BayesMap Solutions

The company BayesMap Solutions was established in October 2014 with the objective to provide unique consulting and software development services for the airborne Lidar industry. The main focus is data processing, providing fast and effective solutions to challenging problems. The company helps clients extract a maximum of information from large and complex datasets and to significantly increase the accuracy of data and derived products.

BayesMap Solutions was founded by André Jalobeanu, who obtained a PhD in image processing from INRIA Sophia Antipolis, France. Before starting BayesMap, he worked as a research scientist in France and Portugal, and then as a research fellow at the Naval Postgraduate School in Monterey, USA. He has been doing research in data processing and analysis (images, signals, time series and point clouds) for more than 15 years, including in Lidar for the past six years. The methods he developed all use Bayesian inference, with an emphasis on automation and uncertainty estimation. In a Bayesian framework, rigorous sensor modelling combined with expert knowledge leads to optimal solutions, which can be point clouds, geometric parameters or elevation models depending on the needs. Probabilistic modelling enables the user to obtain something new: uncertainty attributes and spatial accuracy maps. This is achieved by propagating errors from input to end result. All data sources are combined in a consistent way and automatically weighted by the software, avoiding arbitrary cuts and losses and costly user interaction.

André Jalobeanu decided to start BayesMap to apply these concepts and recent research results to the Lidar mapping industry. In the early days, the first clients purchased consulting services to have strip alignment done using prototype BayesStripAlign software. Due to high demand, this package was the first to be developed (despite extensive experience with waveforms). Production-ready BayesWavEx followed one year later, offering vendor-neutral point cloud extraction from LAS 1.3 waveforms. 

Current profile

BayesMap Solutions is a limited liability company (LLC), now based out of Pleasanton, California, USA. It is managed and operated by the founder, who is also the software engineer. Technical support is provided by the software developer (same day with a fast-lane production licence). BayesMap uses a client-centred approach to product design and development. The small size of the company allows for great flexibility, enabling client requests to be handled and new capabilities to be implemented in a short time. The company offers discounts depending on the client’s corporate social responsibility statement and ‘green’ engagement. Academic pricing is available for research institutions. 

The main business is software and consulting, with a focus on improving data quality and helping clients to reduce collection costs. While it started with traditional airborne Lidar, the company now also provides geometric correction for unmanned aerial vehicle (UAV) sensors, which often follow a more complex trajectory than large aircraft. Increasing the performance and reliability of software products is a priority, through algorithmic development and code optimisation as well as constant feedback from users. All packages are independent, use a simple yet powerful command-line interface and come with a free 30-day evaluation period and full support.

Many people are frustrated with money-wasting practices such as flight-line edge cutting, flying low and calibration lines. At BayesMap, the power of Bayesian inference is leveraged to make the best use of all available data without throwing away anything useful. This approaches allows BayesMap to fly higher and still get high-quality results, thus reducing collection costs. And use only regular flight lines for sensor calibration.

Global scope

The target markets are mainly airborne Lidar data providers, systems builders and research institutions from all countries. Current clients are located in France, Germany, Australia, Canada and the USA. A simple licence management scheme allows the rapid set-up of node-locked trial and paid licences via email, after an EULA is signed electronically via PandaDoc. Support is also provided by email, within one or two business days for production, depending on the licence tier. Quick to install (no dependencies) and compatible with 64-bit OS (Windows, MacOS), the software packages are simple to use for those familiar with LAStools. As the main input is raw data, or uncorrected georeferenced point clouds (billions of waveforms or points), having the software in the same location as the data saves time. This is why BayesMap does not currently provide cloud solutions.

The company offers the following software packages:

• BayesStripAlign 2.0: automatic point cloud registration, geometric correction, quality control – this is BayesMap’s flagship product.
• BayesWavEx 1.0: waveform processing with original attribute extraction such as range uncertainty and target thickness, removes detector artefacts, robust to overlaps.
• BayesCloudChange (under development): automatic detection of significant changes between point clouds (vertical differences and horizontal displacements).
• BayesAccuGrid and other, smaller packages, planned: 3D surface reconstruction with error propagation, de-noising and other features, depending on demand.
  
  

Looking ahead

The main objectives of the company in the near future are as follows:

• To develop research-grade science to serve efficient problem-solving. To continue its research and development efforts to meet ever-more demanding client needs and adapt available tools to new sensors such as photon-counting and bathymetric scanners. To develop new algorithms to tackle complex topology arising in terrestrial and close-range scans.

• To strive for enhanced accessibility through graphical user interface design, allowing users who are unfamiliar with command lines to immediately use all the functionalities. 
• To propose workshops and training sessions within professional meetings or directly with the client. 
• To contribute to brain-storming over data formats, e.g. to include range or point uncertainty in final data products. BayesWavEx already computes range uncertainty and stores it thanks to extra LAS attributes, enabling rigorous error propagation to derived products such as elevation models.
• To start hiring to enhance client-training capabilities, deal with the increase in support requirements and help develop B2B and product sales. 

For more information visit www.bayesmap.com.

Every month GIM International invites a company to introduce itself in these pages. The resulting article, entitled Company's View, is subject to the usual copy editing procedures, but the publisher takes no responsibility for the content and the views expressed are not necessarily those of the magazine. 

The Impressive Contribution of Geomatics to Autonomous Driving

Since Karl Benz was granted a patent for his first internal combustion engine in 1879, the automotive industry has changed substantially. Or has it? The main principle remains the same: cars still have four wheels, a petrol- or diesel-powered engine – electric cars are still underrepresented and so far there are just a few hydrogen cars publicly available in select markets – and they still need to be driven by a human being. However, a major change is just around the corner: self-driving vehicles. And they won’t get far without geomatics technologies.

(By Wim van Wegen, contributing editor, GIM International)

Not only car manufacturers such as Ford, Volvo, Tesla (Figure 1) and Mercedes-Benz (Figure 2), but also the likes of Google and Uber have been testing autonomous vehicles over the past few years. Volvo recently announced it is looking for drivers who are interested in participating in its self-driving cars trial, reportedly the largest conducted by the automobile industry so far. Operating the car should be as easy as using a smartphone, the Swedish carmaker states. Great strides have been made in the development of the next-generation car, but what is the technology behind it? This article zooms in on the key role geomatics plays in autonomous driving.

GNSS

Self-driving cars can navigate on their own, which already implies that geomatics is involved. Global navigation satellite system (GNSS) technology provides the accuracy that a vehicle requires to be self-driving. A high-precision and reliable localisation solution is fundamental. Just imagine, for example, what could happen if poor localisation positions the car on the wrong side of the road. Therefore, the availability of accurate and reliable GNSS technology is a major challenge to the advancement of autonomous driving. Only the most sophisticated GNSS receivers are suitable for use in self-driving cars. Those receivers rely on multiple frequencies and use multiple constellations. GNSS positioning is combined with an inertial navigation system(INS), creating a powerful system that compensates for the inherent weaknesses that occur when just one system is used. Additionally, anti-jam technology is used to provide the required positioning and sensor integration.

One of the companies known among geomatics professionals focusing on autonomous cars is NovAtel. The Canada-based GNSS specialist states that its technology is capable of providing decimetre-level accuracy to ensure a vehicle stays in its lane and/or at a safe distance from other vehicles. NovAtel aims to develop solutions that make driverless cars a common sight on our roads, providing the autonomous driving positioning reference. The Canadians therefore have established a special engineering team – the Safety Critical Systems Group – dedicated to developing functionally safe GNSS positioning technology for fully autonomous applications.

Optical Cameras

Several camera technologies are being applied in the self-driving car industry, each with their own advocates. For example, Tesla uses cameras as a primary sensor and has equipped its cars with eight monocular cameras. Stereo cameras, on the other hand, give the car depth of field that can be compared to human vision. Stereo cameras also offer the advantage of being cheap to produce while providing high-quality measurements in real time. However, some claim that fisheye cameras are an even better alternative, as these are capable of covering a wider field of view as well as of detecting obstacles in the very near vicinity of the car that are often not seen by a binocular stereo camera set-up ([1] Christian Häne et al).

Radar

On-board radar technology increases the safety of passengers, a fundamental issue in autonomous driving. Radar sensors are mounted on the car’s front and rear bumpers, giving the car awareness of what is in front of and behind it. The car will maintain a safe distance (two seconds) from the car ahead. When equipped with radar technology, the car automatically speeds up or slows down depending on the behaviour of other vehicles. In fact, radar observes the (changing) distances between the car and other vehicles. The software interprets the data and sends a signal that the car needs to accelerate or decelerate.

A recent development in the field of radar technology is vehicle-to-everything (V2X) radar. This combines vehicle-to-vehicle communication and vehicle-to-infrastructure technology, while operating on a single antenna. Radar has a big advantage compared to other technologies: it can cope with weather conditions such as fog, snow and heavy rain. V2X is able to instantly detect vehicle speeds, thanks to Doppler measurements, ands 360-degree sensing from a single antenna. These capabilities make V2X radar an important step in developing new sensors for autonomous vehicles.

Lidar

In the automotive industry, Lidar is usually applied as a spinning cylinder mounted on the vehicle’s roof. Laser pulses bounce off the surrounding objects, the time of flight is measured and, thanks to real-time processing of the Lidar data from the 360-degree sensors, the car ‘knows’ exactly how far it is away from other objects. As Lidar functions as the eye of driverless cars, it is no surprise that most self-driving car solutions use Lidar as the main sensor. Lidar is essential for emergency braking, pedestrian detection and collision avoidance.

In August 2016 Velodyne LiDAR, a global leader in Lidar technology, announced that it had received a combined USD150 million investment from co-investors Ford and China’s leading search engine company, Baidu. The investment will allow Velodyne to rapidly expand the design and production of high-performance, cost-effective automotive Lidar sensors (Figure 4). This step paves the way for mass adoption in autonomous vehicles and so-called Advanced Driver Assistance System (ADAS) applications and will thus accelerate the critical, transformative benefits they provide. Lidar technology has been recognised by global automotive companies as a critical enabler in the development of fully autonomous vehicles. Meanwhile, in December 2016, Magna – a leading manufacturer of auto parts – and Innovize revealed that they are partnering to deliver Lidar remote sensing solutions for the implementation of autonomous driving features and full autonomy in future vehicles. These are just two examples of the automotive industry investing in Lidar, and several well-known carmakers have also shifted their focus onto Lidar. Most self-driving concept cars rely on radar and Lidar to cross-validate what they are seeing and to predict motion.

Most self-driving cars rely on Lidar, but Tesla is an exception. So far, the owner of the company, the eccentric billionaire Elon Musk, is sticking to conventional radar combined with ultrasonic sensors. Musk has repeatedly dismissed the need for Lidar, stating that it makes no sense in the context of driverless cars. However, in view of the indisputable fact that the cost of Lidar technology will fall, it is not entirely unlikely that Teslas will also be equipped with Lidar sooner or later.

Artificial Intelligence

Ford is not only focusing heavily on Lidar technology. In February 2017, the firm declared it will be investing USD1 billion over the next five years in Argo AI, an artificial intelligence company – interestingly enough founded by former Google and Uber leaders. The idea behind this massive investment is that Argo AI’s robotics experience and artificial intelligence software is essential to further advance driverless cars. The key objective of this cooperation is a new software platform for Ford’s fully autonomous vehicle due to be launched in 2021.

3D Maps

The advancement of autonomous vehicles is a driving force behind the collection of point clouds around the world. Maps for self-driving cars need to provide more information at a higher fidelity and accuracy, comprising features such as lane markings and roadside barriers. High-definition (HD) map datasets deliver high-precision intelligence on road features, e.g. painted lines, signs, 3D building models, signals, stop signs and parking spaces. So-called self-healing mapping systems provide a state-of-the-art solution for autonomous cars. They solve the problem of out-of-date navigation data since they give cars the intelligence to update their own maps. Autonomous vehicles will be able to acquire and process data and convert it into useful information while on the road. In addition, the cars will be connected with the cloud in order make the right decisions about where they are going, including choosing the optimal route.

A mapping system for self-driving cars, designed to help carmakers, map companies and start-ups to rapidly create HD maps and keep them updated, is being offered by companies such as TomTom, HERE, Nvidia (Figure 6) and Sanborn. An interesting project is underway in Japan, where a consortium of car manufacturers is taking part in the Dynamic Map Planning initiative, initially set up by Mitsubishi Electric. Nine carmakers are teaming up with the mapmakers from Zenrin. The association will create a digital chart of the nation’s key expressways by driving specially equipped vehicles over them. Japan aims to have autonomous cars on its roads on a considerable scale by the 2020 Tokyo Summer Olympics.

Fundamental Factors

A driverless vehicle needs to be able to understand in real time what is happening around it, precisely locate itself on an HD map, and plan a safe path forward. The world’s most advanced self-driving car platforms combine deep learning, sensor fusion and surround vision for an optimal driving experience. GNSS, ranging and 3D mapping systems (in particular Lidar), and artificial intelligence are making this possible. Therefore, they are all fundamental factors in the future success of the autonomous car as a game changer in transportation, as Lidar has already proven to be in the world of autonomous vehicles. What perhaps counts against Lidar is its price tag, especially compared with technologies such as cameras, GPS-like data or radar, but thanks to technical innovations this obstacle is gradually being eroded. As a report by Market Research Future indicates, the global autonomous vehicles market is expected to reach a value of USD65.3 billion by 2027. Hence, the best advice to the geomatics sector is: fasten your seatbelt and enjoy the ride!

Acknowledgement

Thanks to Sabine de Milliano for reviewing the article and her valuable suggestions for improvements.

Further reading

• [1] Christian Häne, Torsten Sattler, Marc Pollefeys: Obstacle Detection for Self-Driving Cars Using Only Monocular Cameras and Wheel Odometry
• Driving towards the Autonomous Vehicle: European GNSS Agency (gsc-europa.eu)
• Mathias Lemmens: Photon Lidar, a Promising Advance in Mapping Applications; GIM International
• Steve Crowe: How AI is Making Self-Driving Cars Smarter; Robotics Trends
• John Ristevski: Building a Global 3D Routing Map, GIM International

Biography of the author

Wim van Wegen is content manager of GIM International. In his role, he is responsible for the print and online publications of one of the world’s leading geomatics trade media brands. He is also a contributor of columns and feature articles, and often interviews renowned experts in the geospatial industry. Van Wegen has a bachelor degree in European studies from the NHL University of Applied Sciences in Leeuwarden, The Netherlands.

wim.van.wegen@geomares.nl

Survey of Geomatics Professionals Reveals Valuable Insights

At the start of this year, 'GIM International'conducted a readers’ survey aimed at gaining a clear picture of the current state of the geospatial industry. With more than a thousand replies received, the response was better than expected and resulted in valuable insights: which new technologies hold the most promise? What is the role of UAVs in today’s geospatial industry? Which other market trends are visible? And how do geomatics specialists view the future of their profession? With consideration of various fields of application – such as mining, forestry, agriculture and building & construction – this article takes you on a journey through the geospatial landscape in 2017.

(By Wim van Wegen and Martin Kodde, GIM International)

GNSS, Lidar, photogrammetry, remote sensing, total stations and unmanned aerial vehicles (UAVs or ‘drones’) are all being used on a large scale. The total station has been called ‘the surveyor’s workhorse’ and is still a familiar sight in today’s world. Building information modelling (BIM), a topic that has received overwhelming attention during trade shows and conferences in the last couple of years, is being adopted slowly but steadily. As the survey reveals, many geomatics professionals are confident that BIM will evolve to play an increasingly crucial role in building documentation, and just over 20% of the respondents are already working with BIM. While BIM is still establishing itself, geographic information systems (GIS) have already secured a solid position in the market and are now commonplace.

GIS and Data

GIS technology is widely recognised by the respondents as a major enabler in their field. Almost 75% of the GIM International readers participating in this survey indicate that they use GIS on a regular basis in their work. Typical GIS usage still mostly relies on desktop applications, with a mere 5% of the respondents indicating that they have fully switched to online GIS, aided by products such as ArcGIS Online or Smart M.apps. The adoption of online GIS systems is currently greatest among end users of geographical information, whereas geoinformation professionals continue to require the extra power of a desktop application. The general belief among almost the entire group of respondents is that this situation is likely to change soon, however. For all manner of usage purposes, they expect the transition from desktop to online GIS to be completed in the next five years at most. This quick transition fits in with the professionals’ general views of rapidly advancing digital technologies, with cloud technology as another major enabler. However, some readers rightfully point out that limited bandwidth and unreliable connectivity are major hurdles in regions such as Africa. If those issues are not addressed, the transition is expected to take a decade or more.

As the capabilities of GIS software expand, it facilitates the handling and processing of multiple types of data. This is resulting in ever-growing volumes of spatial data being stored by our respondents. In total, the survey participants store more than 84 petabytes of spatial data (1 petabyte equals 1,000 terabytes). If we extrapolate this to the entire geospatial industry, the amount of spatial data that is stored around the world is mind-boggling. However, that data is not evenly distributed throughout the industry: 80% of all data is held by less than 10% of the organisations participating in this survey, with only a handful of organisations storing over 10 petabytes of data. On average, most respondents currently store maximum 30 terabytes of data. Lidar data and satellite imagery are quoted as the largest datasets.

In contrast to the high adoption rate for GIS, the usage of BIM is still limited at only 20% of the respondents. BIM scores slightly higher in the infrastructure and oil & gas industries, but adoption remains low in the building & construction market. Given the growing importance of BIM, in particular for building & construction and infrastructure, this situation will need to change rapidly. The sheer amount of attention paid to the subject at the leading trade shows and conferences indicates that visionaries within the industry are aware of this fact – now the rest of the market just needs to realise it too. 

UAVs Become Mainstream

Visitors to geospatial events were first confronted with a significant number of exhibitors showcasing their UAVs about five years ago. Back then, sceptics dismissed them as a hype. Now, just a few years later, the UAV has become a major tool for the professional surveyor. Findings from our readers’ survey show that 37% of geomatics professionals make use of UAVs. They are widely utilised in all fields of application, with miningand agriculture topping the table. Projects in those fields tend to be less affected by legislative restrictions than, for example, urban locations, which has led to quicker adoption.

One eye-catching development in the surveying profession is the integration of UAVs and Lidar, which has only been commercially possible for the past couple of years. Despite this short market availability, the UAV plus Lidar combination is rapidly gaining ground among surveyors. Results from the GIM International readers’ survey indicate that 15% of respondents use unmanned methods to capture Lidar data. With new (lightweight, flexible, easy-to-use and reasonably priced) solutions entering the market all the time, this trend seems set to continue. It’s worth mentioning that there is also a significant market for high-end solutions, which may not be affordable for everyone.

The fact that UAVs are here to stay is good news – not only for manufacturers of unmanned aerial vehicles, but also for software developers since there is a rising demand for accurate and easy-to-use point cloud processing software for UAVs. Agisoft and Pix4D currently top the list of the most-used software solutions, but the readers’ survey shows that there are many competitors in their slipstream; in this growing market, there are still plenty of opportunities for other providers.

Disruptive Technologies

For the purpose of the survey, GIM International identified IT, robotics/autonomous vehicles, apps/mobile devices, augmented reality, virtual reality, artificial intelligence, Internet of Things and blockchain as all being potentially disruptive technologies. The responses show that almost all of these are regarded as having a significant impact on the geomatics industry, except blockchain. This is somewhat surprising, especially given the fact that about a quarter of the respondents are working in the land administration sector and several recent articles in GIM International have advocated the potential of blockchain for land management purposes.

The respondents’ top three disruptors include apps and mobile devices. These do indeed offer endless possibilities and are increasingly being used for cadastral purposes, as highlighted in the article ‘Light Mobile Collection Tools for Land Administration’ by Mathilde Molendijk, Javier Morales and Christiaan Lemmen. And as Brent Jones, Esri’s global manager for land records and cadastre, wrote in a column for GIM International, “By combining technologies and leveraging standards, geospatial mobile apps can be rapidly deployed, eliminating the obstacles that typically impede land administration progress in developing economies”.

Two of the buzzwords that have been heard at geomatics trade shows across the globe in the past year are virtual reality (VR) and augmented reality (AR). In numerous keynotes and presentations, both technologies have been hailed as two powerful tools that may well make a revolutionary impact on the survey industry. But although the spotlight has been shining brightly on VR and AR, today’s geomatics professionals have relatively subdued expectations of working in a virtual or augmented world. The question is: are geomatics professionals simply more conservative than their peers in other industries, or are VR and AR – apart from being nice gimmicks – not actually beneficial for geomatics applications?

Rather than being a single, homogeneous world, the geomatics sector is made up of numerous different fields of application, and the perceived disruptive potential of some technologies varies depending on the respondent’s particular field of work. Opinions are divided on the benefits of artificial intelligence (AI), for example. Geomatics professionals in agriculture (who rank AI as the second-most disruptive technology) and forestry (who even rate it as number one) are currently the most enthusiastic about the potential of AI. Perhaps the other geomatics professionals will become convinced of the opportunities AI offers in their work in the near future.

Market Trends

The responses to the survey paint a generally positive picture of the market situation. On average, over 70% of respondents believe that the market in which they are active will grow in the near future, while a further 20% expect it to stabilise. This sentiment is echoed throughout all market sectors but is most notable in mining, where a hefty 40% expect stabilisation of the market conditions. Among those respondents who expect their sector to decline, over 20% believe that there is still room for survey services to grow within that sector.

The overwhelming majority of respondents, more than 90%, anticipate that private-sector organisations will play an increasingly important role in the geoinformation market – even in land management, an area traditionally dominated by government organisations. Nonetheless, knowledge development remains a great concern. Multiple respondents from different regions and market sectors explicitly express their concerns about the lack of new students and professional development. This seems to be an issue that needs to be addressed if the geoinformation community wants to successfully capitalise on the expected market growth.

The Future of Surveying

An often-heard remark is that the role of the professional surveyor is changing. Some people even say that anyone will be able to be a surveyor in the future, thanks to technological developments making it easier to operate equipment and lower prices making geomatics solutions more widely available. “Many jobs that don’t require high precision will be performed by non-surveyors using mobile apps. Examples are preliminary surveys and estimates in farming and construction. Our job as surveyors will be more focused in areas and jobs that require specific knowledge and higher responsibilities,” states one of the respondents.

Another development is the need for real-time data, which requires the time between acquisition and visualisation to be reduced. This can only be achieved by fully automating the data processing, which will change the work of surveyors currently involved in that step. 

Tech-savvy

Traditional survey techniques are still widely used and highly valued by readers of GIM International, but newly emerging geoinformation techniques are entering the arena. Although there may be a slight difference between the perception of geomatics professionals and the disruptive technologies that are being developed in parallel to the geomatics world – one may not always be aware of advancing technologies just around the corner – it is safe to say that future surveyors must be tech-savvy. Maybe this perspective will open up new opportunities to attract more young people into relevant education and subsequently the industry, as a career as a geomatics professional will be full of appealing high-tech devices and software. A marketing strategy to highlight the cool factor of ‘geo’ would be a great step in the right direction!

The Authors

Wim van Wegen

Wim van Wegen is content manager of GIM International. In his role, he is responsible for the print and online publications of one of the world’s leading geomatics trade media brands. He is also a contributor of columns and feature articles, and often interviews renowned experts in the geospatial industry. Van Wegen has a bachelor degree in European studies from the NHL University of Applied Sciences in Leeuwarden, The Netherlands.

wim.van.wegen@geomares.nl

Martin Kodde

Martin Kodde is a specialist in the field of geomatics with a keen interest in real-time 3D data acquisition. He has a bachelor degree in geodesy from Utrecht University of Applied Sciences and a master degree in geomatics from Delft University of Technology, both in The Netherlands. Kodde leads the Geo-ICT department at Fugro in The Netherlands, where he is also responsible for R&D in geoinformation. He is also a contributing editor for GIM International.

mail@martinkodde.nl