not able to learn about the radio or wi-fi environment due to the system settings from the manufacturer. Using iOS phones requires some Bluetooth beacons to be placed inside the building, which is done with the IndoorAtlas beacon planner tool, that enables the user to draw the area where to perform indoor positioning on top of a floor plan and automatically creates recommendations where to place the beacons.
The number of beacons to be used will be 5-15% of what alternative indoor positioning solutions are using, as the IndoorAtlas primarily relies on geomagnetic technology. The reason this radio positioning technology is used, is to be able to meet the expectancy levels of people using GPS outdoors and provide that same experience indoors: this is possible using a two-step process that first gives a quick positioning using the radio technology and improves that with the geomagnetic technology resulting in accurate tracking when walking around the premises.
Although it is IndoorAtlas’ intent to minimize the amount of infrastructure to have everyone benefit from its technology, and ideally do without any additional infrastructure for the purposes of positioning, it must accommodate different mobile platforms and any possible operating system limitations.
Additionally, there is currently no single technology for getting good indoor accuracy. GPS radio for example requires a line of sight, so they do not travel indoors. This explains why it is necessary to combine multiple technologies for a good indoor location experience. Also, the scenarios differ for outdoor and indoor use cases, which makes indoor navigation a more challenging use case: for example, when outdoors, the typical use case for GPS positioning is car navigation, which comes with the constraints of driving on a given road and where the user is unlikely to make sudden movements to any direction as with indoor navigation.
Additionally, indoor navigation must be able to detect differences in altitude and different floors for multi-story buildings. IndoorAtlas solved this problem using a barometer when present inside a mobile phone, and, as an alternative, by using the building’s geomagnetic fingerprints which are different for each floor.
While there is no single company with an indoor solution that would be available everywhere on earth, IndoorAtlas is the only company that has taken the geomagnetic field of the earth as a core capability which might make them a global player in this space over time. However, as with all indoor technologies, their technology requires following certain workflows to do indoor positioning.
The benefits of indoor positioning are huge and will enable many other exciting services and use cases. For example, it can help users reduce stress levels when they are inside an unknown venue, such as a hospital or airport and need to move to an unknown destination inside that venue quickly. Especially when that venue itself is changing over time, indoor positioning has an added benefit for users. On the other hand, to build trust from the user’s perspective and motivate them to keep using indoor positioning services, their privacy needs be guaranteed, in combination with a pleasant user experience. Finally, to be able to build business models for indoor positioning technology, it is unlikely that the end user will be paying directly for the positioning capability, but the operator of a venue, such as a train or flight operator.
To put it simply, point clouds are a collection of XYZ points that represent some real world object of nearly any scale.They can be generated in a few ways. As geospatial scientists, we mostly work with LAS/LAZ data collected by aerial LiDAR (light detection and ranging) scanners at varying scales, from landscapes, down to project sites. We may also derive point clouds from highly detailed orthoimagery of an area, such as from the products of a drone flight.
As a data scientist, you don’t just go in and solve problems. You make recommendations to multi-faceted issues so that you get a fantastic model in the end. You’ll also be advocating a better use and understanding of the data while you do that.