Artificial intelligence benefits for geospatial-focused drone businesses

July 19th, 2019, Published in Articles: PositionIT

Geospatial insights are in high demand and automating the feature extraction process is key to scaling up your aerial mapping services.

Along with the hardware and software sectors, the drone services market is the largest segment in the commercial drone industry with the strongest expansion. According to the market research report “Global Drone Service Market Analysis & Trends – Industry Forecast to 2025”, the drone services market is estimated at $4,4-billion in 2019 and is projected to reach $63,6-billion by 2025, at a CAGR of 55,9% from 2019 to 2025.

This is a huge opportunity for drone service providers. The key for capturing a share of this growing market is to offer turnkey business solutions beyond data capture, such as mapping, surveying and specialised geospatial analytics.

Geospatial insights are in high demand, with more businesses relying on location data to optimise their daily operations and planning or gain first-hand market insights. The drone service market grows as an effect of this increasing demand for geospatial insights. Furthermore, business and industries in need of geospatial analytics are increasingly diverse, ranging from farmers to utility companies. All of these businesses need the number and the location of each of the objects they are tracking.

Most of the drone service providers excel at generating photogrammetry-based mapping and surveying products. However, delivering geospatial insights derived from these products can be challenging and it starts to become a bottleneck. No one questions the potential value that these insight-rich geospatial products can add to their services, but they are hard to scale.

Manually extracting the features that clients are interested in is time-consuming and costly to scale up. Automating this process by hiring highly specialised professionals  (such as machine learning experts, computer vision specialists and data scientists) and investing in infrastructure is not an option for small and medium-size drone service businesses.

A cost-effective solution to automate the feature extraction process and increase the geospatial analysis production capacity is to use a cloud-based artificial intelligence (AI) object detection platform. Incorporating such platforms like Picterra into a drone service business has multiple benefits.

Fig. 1: Benefits of AI-based drone imagery analyses.

Reduce turnaround time

AI can not only improve the accuracy of a project, but can also reduce the time-to-delivery. The entire workload of mapping, detecting and extracting data can last up to days when done manually. Automated detection shorten the delivery time from days to minutes, and frees you up from the repetitive manual process to work on a new project or acquire new clients.

Accuracy

In addition to the scale at which it can operate, AI can also improve the accuracy of the detections. This is because AI-powered platforms are able to cover large areas and spot tens, hundreds or thousands of objects in seconds. Performing the same steps accurately every time they are executed allows you to focusing human expertise on challenging and rare features.

Avoid infrastructure investment and reduce labour costs

Cloud-based AI platforms takes away the need for you to invest in infrastructure like graphical unit processors or R&D and other specialised expertise which are expensive. The same heavy workload being repeated with every project requires more cost and labour to deliver the results in time. In contrast, once created ,  automated detection can be executed again and again, without additional cost at a much faster pace. By integrating AI in the process, the overall timespan can be reduced which translates directly into cost savings.

Fig. 2: Example of automated imagery analyses of different objects.

Serve diverse markets with a single tool

Using a single tool for all of your feature extraction projects can maximise your return on investment. The versatility and flexibility of the object detection algorithms that platforms such as Picterra deploys, allows users to customise them and count objects ranging from trees, sheep and solar panels to shipping containers or buildings. At the same time, users are able to create a custom detector for any other type of objects.

Streamline workflow integration

Platforms like Picterra allow you to run AI object detection on orthophotos produced with any photogrammetry software in the market, be it Reality Capture, DroneDeploy, Agisoft Metashape, SimActive Correlator3D or Pix4Dmapper. It allows you to analyse the detections, derive statistics and generate customised reports you can deliver to clients. Uses can also export the detections as georeferenced layers in various formats that are optimised to match a workflow in ArcGIS and other GIS software.

Easy learning curve

Like other technologies, AI has become a lot more accessible and easier to use. AI platforms like Picterra offers an intuitive user interface to build and run custom detection algorithms in a short time.

Examples of detection algorithms

After the acquisition of aerial images over an urban scene, an orthomosaic has been uploaded to Picterra to localise and map seven categories of objects. The detections can be exported in a range of popular GIS formats (KML, GeoJSON, Shapefile) and PDF reports can also be also generated.

Fig. 3: The analysed data can serve various applications.

  • Road marks: Up-to-date detections provide key insights to local infrastructure and traffic agencies or insurance companies when analysing the geographic prevalence and distribution of traffic accidents. Moreover, this supports an efficient maintenance planning of road marks.
  • Solar panels: Determining their prevalence and geolocation unlock key market insights for energy companies and solar panel manufacturers. Optimised management of the demand and supply of renewable energy requires also up-to-date information on the solar panel locations.
  • Manhole covers: Water and utility companies need this information in order to plan maintenance and network expansion.
  • Trees: Detecting trees in proximity to key assets provides insurance companies with valuable risk assessment information. Detecting trees encroaching buffer zones is also useful to infrastructure planning such as gas pipeline or overhead power lines.
  • Roofs: Up-to-date detections give local governments and insurance companies insights on discrepancies on declared values and a correct parametrisation of the prime.
  • Swimming pools: Local governments can localise swimming pools and compare this information with building permit registers. Moreover, tax declaration discrepancies can be spotted.
  • Vehicles: Local governments to plan parking infrastructure and road network adaptations and real estate agencies to spot and assess most frequently visited areas and shop windows.

Check out the project here: http://app.picterra.ch/shared_projects/ee3ee4b7-114b-42e1-8eac-cd9cb2168bd5

Contact Veronica Alonso, Picterra, veronica.alonso@picterra.ch

Related Articles

  • Earth observation challenge seeks mining solutions
  • Geospatial Round-up – Sept/Oct 2019
  • Major improvements to airborne urban mapping solution
  • Versatile fixed-wing drone portfolio showcased
  • Rapid urban mapping system product range expanded