| Surveying | |
Emerging Technologies and their integration in Surveying Profession
The integration of IPS, VPS, SLAM, AI, and Machine Learning into the surveying profession signifies a major advancement from conventional practices. |
 |
|
 |
|
Abstract
The Surveying profession is experiencing a paradigm shift due to the emergence of advanced technologies such as Indoor Positioning Systems (IPS), Visual Positioning Systems (VPS), Simultaneous Localization and Mapping (SLAM), Artificial Intelligence (AI), and Machine Learning (ML). These technologies address the limitations of traditional tools like GPS and total stations, especially in environments where visibility, accessibility, or real-time data processing pose challenges. IPS facilitates precise indoor positioning where GPS fails, VPS leverages visual data for accurate localization in urban or structured environments, while SLAM enables real time mapping in unknown or dynamic terrains. AI and ML further enhance surveying by automating data analysis, feature recognition, and predictive modeling. This paper discusses how these technologies reshape surveying practices and argues for their integration into higher education curricula. Emphasis is placed on equipping students with hands-on experience and theoretical understanding, ensuring they are prepared for the demands of a rapidly evolving geo-spatial industry.
Keywords: Artificial, Education, Machine, Positioning and Surveying.
Introduction
A lot of us here today can attest that we are used to the normal or the generic Surveying which if asked, we would mention cadastral, engineering, hydrography, geodesy, seismics or special surveys but most practiced is cadastral. Most Surveyors registered by Surveyors Council of Nigeria (SURCON) mostly want to delve into private cadastral practice and I permit me to say that the word cadastral surveying is synonymous to private practice as acclaimed by many private practitioners. So, I think we are still orbit around the cadastral axis just like the Israelites in the wilderness for 40 years. However, we will not fail to commend the massive growth in the evolution of surveying equipment, data acquisition methods, data processing and visualization as the practice progressed from the ancient to the modern data acquisition method. The thought of the theme of the 2015 FIG working week: From the wisdom of the ages to the challenges of the modern world. Where measurements were obtained using Human Legs by pacing, Gunter’s chain with arrows, Tapes, Compass, Sextant etc. Evolved to Theodolite, Electronic Distance Measurement (EDM), Total Station and the multiple frequency Differential Global Positioning System (DGPS), Light Detection and Ranging (LiDAR), Light Amplification Stimulated Emission Radiation (LASER), Multi-spectral imaging systems etc.
Brown and Smith (2020) in their article Advancements in Surveying: The Role of Emerging Technologies in Data Acquisition, ‘The technological growth in surveying data acquisition has transformed traditional methods, with innovations like LiDAR, drones, and satellite imagery enabling surveyors to capture precise spatial data faster and more efficiently than ever before’. He emphasized that these advancements not only increase data accuracy but also expand the capabilities of surveyors to access previously unreachable areas and perform real-time analyses. These methods of data acquisition have increased the surveying horizon, but with limits and you know the end of one thing is the beginning of a new one. Also, we record an increasing number of young surveyors eager to take this technology to the next future. Now it is pertinent for us to ask ourselves, what next?
The field of surveying is rapidly advancing due to the integration of innovative technologies that provide improved accuracy, efficiency, and automation. These technologies are;
a. Indoor Positioning Systems (IPS).
b. Visual Positioning Systems (VPS).
c. Simultaneous Localization and Mapping (SLAM). d. Artificial Intelligence (AI) and Machine Learning (ML).
These are emerging as transformative tools in surveying as these technologies allow surveyors to capture, process, and analyze spatial data in new ways, enabling detailed indoor mapping, urban navigation, 3D mapping of complex environments, and predictive analytics and it is of importance that higher education inculcates in into her curricula. Let’s buttress on each technology and how they are reshaping surveying practices and academic programs.
2.1 Indoor Positioning System
As stated earlier, these equipment types have limits, so we are looking out for technologies that overcame the limitations of traditional tools. As we know, GPS signals are ineffective in confined or enclosed spaces, where underground structures, walls and ceilings obstruct satellite signals. How then do we map indoor positions? Well, that is what the Indoor Positioning System (IPS) addresses.
2.1.1 What is IPS?
The Indoor Positioning System (IPS) is a technology designed to provide accurate, real-time location information within indoor spaces, where GPS signals are unreliable or unavailable. IPS uses a combination of technologies like Wi-Fi, Bluetooth, magnetic field mapping, and even infrared signals to pinpoint a device or user’s location with high accuracy, down to a few meters or even centimeters, depending on the setup (Luo et al., 2020).
2.1.2 How IPS Works
IPS operates through a network of sensors and transmitters installed in an indoor environment. Unlike GPS, which relies on satellites that lose signal strength indoors, IPS uses nearby signals such as Wi-Fi, Bluetooth, magnetic f ields, and radio waves to determine a device’s position? This system uses two main methods: triangulation and f ingerprinting. In triangulation, IPS calculates distances between the device and multiple transmitters to pinpoint the location, similar to how GPS calculates outdoor locations. In fingerprinting, IPS identifies unique signal patterns that are matched to specific points within a building, enabling precise indoor mapping. Advanced IPS setups also incorporate sensor fusion, combining data from gyroscopes, accelerometers, and compasses in mobile devices to achieve even greater accuracy and real time tracking of movement indoors.
2.1.3 Relevance of IPS in Shaping the Surveying Profession
IPS plays an essential role in transforming the surveying profession by enabling accurate indoor mapping and positioning, especially in areas where traditional methods are challenging. For example, it allows surveyors to create precise indoor maps of complex structures like airports, hospitals, shopping malls, and large industrial sites. These maps are crucial for applications such as facilities management, emergency planning, and indoor navigation. IPS also enhances surveying efficiency by automating location tracking and reducing the need for manual measurements. With IPS, surveyors can manage and monitor assets in real time, streamline workflows, and increase the accuracy of spatial data. This technology opens up new possibilities in surveying and is becoming increasingly important as demand grows for detailed indoor data in urban planning, construction, and logistics (Torres-Sospedra & Montoliu, 2021).
2.2 Visual Positioning Systems Visual Positioning Systems
(VPS) address critical limitations in both GPS and IPS by providing precise positioning in environments where traditional systems struggle, especially when neither satellite signals nor Wi-Fi triangulation is adequate for accuracy. VPS uses a device’s camera and computer vision to analyze visual features in the environment, creating a more reliable positioning system for complex outdoor and indoor settings, particularly urban environments with high-rise buildings or indoor areas lacking structured signal coverage (Fischler & Bolles, 1981; Ishikawa et al., 2022).
2.2.1 How VPS Works
The VPS operates by capturing images through a device’s camera, comparing them to a reference database of images and spatial data to determine the exact location. This reference database might be composed of previously captured photos or 3D models of the area, allowing VPS to see and identify specific landmarks and features that GPS or IPS would miss. The system uses machine learning and computer vision algorithms to match what the camera sees with pre-mapped images or models, accurately identifying position and orientation. Unlike GPS or IPS, which rely solely on signals, VPS takes advantage of the visual information in the environment to provide location data, even in areas with low connectivity or dense urban structures.
2.2.2 Relevance of VPS in Shaping the Surveying Profession
The VPS has transformative potential in surveying by enabling highly accurate, feature-rich mapping and positioning in areas with complex structures. Surveyors can use VPS for precise navigation and mapping in urban centers, construction sites, or any setting where environmental details are necessary for accurate spatial analysis. For example, VPS enhances the ability to navigate densely built urban areas where GPS accuracy is reduced, as it uses visual cues that can be more reliable than satellite signals. This technology also supports augmented reality (AR) applications, allowing surveyors to visualize spatial data in real-time while in the field, enhancing their ability to make immediate assessments and decisions.
2.3 Simultaneous Localization and Mapping
Simultaneous Localization and Mapping (SLAM) addresses the challenge of creating real-time precise maps of unknown environments while simultaneously determining the user or device’s location within that map. SLAM f ills a vital gap by allowing for accurate positioning and mapping in settings where pre-existing maps or positioning data are unavailable, making it highly valuable for dynamic and unstructured environments like construction sites, mines, forests, or any area undergoing rapid change.
2.3.1 How SLAM Works
SLAM combines sensor data from sources like cameras, LiDAR, radar, and inertial measurement units (IMUs) to build a map and track movement in real time. As the device (such as a robot, drone, or handheld unit) moves through an environment, it detects landmarks or features around it. The SLAM algorithms then use these landmarks to build a continuously updated map, all while tracking the device’s changing position within that environment. By processing this data rapidly, SLAM can estimate both the layout of the area and the device’s exact location with minimal delay (Thrun et al., 2005; Cadena et al., 2016). This process involves complex mathematical models and probabilistic algorithms that predict and correct any position discrepancies, making SLAM an ideal tool for dynamic or unknown environments.
2.3.2 Relevance of SLAM in Shaping the Surveying Profession
SLAM technology is revolutionizing surveying by enabling accurate mapping in areas where conventional methods may be too slow or impossible to implement. Surveyors can utilize SLAM-based devices to quickly map complex indoor spaces, densely vegetated outdoor areas, or construction sites, often in less time than traditional surveying techniques require. SLAM also enables the use of autonomous or remotely operated robots and drones to map hazardous or inaccessible locations, reducing safety risks for surveyors. Furthermore, SLAM’s real-time mapping capabilities mean surveyors can instantly assess and adapt to the environment, enabling immediate decisions and reducing the need for repeat visits to the field. By incorporating SLAM into surveying workflows, professionals gain a powerful tool for high-precision mapping in dynamic environments, vastly improving data quality and efficiency.
2.4 Artificial Intelligence and Machine Learning
Artificial Intelligence (AI) and Machine Learning (ML) fill a significant gap in traditional surveying by automating data analysis, pattern recognition and decision-making processes, which are often time-consuming and complex. AI and ML enable surveyors to handle vast datasets more effectively, extract meaningful insights from them, and make predictive analyses, transforming how surveying projects are planned, managed, and executed.
2.4.1 How AI and ML Work in Surveying
AI refers to the simulation of human intelligence by computers, which can be applied to automate tasks, recognize patterns, and make decisions based on data. ML, a subset of AI, involves training algorithms to learn from data and improve over time. In surveying, AI and ML systems are trained on large datasets that may include remotely sensed datasets, LiDAR scans, GPS data, or even historical surveying records. These algorithms can then recognize patterns in the data, such as identifying terrain features, categorizing land use, or predicting structural changes over time (Goodfellow et al., 2016). For example, AI-driven image recognition algorithms can analyze aerial or satellite images and automatically identify features like roads, buildings, vegetation, and water bodies, vastly reducing the time surveyors would need for manual digitization. Additionally, ML models can make predictions, such as forecasting flood risks in specific areas based on previous data, which enhances planning for environmental or infrastructure projects.
2.4.2 Relevance of AI and ML in Shaping the Surveying Profession
AI and ML are reshaping surveying by enabling rapid data processing and automation of repetitive tasks, leading to increased efficiency and precision. Surveyors can use AI to streamline data collection and processing, allowing them to focus on higher-level analysis and decision-making. In environmental surveying, for instance, AI can be used to analyze land use changes over time, helping surveyors make data-backed recommendations for land management. For GIS and remote sensing, AI tools are becoming essential for automated image classification, feature extraction, and anomaly detection, all of which can dramatically enhance the accuracy of spatial data. These advancements not only increase productivity but also enhance data accuracy, reducing the potential for human error in complex surveying tasks (Bengio, 2012). Incorporating AI and ML into higher education allows surveying students to gain skills in data science, image processing, and predictive analysis, preparing them for a technologically advanced industry. As AI and ML continue to evolve, they will remain at the forefront of innovations in surveying, ensuring that professionals can tackle increasingly complex projects with efficiency and foresight.
3.1 Relevance of integrating these new technologies in the Surveying and Mapping
The integration of IPS, VPS, SLAM, AI and ML represents a transformative leap forward in the surveying profession, addressing previous technological limitations and setting new standards for accuracy, efficiency, and safety. These technologies enable surveyors to conduct highly precise measurements in environments where traditional methods may fall short, such as indoors, in dense urban areas, and in dynamic or unstructured environments. IPS and VPS make it possible to map indoor and complex spaces where GPS is ineffective, while SLAM offers real-time mapping capabilities in unknown or changing environments, making it invaluable for construction and environmental surveying. AI and ML automate data processing, pattern recognition, and predictive analytics, allowing surveyors to manage and interpret vast datasets more effectively, which enhances data quality and speeds up decision-making processes. The collective impact of these technologies goes beyond technical efficiency; they empower surveyors to tackle projects with a level of precision and insight previously unattainable. Automated feature recognition, predictive modeling, and real time spatial analysis mean that surveyors can focus more on strategic planning and less on time-consuming manual tasks. This not only reduces errors and improves accuracy but also opens new applications for surveyors, such as urban planning, disaster response, and environmental management (Campbell, 2011).
4.1 Integrating these Technologies into the Higher Education Curricula
From everything we have heard, how many of us have this knowledge? It would have sounded more familiar if we had been taught or grounded in these areas during our higher education. Doesn’t this indicate the importance of incorporating these technologies into the curriculum of our higher institutions? As surveying evolves into a data-driven field, it’s essential for educational institutions to prepare students for a landscape that demands proficiency in these emerging technologies. To incorporate these technologies into the curriculum, institutions should consider adding specialized courses in topics like indoor mapping (IPS and VPS), robotics and automation (for SLAM), and data science (AI and ML). Practical training sessions, using advanced equipment like drones, LiDAR scanners, and mobile mapping systems, will ensure students gain hands-on experience with these tools (Chen et al., 2020). Additionally, institutions should establish partnerships with tech firms and industry experts to create internship programs and guest lectures, providing students with real world applications and industry insights. Furthermore, integrating interdisciplinary projects where students from surveying, computer science, and engineering work together can foster a broader understanding of how these technologies interconnect in practice. By embracing this integrated, tech-forward curriculum, higher education can ensure that the next generation of surveyors is well-prepared to lead in a rapidly advancing profession.
Conclusion
The integration of IPS, VPS, SLAM, AI, and Machine Learning into the surveying profession signifies a major advancement from conventional practices. These technologies collectively overcome key limitations of traditional equipment, offering improved accuracy, speed, and adaptability across diverse environments. As the demand for smart cities, indoor mapping, automation, and real-time data increases, the role of these innovations becomes indispensable. However, a significant gap remains in higher education, where many surveying students graduate without exposure to these emerging tools. This highlights the urgent need to embed these technologies into the curriculum through practical training, interdisciplinary projects, and partnerships with industry. By doing so, institutions will produce surveyors who are not only competent in classical techniques but also fluent in modern geospatial technologies, positioning them to lead in an increasingly digital and data-driven world.
References
Bengio, Y. (2012). Deep learning of representations: Looking forward. In Statistical language and speech processing pp. 1 – 37. Springer.
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., … & Leonard, J. J. (2016). Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on Robotics, 32(6), pp. 1309 – 1332.
Campbell, J. B. (2011). Introduction to remote sensing, Guilford Press.
Chen, W., Wang, L., Li, W., Yu, Z., & Li, J. (2020). Real-time indoor positioning technique and its applications in the survey industry. International Journal of Geo-Information, 9(1), p. 56.
Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6), pp. 381 – 395.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning, MIT press.
Ishikawa, T., Wada, T., & Kameda, Y. (2022). Visual positioning in urban environments with complex structural elements. Urban Informatics, 8(4), pp. 1 – 15.
Luo, H., Yu, W., Chen, Z., & Tian, Y. (2020). Indoor positioning systems based on Wi-Fi: Principles, applications, and performance improvements. Sensors, 20(12), p. 3772.
Pepple, G. T. (2024). Emerging Technologies: IPS, VPS, SLAM, AI & Machine Learning integration in Surveying Practice and Higher Institution Curriculum, Paper presented at the Harvest of Ideas VIII Delegate Conference of the Young Surveyors Network, Asaba, Delta State.
Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics (Intelligent robotics and autonomous agents). MIT Press.
Torres-Sospedra, J., & Montoliu, R. (2021). Indoor positioning for the Internet of Things, In Handbook of Smart Cities, pp. 643 – 673.
(No Ratings Yet)
Loading...
Leave your response!