In order to transcend the challenge of accelerating the establishment of cadastres and to efficiently maintain them once established, innovative, and automated cadastral mapping techniques are needed. The focus of the research is on the use of high-resolution optical sensors on unmanned aerial vehicle (UAV) platforms. More specifically, this study investigates the potential of UAV-based cadastral mapping, where the ENVI feature extraction (FX) module has been used for data processing. The paper describes the workflow, which encompasses image pre-processing, automatic extraction of visible boundaries on the UAV imagery, and data post-processing. It shows that this approach should be applied when the UAV orthoimage is resampled to a larger ground sample distance (GSD). In addition, the findings show that it is important to filter the extracted boundary maps to improve the results. The results of the accuracy assessment showed that almost 80% of the extracted visible boundaries were correct. Based on the automatic extraction method, the proposed workflow has the potential to accelerate and facilitate the creation of cadastral maps, especially for developing countries. In developed countries, the extracted visible boundaries might be used for the revision of existing cadastral maps. However, in both cases, the extracted visible boundaries must be validated by landowners and other beneficiaries.

Current efforts aim to accelerate cadastral mapping through innovative and automated approaches and can be used to both create and update cadastral maps. This research aims to automate the detection of visible land boundaries from unmanned aerial vehicle (UAV) imagery using deep learning. In addition, we wanted to evaluate the advantages and disadvantages of programming-based deep learning compared to commercial software-based deep learning. For the first case, we used the convolutional neural network U-Net, implemented in Keras, written in Python using the TensorFlow library. For commercial software-based deep learning, we used ENVINet5. UAV imageries from different areas were used to train the U-Net model, which was performed in Google Collaboratory and tested in the study area in Odranci, Slovenia. The results were compared with the results of ENVINet5 using the same datasets. The results showed that both models achieved an overall accuracy of over 95%. The high accuracy is due to the problem of unbalanced classes, which is usually present in boundary detection tasks. U-Net provided a recall of 0.35 and a precision of 0.68 when the threshold was set to 0.5. A threshold can be viewed as a tool for filtering predicted boundary maps and balancing recall and precision. For equitable comparison with ENVINet5, the threshold was increased. U-Net provided more balanced results, a recall of 0.65 and a precision of 0.41, compared to ENVINet5 recall of 0.84 and a precision of 0.35. Programming-based deep learning provides a more flexible yet complex approach to boundary mapping than software-based, which is rigid and does not require programming. The predicted visible land boundaries can be used both to speed up the creation of cadastral maps and to automate the revision of existing cadastral maps and define areas where updates are needed. The predicted boundaries cannot be considered final at this stage but can be used as preliminary cadastral boundaries.

One of the main concerns of land administration in developed countries is to keep the cadastral system up to date. The goal of this research was to develop an approach to detect visible land boundaries and revise existing cadastral data using deep learning. The convolutional neural network (CNN), based on a modified architecture, was trained using the Berkeley segmentation data set 500 (BSDS500) available online. This dataset is known for edge and boundary detection. The model was tested in two rural areas in Slovenia. The results were evaluated using recall, precision, and the F1 score—as a more appropriate method for unbalanced classes. In terms of detection quality, balanced recall and precision resulted in F1 scores of 0.60 and 0.54 for Ponova vas and Odranci, respectively. With lower recall (completeness), the model was able to predict the boundaries with a precision (correctness) of 0.71 and 0.61. When the cadastral data were revised, the low values were interpreted to mean that the lower the recall, the greater the need to update the existing cadastral data. In the case of Ponova vas, the recall value was less than 0.1, which means that the boundaries did not overlap. In Odranci, 21% of the predicted and cadastral boundaries overlapped. Since the direction of the lines was not a problem, the low recall value (0.21) was mainly due to overly fragmented plots. Overall, the automatic methods are faster (once the model is trained) but less accurate than the manual methods. For a rapid revision of existing cadastral boundaries, an automatic approach is certainly desirable for many national mapping and cadastral agencies, especially in developed countries.

Most cadastral systems today are coordinate-based and contain only a weak or no reference to measurements or the origin of the information. In some contexts, this is largely due to the transition of land data management and maintenance from an analogue to a digital environment. This study focuses on analysing the importance of the measurement-based cadastre and the digitisation process in North Macedonia and Slovenia. The survey-based boundary data and their integration into the digital environment were not considered in either case study. The positional differences between the survey-based boundary coordinates and the graphical coordinates of the boundaries are significant. The RMSE(2D) for Trebosh was 48 cm, and the RMSE(2D) for Ivanjševci was 56 cm. Consequently, the differences in location affected the areas of the cadastral parcels, resulting in an RMSE of 26 m² and 23 m² for Trebosh and Ivanjševci, respectively. These differences can be considered as differences within the cadastral boundary data. Therefore, before harmonising the data between the cadastre and the land register, the inconsistencies within the cadastral data should be eliminated first. The differences in the location of cadastral boundaries and parcel area create new challenges in cadastral procedures (formatting of parcels), conflicts in the relocation of boundaries, and impacts on the land market. The solution lies in the way data is maintained, avoiding duplication of attributes or eliminating inconsistencies (after duplication). Both solutions require further modifications of the legal framework for cadastral procedures related to boundary adjustments and data compliance. This study provides a basis for evaluating inconsistencies in cadastral data and highlights the importance of proper source data selection in the digitization process.

Land administration databases are central to property taxation, urban planning and development finance, yet the reliability of their records is rarely examined closely. This study analyses valuation inversion, a mismatch in which the land readiness categories recorded in the national transaction register contradict the expected price hierarchy, in the Ljubljana Urban Region, Slovenia. The analysis draws on 735 valid land transactions across four Market Analytical Areas of the Slovenian mass appraisal system. Under the recorded categories, parcels with a building permit, the highest readiness category, carried no significant price premium over partly equipped or non-equipped parcels and sold on average 12–17% below parcels recorded as equipped, even within the same municipality, while the recorded equipped category implied a premium of only 18–24%. A spatial proximity scoring model was developed to reclassify cadastral parcels based on measured distances to water supply, sewerage, electricity and road infrastructure. After reclassification, land within connectable distance of all four networks achieved on average 46.1% higher prices than partly or non-equipped land (unweighted mean of the four areas). In hedonic models controlling for location, plot size, slope and transaction year, the premium was 48–76%, and it remained significant under alternative scoring thresholds and distance bands and for the most recent sales. Once infrastructure is accounted for, the price gap between permit-labelled and equipped parcels is roughly halved and no longer significant. These findings indicate that valuation models relying solely on recorded readiness classifications may introduce systematic bias into mass appraisal systems. Spatial proximity scoring offers a scalable approach to screening the infrastructure component of land readiness records, with implications for automated valuation models, property tax equity and infrastructure investment planning.