CoChat
Sign Up
Cited by 187Augmented Reality ApplicationsDigital Transformation in IndustryInteractive and Immersive Displays

A Practical Evaluation of Commercial Industrial Augmented Reality Systems in an Industry 4.0 Shipyard

Open access
Blanco-Novoa, Oscar, Fernandez-Carames, Tiago M., Fraga-Lamas, Paula, Vilar-Montesinos, Miguel A.·2018·IEEE Access
DOI 10.1109/access.2018.2802699
Open this paper in CoChat — free account

Abstract

The principles of the Industry 4.0 are guiding manufacturing companies toward more automated and computerized factories. Such principles are also applied in shipbuilding, which usually involves numerous complex processes whose automation will improve its efficiency and performance. Navantia, a company that has been building ships for 300 years, is modernizing its shipyards according to the Industry 4.0 principles with the help of the latest technologies. Augmented reality (AR), which when utilized in an industrial environment is called industrial AR (IAR), is one of such technologies, since it can be applied in numerous situations in order to provide useful and attractive interfaces that allow shipyard operators to obtain information on their tasks and to interact with certain elements that surround them. This article first reviews the state of the art on IAR applications for shipbuilding and smart manufacturing. Then, the most relevant IAR hardware and software tools are detailed, as well as the main use cases for the application of IAR in a shipyard. Next, it is described Navantia's IAR system, which is based on a fog-computing architecture. Such a system is evaluated when making the use of three IAR devices (a smartphone, a tablet, and a pair of smart glasses), two AR software development kits (ARToolKit and Vuforia) and multiple IAR markers, with the objective of determining their performance in a shipyard workshop and inside a ship under construction. The results obtained show a remarkable performance differences among the different IAR tools and the impact of factors like lighting, pointing out the best combinations of markers, and hardware and software to be used depending on the characteristics of the shipyard scenario.

AI snapshot

Written from the paper’s full text.

TL;DR

This paper reviews Industrial Augmented Reality (IAR) for shipbuilding and evaluates commercial IAR hardware/software in a Navantia Industry 4.0 shipyard and inside a ship under construction. It finds that ARToolKit generally achieves longer marker recognition distances than Vuforia, especially with binary markers, while lighting and reading angle strongly affect performance.

Key findings

  • ARToolKit obtained longer maximum recognition/tracking distances than Vuforia, with binary markers reaching more than 25 m in some scenarios; the longest reported distance was 26 m with the Panasonic FZ-A2mk1 tablet and ARToolKit detecting binary marker C at 280 lx.
  • NFT-based recognition did not exceed 2 m, whereas ARToolKit’s binary marker detection worked at more than 20 m under good lighting when markers were fully visible; BCH error correction improved binary marker detection rates.
  • Lighting strongly affected marker-based IAR: most systems became useless under low lighting, Vuforia was less affected by poor lighting than ARToolKit but gave shorter distances, and reflections at higher reading angles reduced recognition distance.
  • Hardware mattered mainly in low light: the UMI Super smartphone performed worst due to its low-range 13 MP camera, while the Panasonic tablet and Epson Moverio glasses had wider dynamic range and performed better; under good lighting, hardware differences disappeared.

Methods

  • The authors reviewed IAR for smart manufacturing and shipbuilding, designed a fog-computing IAR architecture, and selected three devices (UMI Super smartphone, Panasonic FZ-A2mk1 rugged tablet, Epson Moverio BT-2000 smart glasses), two SDKs (ARToolKit and Vuforia), and multiple marker types.
  • Experiments were performed in Navantia’s Ferrol shipyard pre-assembly P1 workshop and inside a modular offshore patrol vessel under construction, specifically in the dining room and bridge, varying marker type, lighting conditions, and reading angle.
  • The main measurements were maximum marker recognition/tracking distances and detection rates; detection-rate tests averaged results over 15 executions per test at a 0° reading angle, with workshop luminosity ranging from under 160 lx early to around 280 lx at noon and dining-room lighting averaging 160 lx.

Limitations

  • The paper states that the results do not evaluate the communications performance of the architecture, only the marker recognition and tracking performance of the IAR devices.
  • The paper states that current marker-based IAR solutions still need to progress and be adapted to low-lighting situations, and that markerless systems such as HoloLens, Meta2, or ARCore require further study for Shipyard 4.0 requirements.
  • Evident from the text: the evaluation is limited to three devices, two SDKs, selected marker types, and specific workshop/ship locations; lighting was variable and not stable, and detection-rate results were averaged over 15 executions at 0° only.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/access.2018.2802699

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 6 cited sources checked · 0 supported · 0 flagged

  • Findingreasoning
    § C. WORKSHOP TESTS · p. 11

    Vuforia obtains its best results with the Rectangular QR marker due to the increase in size and number of characteristic points.

    “Regarding the Rectangular QR, it is not correctly recognized by ARToolkit due to its shape, while Vuforia obtains its best results with it due to the increase in size and, therefore, in the number of characteristic points.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § C. WORKSHOP TESTS · p. 11

    As light conditions improved, the recognition distances for the same binary markers went up to 26 m.

    “As light conditions improved, the recognition distances for the same markers went up to 26 m.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § C. WORKSHOP TESTS · p. 11

    When lighting conditions were around 220 lx, ARToolkit reached recognition distances between 6 and 10 m with the optimized binary markers.

    “The values contained in Table 4 allow for observing that, when lighting conditions were around 220 lx, ARToolkit reached recognition distances between 6 and 10 m with the optimized binary markers.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § C. WORKSHOP TESTS · p. 11

    Both the tablet and the smartphone obtain similar results.

    “With respect to the hardware, both the tablet and the smartphone obtain similar results, while the Epson Moverio smart glasses are not able to reach detection distances as long as the other IAR devices.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § ÓSCAR BLANCO-NOVOA 1 , TIAGO M. FERNÁNDEZ-CARAMÉS 1 , (Senior Member, IEEE), PAULA FRAGA-LAMAS 1 , (Member, IEEE), and MIGUEL VILAR-MONTESINOS 2 · p. 1

    The evaluation showed the impact of factors like lighting on IAR performance.

    “The results obtained show remarkable performance differences among the different IAR tools and the impact of factors like lighting, pointing out the best combinations of markers, hardware and software to be used depending on the characteristics of the shipyard scenario.”
    Quote in the paperSubstantial claim
  • May combine two claims. 24
  • Classified as probably not a substantial claim. 22

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    Early in the morning, natural lighting was scarce, so values under 160 lx were obtained; luminosity values increase gradually until noon, reaching around 280 lx.

    “For instance, early in the morning, natural lighting was scarce, so values under 160 lx were obtained. However, luminosity values increase gradually until noon, reaching around 280 lx.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    Vuforia gets its best results with QR markers, although most distances are lower than 2 m.

    “Vuforia gets its best results with QR markers, although most distances are lower than 2 m.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingnone given
    § C. WORKSHOP TESTS · p. 11

    The differences in recognition distances among the three binary markers are very small.

    “It is also worth mentioning that the differences in recognition distances among the three binary markers are very small.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    Natural lighting projected through the main workshop entrance and skylights increases luminosity, although it varies throughout the day.

    “Nevertheless, the natural lighting projected through the main workshop entrance and the skylights increase the luminosity, although it varies throughout the day.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    The best recognition distances are obtained with the binary markers and ARToolkit, although such distances will decrease remarkably in low light scenarios.

    “After analyzing all the results, it can be concluded that the best recognition distances are obtained with the binary markers and ARToolkit, although it is important to note that such distances will decrease remarkably in low light scenarios.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    Vuforia recognized correctly the custom square marker, but recognition distances were less than 2 m.

    “Vuforia also recognized correctly the custom square marker, but recognition distances were clearly shorter (less than 2 m).”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingreasoning
    § C. WORKSHOP TESTS · p. 11

    In the pre-assembly P1 workshop, luminosity is low due to the height of the ceilings, where the spotlights are installed.

    “It is important to emphasize that in this environment luminosity is low due to the height of the ceilings, where the spotlights are installed.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingnone given
    § D. EVALUATION OF THE IAR SYSTEMS IN A SHIP · p. 12

    In the dining room there is no natural light and all the light comes from fluorescent lamps installed temporarily on the ceilings and walls for the construction works.

    “In the dining room there is no natural light and all the light comes from fluorescent lamps installed temporarily on the ceilings and walls for the construction works.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data
    § C. WORKSHOP TESTS · p. 11

    The markers that make use of error correction codes perform better, although above 15 m, one of the markers showed a remarkable decrease in its detection rate.

    “At the view of the results, it can be observed that the markers that make use of error correction codes perform better, although above 15 m, one of the markers showed a remarkable decrease in its detection rate.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data
    § D. EVALUATION OF THE IAR SYSTEMS IN A SHIP · p. 13

    Vuforia is less affected by the lighting conditions than ARToolkit, being able to recognize patterns with poor lighting.

    “As it can be observed in Table 6, Vuforia is less affected by the lighting conditions than ARToolkit, being able to recognize patterns with poor lighting.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingreasoning
    § E. KEY FINDINGS · p. 16

    The open-source feature of ARToolKit allowed the authors to adapt it to work on the Epson Moverio glasses during the development stage for the experiments, but it was not possible to do so with a proprietary solution like Vuforia.

    “This open-source feature is what allowed us to adapt ARToolkit to work on the Epson Moverio glasses during the development stage for the experiments, but it was not possible to do it with a proprietary solution like Vuforia.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: ARToolKit is open-source.
    • Rests on an assumption: Vuforia is proprietary.

  • May combine two claims.

    Findingown data
    § E. KEY FINDINGS · p. 14

    ARToolKit obtains its best results with binary markers, reaching in some scenarios more than 25 m.

    “Specifically, ARToolKit obtains its best results with binary markers, reaching in some scenarios more than 25 m.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingreasoning
    § E. KEY FINDINGS · p. 16

    The resolution of the camera is not a limiting factor, since the size of the frames should be restricted to a maximum of 1080 pixels in height to obtain acceptable performance.

    “the resolution of the camera is not a limiting factor, since the size of the frames should be restricted to a maximum of 1080 pixels in high to obtain an acceptable performance.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingnone given
    § E. KEY FINDINGS · p. 15

    With regular luminosity, reflections might become an issue and, as the reading angle increases, they reduce the recognition distance.

    “However, with a regular luminosity, reflections might become an issue and, as the reading angle increases, they reduce the recognition distance.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data
    § E. KEY FINDINGS · p. 16

    Tests with laser-printed, ink-printed and laminated markers showed that non-laminated markers produced less reflections, but this effect only slightly decreases the maximum tracking/detection distance.

    “The different tests performed with laser-printed, ink-printed and laminated markers showed that the non-laminated markers produced less reflections, but such effect just decreases slightly the maximum tracking/detection distance.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingreasoning
    § E. KEY FINDINGS · p. 15

    The UMI Super smartphone's performance deteriorates very noticeably when lighting conditions are not good or when there is backlighting.

    “the UMI Super smartphone has a low range 13 MP camera, which causes the performance to deteriorate very noticeably when the lighting conditions are not good or when there is backlighting.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: The UMI Super smartphone has a low range 13 MP camera.

  • Probably not a substantial claim: may not pass S4 (based).

    Premisereasoning
    § A. OBJECTIVE · p. 9

    A dynamic environment like a shipyard workshop or a ship under construction, where the geometrical structure changes through time, can mislead markerless IAR systems that rely on incremental tracking.

    “Nonetheless, a dynamic environment like a shipyard workshop or a ship that is being built, where the geometrical structure of the place changes through time, can mislead the markerless IAR system.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisereasoning
    § A. OBJECTIVE · p. 8

    In an IAR system, the luminosity of the environment, the type of light and the light temperature are essential for implementing reliable and fast IAR applications.

    “First, note that, in an IAR system, the luminosity of the environment, the type of light and the light temperature are essential for implementing reliable and fast IAR applications.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisereasoning
    § A. OBJECTIVE · p. 8

    Most markerless IAR systems are based on detecting physical characteristics of an object or a place; such detection is usually more complex, making algorithms more compute intensive and requiring more powerful hardware.

    “Most markerless IAR systems are based on detecting physical characteristics of an object or a place. Such a detection is usually more complex, what makes algorithms more compute intensive and, therefore, more powerful hardware is required.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given
    § I. INTRODUCTION · p. 2

    No practical evaluation on the application of generic IAR technology in similar use cases and scenarios was found in the literature.

    “In fact, it was not found in the literature any practical evaluation on the application of generic IAR technology in similar use cases and scenarios.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation
    § B. IAR FOR SHIPBUILDING · p. 3

    Several companies offer IAR solutions that have been developed explicitly for shipbuilding.

    “Finally, it is worth mentioning that there are several companies that offer IAR solutions that have been developed explicitly for shipbuilding.”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [50] [50] Newport news shipbuilding. [Online]. Available: http://nns. huntingtoningalls.com/ar. Accessed on: December 1, 2017. -

      Not checked in the free run.

    • cites [51] [51] Index AR Solutions. [Online]. Available: https://www.indexarsolutions. com/about-us. Accessed on: December 1, 2017. -

      Not checked in the free run.

    • cites [52] [52] Virtual Reality Technology Transforms Design of UK Warships. [Online]. Available: http://www.baesystems.com/en/article/ virtualreality-technology-transforms-design-of-uk-warships. Accessed on: December 1, 2017. -

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given
    § B. IAR FOR SHIPBUILDING · p. 3

    Regarding the use of IAR for design tasks, there are not many academic examples of practical applications.

    “Regarding the use of IAR for design tasks, there are not many academic examples of practical applications.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisereasoning
    § A. OBJECTIVE · p. 9

    A problem may occur in a shipyard when a markerless system relies on GPS or WiFi signals to locate a user or a room, since in certain environments such positioning techniques may not work properly.

    “A problem may occur in a shipyard when a markerless system relies on a GPS receiver or in WiFi signals to locate a user or a room, since in certain environments (for instance, indoors or inside a ship under construction) such positioning techniques may not work properly.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given
    § A. OBJECTIVE · p. 8

    Detection of physical patterns is influenced by ambient light, often more sensitive to changes in the environment than marker-based detection techniques.

    “Moreover, the detection of physical patterns is not only more complicated computationally, but it is also influenced by ambient light, being often even more sensitive to changes in the environment than other marker-based detection techniques.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation
    § I. INTRODUCTION · p. 1

    AR has been previously proposed for use in industrial processes related to design, commissioning, manufacturing or quality control.

    “One of such technologies to be further studied is Augmented Reality (AR), which has been previously proposed for being used in industrial processes related to the stages of design, commissioning, manufacturing or quality control [1].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [1] [1] N. Navab, 'Developing Killer Apps for Industrial Augmented Reality,' IEEE Computer Graphics and Applications, vol. 24, no. 3, pp. 16-20, May 2004. -

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning
    § B. EXPERIMENTAL SETUP · p. 10

    For fairness, during the tests two types of binary markers were selected: one without error detection/correction codes and another with a BCH (13,9,3).

    “Thus, for the sake of fairness, during the tests performed two types of binary markers were selected: one without error detection/correction codes and another one with a BCH (13,9,3).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation
    § A. IAR FOR SMART MANUFACTURING · p. 2

    IAR reduces significantly the number of errors and decreases time and mental workload with respect to other approaches in assembly processes.

    “The most popular IAR applications are for the assembly processes, where it has been recently demonstrated that IAR reduces significantly the number of errors and decreases time and mental workload respect to other approaches [26].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [26] [26] F. Loch, F. Quint, and I. Brishtel, 'Comparing Video and Augmented Reality Assistance in Manual Assembly,' in 2016 12th International Conference on Intelligent Environments (IE), Sept 2016, pp. 147-150. -

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given
    § A. OBJECTIVE · p. 8

    Markerless IAR systems currently have limitations that reduce their applicability in a shipyard.

    “Such markerless systems are still a minority in the world of IAR and, although they work fine in certain environments, they currently have some limitations that reduce their applicability in a shipyard:”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning
    § C. WORKSHOP TESTS · p. 11

    Exhaustive measurements of the lighting level were carried out.

    “Due to such a variability in the lighting conditions, exhaustive measurements of the lighting level were carried out.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation
    § B. COMMUNICATIONS ARCHITECTURE · p. 6

    Fog computing extends cloud computing by moving part of the computational and communication capabilities of the cloud close to the sensor nodes.

    “Fog computing extends cloud computing by moving part of the computational and communication capabilities of the cloud close to the sensor nodes [4].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [4] [4] F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, 'Fog Computing and its Role in the Internet of Things,' in Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing, Helsinki, Finland, 17 August 2012, pp. 13-16. -

      Not checked in the free run.

  • Classified as probably not a substantial claim. May combine two claims.

    Premisereasoning
    § A. OBJECTIVE · p. 8

    AR algorithms make use of computer vision techniques based in thresholding and color measurement metrics, so lighting characteristics can impact system performance significantly.

    “Since AR algorithms make use of computer vision techniques based in thresholding and color measurement metrics, the lighting characteristics can impact the system performance significantly.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Premisereasoning
    § A. OBJECTIVE · p. 8

    Due to limited memory of current markerless IAR hardware, its use tends to be limited to rooms or reduced areas, which have to be mapped by using different sensors.

    “Due to the limited memory of current markerless IAR hardware, its use tends to be limited to rooms or reduced areas, which have to be mapped (usually on-the-fly) by using different sensors.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning
    § B. COMMUNICATIONS ARCHITECTURE · p. 6

    Fog computing is ideal for providing IAR services thanks to its ability to support physically distributed, low-latency and QoS-aware applications that decrease network traffic and computational load of traditional cloud computing systems.

    “Therefore, fog computing is ideal for providing IAR services thanks to its ability to support physically distributed, low-latency and QoS-aware applications that decrease the network traffic and the computational load of traditional cloud computing systems.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning
    § D. EVALUATION OF THE IAR SYSTEMS IN A SHIP · p. 12

    In the dining room, the non-homogeneous lighting and warm color temperature reduce the pure white levels of the markers and greatly affect the thresholding calculations.

    “In addition to the non-homogeneous lighting, the color temperature is quite warm, what reduces the pure white levels of the markers and also greatly affects the thresholding calculations.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductown data
    § C. WORKSHOP TESTS · p. 11

    The three different IAR devices were evaluated under the same lighting conditions, averaging the results for 15 executions of every test and when reading the markers at a 0° angle.

    “The three different IAR devices of the previous tests were evaluated under the same lighting conditions, averaging the results for 15 executions of every test and when reading the markers at a 0°angle (i.e., in parallel to them).”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning
    § C. WORKSHOP TESTS · p. 12

    The two markers at the top obtain better results due to the fact that they are less complex than the others, so they can be detected easier, even when they are partially hidden.

    “Finally, it should be mentioned that the two markers at the top obtain better results due to the fact that they are less complex than the others, so they can be detected easier, even when they are partially hidden.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationnone given
    § VI. CONCLUSIONS · p. 16

    IAR can bring multiple benefits to an Industry 4.0 shipyard, but current marker-based IAR solutions, although they work fine in many scenarios, still have to progress and be adapted to low lighting situations.

    “IAR can bring multiple benefits to an Industry 4.0 shipyard, but current marker-based IAR solutions, although they work fine in many scenarios, still have to progress and be adapted to low lighting situations.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationreasoning
    § E. KEY FINDINGS · p. 16

    An open-source framework makes it possible to develop adaptations to work with different platforms and opens the door to future optimizations of the final system, something unfeasible in the case of proprietary software.

    “An open-source framework makes it possible to develop adaptations to work with different platforms and opens the door to future optimizations of the final system, something unfeasible in the case of proprietary software.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationreasoning
    § E. KEY FINDINGS · p. 16

    When lighting is good, the differences among hardware devices disappear and the software algorithms are more important.

    “On the contrary, when lighting is good, the differences among the hardware devices disappear and the software algorithms are more important.”
    • Also stated in: § D. EVALUATION OF THE IAR SYSTEMS IN A SHIP · p. 14 · plain
      “On the contrary, when lighting is good, the differences between different hardware devices disappear.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning
    § VI. CONCLUSIONS · p. 16

    ARToolKit, since it is open-source, is a better long-term choice than other proprietary solutions when developing applications for IAR devices because of the possibility of extending the software.

    “ARToolKit, since it is opensource, is a better long-term choice than other proprietary solutions when developing applications for IAR devices because of the possibility of extending the software.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: ARToolKit is open-source.
    • Rests on an assumption: Vuforia is proprietary.

  • May combine two claims.

    Interpretationnone given
    § E. KEY FINDINGS · p. 16

    The vast majority of current IAR hardware devices can still be considered experimental developments, which makes their integration with existing IAR frameworks and the implementation of new features difficult.

    “the vast majority of current IAR hardware devices can be still considered experimental developments, what makes it difficult their integration with existing IAR frameworks and the implementation of new features.”
    Quote in the paperSubstantial claim
41 of 41

  • The paper relies on this without support.

    Communications inside a ship pose a challenge for electro-magnetic propagation due to the presence of numerous large metal elements.

    “However, note that communications inside a ship suppose a challenge for electro-magnetic propagation due to the presence of numerous large metal elements.”

  • The paper relies on this without support.

    Vuforia cannot be used with certain smart AR glasses, like the Epson Moverio BT-2000.

    “It enables to create IAR systems on the most common development platforms, but it is not possible to use it with certain smart AR glasses, like the Epson Moverio BT-2000.”

  • The paper relies on this without support.

    ARToolkit includes algorithms optimized for long-distance pattern recognition.

    “Moreover, ARToolkit includes algorithms optimized for long-distance pattern recognition, which is a desirable feature in multiple shipbuilding scenarios.”

  • The paper relies on this without support.

    Most of the IAR smart manufacturing systems previously mentioned can be used directly, or with a light adaptation, for the shipbuilding industry.

    “Most of the IAR smart manufacturing systems previously mentioned can be used directly, or with a light adaptation, for the shipbuilding industry.”

  • The paper relies on this without support.

    Shipyard operators usually rely on paper to identify assets and determine which action should be performed according to the work orders.

    “shipyard operators usually rely on paper to identify assets (e.g, pipes, machines, pallets) and determine which action should be performed according to the work orders.”

  • The paper relies on this without support.

    In real-world scenarios, shadows and reflections can appear on the marker, impacting the recognition distance and the marker detection success rate.

    “Note that, in real-world scenarios, shadows and reflections can appear on the marker, what impacts the recognition distance and the marker detection success rate.”

  • The paper relies on this without support.

    Sunlight causes back-light and reflections that may impact the recognition performance of IAR systems.

    “Nonetheless, sunlight causes back-light and reflections that may impact the recognition performance of the IAR systems.”

  • The paper relies on this without support.

    Light reflections occur because of the position of the windows.

    “since light reflections occur because of the position of the windows”

  • The paper relies on this without support.

    The UMI Super smartphone has a low range 13 MP camera.

    “the UMI Super smartphone has a low range 13 MP camera”

  • The paper relies on this without support.

    ARToolKit is open-source.

    “ARToolKit, since it is opensource”

  • The paper relies on this without support.

    Vuforia is proprietary.

    “a proprietary solution like Vuforia”
11 of 11

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Cites

Flagged first, then by citations

Research works printed but not linked: 41

  1. 2017, Aurasma
  2. 2017, Aruco
  3. 2017, ARToolKit
  4. 2017, ARMed
  5. 2017, Beyond Reality Face
  6. 2017, Catchoom
  7. 2017, Bazar
  8. 2017, BeyondAR
  9. 2017, IN2AR
  10. 2017, Instant Reality
  11. 2017, Daqri Smarthelmet Glasses
  12. 2017, FUJITSU Ubiquitousware HMD
  13. 2017, Microsoft HoloLens
  14. 2017, Laster WAV? Glasses
  15. 2017, Optinvent ORA-2 Glasses
  16. 2017, Penny C Wear Glasses
  17. 2017, Augmenta Studio
  18. 2017, AugmentedPro
  19. 2017, Alvar
  20. 2017, ARLab
  21. 2017, (Joint Research Unit Navantia-UDC)
  22. 2017, Newport News Shipbuilding
  23. 2017, Index AR Solutions
  24. 2017, Unity 3d
  25. 2017, Vuzix Glasses
  26. 2017, Sony Smarteye Glasses
  27. 2017, Recon Jet Glasses
  28. 2017, ODG R-7 Glasses
  29. 2017, Epson Moverio Glasses
  30. 2017, CHIPSIP Sime Glasses
  31. 2017, Atheer Air
  32. 2017, Virtual Reality Technology Transforms Design of UK Warships
  33. 2017, Open Space 3D
  34. 2017, mixare
  35. 2017, UART
  36. 2017, SSTT
  37. 2017, Layar AR SDK
  38. 2017, Navantia S A S M E
  39. 2017, Vuforia
  40. 2017, Wikitude
  41. 2017, ZappWorks

Cited by

Sorted by citations

Related

Authors
Blanco-Novoa, O., Fernandez-Carames, T. M., Fraga-Lamas, P., & Vilar-Montesinos, M. A.
ORCID
Fraga-Lamas, Paula
Venue
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2018
Volume
6
Pages
8201-8218
ISSN
2169-3536 (ISSN-L)
DOI
10.1109/access.2018.2802699
OpenAlex
W2790452817
Semantic Scholar
aebe9430c25c452427ecf7c8dfad1dcade538961
Cited by
183
References
50
Citations by year
2026: 7 · 2025: 12 · 2024: 22 · 2023: 15 · 2022: 20 · 2021: 26 · 2020: 42 · 2019: 21 · 2018: 18
FWCI
13.39
Type
journal article
Language
en
Open access
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html (vor)
Locations
  • IEEE Access (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • RUC (Universidade Da Coruña) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
Plant Information and Augmented Reality research line of the Navantia-UDC Joint Research Unit
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Augmented Reality Applications
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Digital Transformation in Industry
  • Physical Sciences › Computer Science › Human-Computer Interaction › Interactive and Immersive Displays
Keywords
industrial augmented reality, shipbuilding, Industry 4.0, smart manufacturing, fog computing, AR markers, ARToolKit, Vuforia, smart glasses, shipyard automation, Navantia

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review