Reliable Ground Truth Research Articles

Assessing fidelity in XAI post-hoc techniques: A comparative study with ground truth explanations datasets

The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing three novel image datasets with reliable ground truth for explanations. The primary objective of this comparison is to identify methods with low fidelity and eliminate them from further research, thereby promoting the development of more trustworthy and effective XAI techniques. Our results demonstrate that XAI methods based on the direct gradient calculation and the backpropagation of output information to input yield higher accuracy and reliability compared to methods relying on perturbation based or Class Activation Maps (CAM). However, these methods tend to generate more noisy saliency maps. These findings have significant implications for the advancement of XAI methods, enabling the elimination of erroneous explanations and fostering the development of more robust and reliable XAI.

Deep multiple instance learning versus conventional deep single instance learning for interpretable oral cancer detection.

The current medical standard for setting an oral cancer (OC) diagnosis is histological examination of a tissue sample taken from the oral cavity. This process is time-consuming and more invasive than an alternative approach of acquiring a brush sample followed by cytological analysis. Using a microscope, skilled cytotechnologists are able to detect changes due to malignancy; however, introducing this approach into clinical routine is associated with challenges such as a lack of resources and experts. To design a trustworthy OC detection system that can assist cytotechnologists, we are interested in deep learning based methods that can reliably detect cancer, given only per-patient labels (thereby minimizing annotation bias), and also provide information regarding which cells are most relevant for the diagnosis (thereby enabling supervision and understanding). In this study, we perform a comparison of two approaches suitable for OC detection and interpretation: (i) conventional single instance learning (SIL) approach and (ii) a modern multiple instance learning (MIL) method. To facilitate systematic evaluation of the considered approaches, we, in addition to a real OC dataset with patient-level ground truth annotations, also introduce a synthetic dataset-PAP-QMNIST. This dataset shares several properties of OC data, such as image size and large and varied number of instances per bag, and may therefore act as a proxy model of a real OC dataset, while, in contrast to OC data, it offers reliable per-instance ground truth, as defined by design. PAP-QMNIST has the additional advantage of being visually interpretable for non-experts, which simplifies analysis of the behavior of methods. For both OC and PAP-QMNIST data, we evaluate performance of the methods utilizing three different neural network architectures. Our study indicates, somewhat surprisingly, that on both synthetic and real data, the performance of the SIL approach is better or equal to the performance of the MIL approach. Visual examination by cytotechnologist indicates that the methods manage to identify cells which deviate from normality, including malignant cells as well as those suspicious for dysplasia. We share the code as open source.

Domain Adaptation Curriculum Learning for Scene Text Detection in Inclement Weather Conditions

AbstractScene text detection has been widely studied on haze‐free images with reliable ground truth annotation. However, detecting scene text in inclement weather conditions remains a major challenge due to the severe domain distribution mismatch problem. This paper introduces a domain adaptation curriculum learning method to address this problem. The scene text detector is self‐trained in an easy‐to‐hard manner using the pseudo‐labels predicted from foggy images. Thus, our method reduces the pseudo‐labeling noise level. Then, a feature alignment module is introduced to help the network learn domain‐invariant features by training a domain classifier. Experimental results show that our method improved significantly on both synthetic foggy data sets and natural foggy data sets, outperforming many state‐of‐the‐art scene text detectors. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Fast and accurate 3-D spine MRI segmentation using FastCleverSeg

Accurate and efficient segmenting of vertebral bodies, muscles, and discs is crucial for analyzing various spinal diseases. However, traditional methods are either laborious and time-consuming (manual segmentation) or require extensive training data (fully automatic segmentation). FastCleverSeg, our proposed semi-automatic segmentation approach, addresses those limitations by significantly reducing user interaction while maintaining high accuracy. First, we reduce user interaction by requiring the manual annotation of only two or three slices. Next, we automatically Estimate the Annotation on Intermediary Slices (EANIS) using traditional computer vision/graphics concepts. Finally, our proposed method leverages improved voxel weight balancing to achieve fast and precise volumetric segmentation in the segmentation process. Experimental evaluations on our assembled diverse MRI databases comprising 179 patients (60 male, 119 female), demonstrate a remarkable 25 ms (30 ms standard deviation) processing time and a significant reduction in user interaction compared to existing approaches. Importantly, FastCleverSeg maintains or surpasses the segmentation quality of competing methods, achieving a Dice score of 94%. This invaluable tool empowers physicians to efficiently generate reliable ground truths, expediting the segmentation process and paving the way for future integration with deep learning approaches. In turn, this opens exciting possibilities for future fully automated spine segmentation.

QLB-NET: A Dense Soil Moisture and Freeze–Thaw Monitoring Network in the Qinghai Lake Basin on the Qinghai–Tibetan Plateau

Abstract Soil moisture (SM) and soil freeze–thaw (FT) are two relatively active surface parameters that are significant to the sustainable development of the water–land–air–plant–human nexus. Over time, regional or global SM and FT datasets with different spatial resolutions have been developed. In response to the requirements of multiscale product validation and multisource uncertainty tracking, a soil moisture and soil temperature (ST) monitoring network in the Qinghai Lake Basin (QLB-NET) was established in September 2019. The QLB-NET is characterized by densely distributed in situ sites (82 sites) measuring SM and ST at 5-, 10-, and 30-cm depths, with 60 sites in a large-scale network covering an area of 36 km × 40 km and 22 sites evenly distributed across two small-scale 1 km × 1 km networks. Quantitative analyses of the in situ measurements show that the QLB-NET can provide stable and reliable ground truth for SM and FT over coarse grid scales, e.g., 36 km × 36 km, 25 km × 25 km, and 0.25° × 0.25°. When statistics are correspondingly performed over 50 out of 54, 25 out of 29, and 25 out of 28 sites, the results are described as follows: 1) the standard deviation of the mean SM varies between 0.0127 and 0.0196 m3 m−3, with the corresponding difference between the upper and lower quartiles being less than 0.02 m3 m−3; 2) the ground freeze–thaw state can be correctly identified with high probabilities ranging from 85.3% to 100% on two freeze–thaw transitional dates. The QLB-NET observed datasets are distributed online and will be continuously updated through cooperation with the National Tibetan Plateau Data Center (http://data.tpdc.ac.cn), facilitating product validation and uncertainty tracking, spatiotemporal analysis of SM change and FT transition, optimization of the SM and FT retrieving algorithms and scaling methods, and development of the mountainous microwave radiative transfer model.

Unsupervised Learning for Enhanced Computed Photoacoustic Microscopy

Photoacoustic microscopy (PAM) is a medical-imaging technique with the merits of high contrast and resolution. Nevertheless, conventional PAM scans specimens in a diameter-by-diameter fashion, resulting in a time-consuming process. Furthermore, deep-learning-based PAM image enhancement necessitates acquiring ground-truth data for training purposes. In this paper, we built an optical-resolution photoacoustic microscopy system and introduced an innovative unsupervised-learning algorithm. First, we enhanced the rotational-scanning method, transitioning from a diameter-by-diameter approach to a sector-by-sector one, significantly reducing imaging time (from 280 s to 109 s). Second, by establishing a metric for unsupervised learning, we eliminated the need for collecting reliable and high-quality ground truth, which is a challenging task in photoacoustic microscopy. A total of 324 pairs of datasets (mouse ears) were collected for unsupervised learning, with 274 for training and 50 for testing. Additionally, carbon-fiber data were sampled for lateral resolution and contrast evaluation, as well as the effective rate evaluation of the algorithm. The enhanced images demonstrated superior performance compared with that of maximum projection, both subjectively and objectively. A 76% improvement in the lateral resolution was observed. The effective rate of the algorithm was measured to be 100%, which was tested on 50 random samples. The technique presented in this paper holds substantial potential for image postprocessing and opens new avenues for unsupervised learning in photoacoustic microscopy.

Leveraging Remote Sensing Data for Yield Prediction with Deep Transfer Learning

Remote sensing data represent one of the most important sources for automized yield prediction. High temporal and spatial resolution, historical record availability, reliability, and low cost are key factors in predicting yields around the world. Yield prediction as a machine learning task is challenging, as reliable ground truth data are difficult to obtain, especially since new data points can only be acquired once a year during harvest. Factors that influence annual yields are plentiful, and data acquisition can be expensive, as crop-related data often need to be captured by experts or specialized sensors. A solution to both problems can be provided by deep transfer learning based on remote sensing data. Satellite images are free of charge, and transfer learning allows recognition of yield-related patterns within countries where data are plentiful and transfers the knowledge to other domains, thus limiting the number of ground truth observations needed. Within this study, we examine the use of transfer learning for yield prediction, where the data preprocessing towards histograms is unique. We present a deep transfer learning framework for yield prediction and demonstrate its successful application to transfer knowledge gained from US soybean yield prediction to soybean yield prediction within Argentina. We perform a temporal alignment of the two domains and improve transfer learning by applying several transfer learning techniques, such as L2-SP, BSS, and layer freezing, to overcome catastrophic forgetting and negative transfer problems. Lastly, we exploit spatio-temporal patterns within the data by applying a Gaussian process. We are able to improve the performance of soybean yield prediction in Argentina by a total of 19% in terms of RMSE and 39% in terms of R2 compared to predictions without transfer learning and Gaussian processes. This proof of concept for advanced transfer learning techniques for yield prediction and remote sensing data in the form of histograms can enable successful yield prediction, especially in emerging and developing countries, where reliable data are usually limited.

Simulating cardiac signals on 3D human models for photoplethysmography development.

Introduction: Image-based heart rate estimation technology offers a contactless approach to healthcare monitoring that could improve the lives of millions of people. In order to comprehensively test or optimize image-based heart rate extraction methods, the dataset should contain a large number of factors such as body motion, lighting conditions, and physiological states. However, collecting high-quality datasets with complete parameters is a huge challenge. Methods: In this paper, we introduce a bionic human model based on a three-dimensional (3D) representation of the human body. By integrating synthetic cardiac signal and body involuntary motion into the 3D model, five well-known traditional and four deep learning iPPG (imaging photoplethysmography) extraction methods are used to test the rendered videos. Results: To compare with different situations in the real world, four common scenarios (stillness, expression/talking, light source changes, and physical activity) are created on each 3D human. The 3D human can be built with any appearance and different skin tones. A high degree of agreement is achieved between the signals extracted from videos with the synthetic human and videos with a real human-the performance advantages and disadvantages of the selected iPPG methods are consistent for both real and 3D humans. Discussion: This technology has the capability to generate synthetic humans within various scenarios, utilizing precisely controlled parameters and disturbances. Furthermore, it holds considerable potential for testing and optimizing image-based vital signs methods in challenging situations where real people with reliable ground truth measurements are difficult to obtain, such as in drone rescue.

Activity-Based Detection of (Anti-)Patterns: An Embedded Case Study of the Fire Drill

Background: Nowadays, expensive, error-prone, expert-based evaluations are needed to identify and assess software process anti-patterns. Process artifacts cannot be automatically used to quantitatively analyze and train prediction models without exact ground truth. Aim: Develop a replicable methodology for organizational learning from process (anti-)patterns, demonstrating the mining of reliable ground truth and exploitation of process artifacts. Method: We conduct an embedded case study to find manifestations of the Fire Drill anti-pattern in n=15 projects. To ensure quality, three human experts agree. Their evaluation and the process’ artifacts are utilized to establish a quantitative understanding and train a prediction model. Results: Qualitative review shows many project issues. (i) Expert assessments consistently provide credible ground truth. (ii) Fire Drill phenomenological descriptions match project activity time (for example, development). (iii) Regression models trained on approx. 12–25 examples are sufficiently stable. Conclusion: The approach is data source-independent (source code or issue-tracking). It allows leveraging process artifacts for establishing additional phenomenon knowledge and training robust predictive models. The results indicate the aptness of the methodology for the identification of the Fire Drill and similar anti-pattern instances modeled using activities. Such identification could be used in post mortem process analysis supporting organizational learning for improving processes.

Ultrasound-guided needle tracking with deep learning: A novel approach with photoacoustic ground truth

Accurate needle guidance is crucial for safe and effective clinical diagnosis and treatment procedures. Conventional ultrasound (US)-guided needle insertion often encounters challenges in consistency and precisely visualizing the needle, necessitating the development of reliable methods to track the needle. As a powerful tool in image processing, deep learning has shown promise for enhancing needle visibility in US images, although its dependence on manual annotation or simulated data as ground truth can lead to potential bias or difficulties in generalizing to real US images. Photoacoustic (PA) imaging has demonstrated its capability for high-contrast needle visualization. In this study, we explore the potential of PA imaging as a reliable ground truth for deep learning network training without the need for expert annotation. Our network (UIU-Net), trained on ex vivo tissue image datasets, has shown remarkable precision in localizing needles within US images. The evaluation of needle segmentation performance extends across previously unseen ex vivo data and in vivo human data (collected from an open-source data repository). Specifically, for human data, the Modified Hausdorff Distance (MHD) value stands at approximately 3.73, and the targeting error value is around 2.03, indicating the strong similarity and small needle orientation deviation between the predicted needle and actual needle location. A key advantage of our method is its applicability beyond US images captured from specific imaging systems, extending to images from other US imaging systems.

High-Resolution Real-Time Coastline Detection Using GNSS RTK, Optical, and Thermal SfM Photogrammetric Data in the Po River Delta, Italy

High-resolution coastline detection and monitoring are challenging on a global scale, especially in flat areas where natural events, sea level rise, and anthropic activities constantly modify the coastal environment. While the coastline related to the 0-level contour line can be extracted from accurate Digital Terrain Models (DTMs), the detection of the real-time, instantaneous coastline, especially at low tide, is a challenge that warrants further study and evaluation. In order to investigate an efficient combination of methods that allows to contribute to the knowledge in this field, this work uses topographic total station measurements, Global Navigation Satellite System Real-Time Kinematic (GNSS RTK) technique, and the Structure from Motion (SfM) approach (using a low-cost drone equipped with optical and thermal cameras). All the data were acquired at the beginning of 2022 and refer to the areas of Boccasette and Barricata, in the Po River Delta (Northeastern of Italy). The real-time coastline obtained from the GNSS data was validated using the topographic total station measurements; the correspondent polylines obtained from the photogrammetric data (using both automatic extraction and manual restitutions by visual inspection of orhophotos) were compared with the GNSS data to evaluate the performances of the different techniques. The results provided good agreement between the real-time coastlines obtained from different approaches. However, using the optical images, the accuracy was strictly connected with the radiometric changes in the photos and using thermal images, both manual and automatic polylines provided differences in the order of 1–2 m. Multi-temporal comparison of the 0-level coastline with those obtained from a LiDAR survey performed in 2018 provided the detection of the erosion and accretion areas in the period 2018–2022. The investigation on the two case studies showed a better accuracy of the GNSS RTK method in the real-time coastline detection. It can be considered as reliable ground-truth reference for the evaluation of the photogrammetric coastlines. While GNSS RTK proved to be more productive and efficient, optical and thermal SfM provided better results in terms of morphological completeness of the data.

EVALUATING GEOMETRY OF AN INDOOR SCENARIO WITH OCCLUSIONS BASED ON TOTAL STATION MEASUREMENTS OF WALL ELEMENTS

Abstract. Scan2BIM approaches, i.e. the automated reconstruction of building models from point cloud data, is typically evaluated against the same point clouds which are used as input for the reconstruction process. In doing so, the point clouds are often used as ground truth without considering their own inaccuracies. Thus, in this research, we investigate the manual creation of an accurate ground truth, with a process which takes into account the measurement accuracy as well as the modeling accuracy. Therefore we created a ground truth to an existing laser scan data with a total station, based on the assumption that a total station generally measures points more reliably. In addition, a manual selection and classification of points on the wall surfaces during the measurement, serves a reliable detection of the walls via plane fitting. This allows for the creation of a more reliable ground truth, which is determined by the intersection of the planes from corners and edges. The ground truth is aligned parallel to the axes of a local coordinate system. From MLS and TLS point clouds of the same building area, walls are manually classified and corners and edges are determined in a similar way to the total station. These TLS and MLS corners are registered to this ground truth using least squares optimisation at the vertices. The transformation thus determined is used to transform the laser scanning point clouds as well. The resulting errors in the corners and the whole point cloud are evaluated. We conclude that the standard deviation of wall surfaces alone isn’t sufficient to determine the quality of the reconstructed building model. Despite low measurement noise in single wall surfaces, deviations in the reconstructed room model may arise.

MIN3D Dataset: MultI-seNsor 3D Mapping with an Unmanned Ground Vehicle

The research potential in the field of mobile mapping technologies is often hindered by several constraints. These include the need for costly hardware to collect data, limited access to target sites with specific environmental conditions or the collection of ground truth data for a quantitative evaluation of the developed solutions. To address these challenges, the research community has often prepared open datasets suitable for developments and testing. However, the availability of datasets that encompass truly demanding mixed indoor–outdoor and subterranean conditions, acquired with diverse but synchronized sensors, is currently limited. To alleviate this issue, we propose the MIN3D dataset (MultI-seNsor 3D mapping with an unmanned ground vehicle for mining applications) which includes data gathered using a wheeled mobile robot in two distinct locations: (i) textureless dark corridors and outside parts of a university campus and (ii) tunnels of an underground WW2 site in Walim (Poland). MIN3D comprises around 150 GB of raw data, including images captured by multiple co-calibrated monocular, stereo and thermal cameras, two LiDAR sensors and three inertial measurement units. Reliable ground truth (GT) point clouds were collected using a survey-grade terrestrial laser scanner. By openly sharing this dataset, we aim to support the efforts of the scientific community in developing robust methods for navigation and mapping in challenging underground conditions. In the paper, we describe the collected data and provide an initial accuracy assessment of some visual- and LiDAR-based simultaneous localization and mapping (SLAM) algorithms for selected sequences. Encountered problems, open research questions and areas that could benefit from utilizing our dataset are discussed. Data are available at https://3dom.fbk.eu/benchmarks.

Monte Carlo simulation of water diffusion through cardiac tissue models.

Monte Carlo diffusion simulations are commonly used to establish a reliable ground truth of tissue microstructure, including for the validation of diffusion-weighted MRI. However, selecting simulation parameters is challenging and affects validity and reproducibility. We conducted experiments to investigate critical conditions in Monte Carlo simulations, such as tissue representation complexity, simulated molecules, update duration, and compartment size. Results show significant changes in microstructure characteristics when parameters are altered, emphasizing the importance of careful control for a reliable ground truth.

Confidence-aware self-supervised learning for dense monocular depth estimation in dynamic laparoscopic scene

This paper tackles the challenge of accurate depth estimation from monocular laparoscopic images in dynamic surgical environments. The lack of reliable ground truth due to inconsistencies within these images makes this a complex task. Further complicating the learning process is the presence of noise elements like bleeding and smoke. We propose a model learning framework that uses a generic laparoscopic surgery video dataset for training, aimed at achieving precise monocular depth estimation in dynamic surgical settings. The architecture employs binocular disparity confidence information as a self-supervisory signal, along with the disparity information from a stereo laparoscope. Our method ensures robust learning amidst outliers, influenced by tissue deformation, smoke, and surgical instruments, by utilizing a unique loss function. This function adjusts the selection and weighting of depth data for learning based on their given confidence. We trained the model using the Hamlyn Dataset and verified it with Hamlyn Dataset test data and a static dataset. The results show exceptional generalization performance and efficacy for various scene dynamics, laparoscope types, and surgical sites.

Chemical Blast Standard (1 kg)

Abstract Chemical explosions create blast waves with large overpressure disturbances. It is important to develop a standard blast model based on data to accurately predict acoustic blast-wave amplitudes near detonations and invert for explosion energy from distant observations of blast-wave signals. However, open data from large, controlled chemical explosions with reliable ground truth can be challenging to find. The lack of access to such data could limit the number of contributions to related research and potentially stifle the rate of discoveries or validation of existing models. To address these data scarcity problem, we have curated and compiled a standardized set of 817 blast-wave waveforms from 19 distinct high-explosive events. The blast-wave waveforms are standardized to a 1 kg trinitrotoluene explosion using scaling laws and corrections for location effects. A brief overview of the dataset is presented along with explosion feature models as well as recommendations for extracting explosion features. The resulting dataset is distributed to an open repository in both Seismic Analysis Code and pandas DataFrame formats containing the waveforms, the scaled distances, and the sample rates.

Reliability of whole mount radical prostatectomy histopathology as the ground truth for artificial intelligence assisted prostate imaging

The development of artificial intelligence–based imaging techniques for prostate cancer (PCa) detection and diagnosis requires a reliable ground truth, which is generally based on histopathology from radical prostatectomy specimens. This study proposes a comprehensive protocol for the annotation of prostatectomy pathology slides. To evaluate the reliability of the protocol, interobserver variability was assessed between five pathologists, who annotated ten radical prostatectomy specimens consisting of 74 whole mount pathology slides. Interobserver variability was assessed for both the localization and grading of PCa. The results indicate excellent overall agreement on the localization of PCa (Gleason pattern ≥ 3) and clinically significant PCa (Gleason pattern ≥ 4), with Dice similarity coefficients (DSC) of 0.91 and 0.88, respectively. On a per-slide level, agreement for primary and secondary Gleason pattern was almost perfect and substantial, with Fleiss Kappa of .819 (95% CI .659–.980) and .726 (95% CI .573–.878), respectively. Agreement on International Society of Urological Pathology Grade Group was evaluated for the index lesions and showed agreement in 70% of cases, with a mean DSC of 0.92 for all index lesions. These findings show that a standardized protocol for prostatectomy pathology annotation provides reliable data on PCa localization and grading, with relatively high levels of interobserver agreement. More complicated tissue characterization, such as the presence of cribriform growth and intraductal carcinoma, remains a source of interobserver variability and should be treated with care when used in ground truth datasets.

Maintainable Log Datasets for Evaluation of Intrusion Detection Systems

Intrusion detection systems (IDS) monitor system logs and network traffic to recognize malicious activities in computer networks. Evaluating and comparing IDSs with respect to their detection accuracies is thereby essential for their selection in specific use-cases. Despite a great need, hardly any labeled intrusion detection datasets are publicly available. As a consequence, evaluations are often carried out on datasets from real infrastructures, where analysts cannot control system parameters or generate a reliable ground truth, or private datasets that prevent reproducibility of results. As a solution, we present a collection of maintainable log datasets collected in a testbed representing a small enterprise. Thereby, we employ extensive state machines to simulate normal user behavior and inject a multi-step attack. For scalable testbed deployment, we use concepts from model-driven engineering that enable automatic generation and labeling of an arbitrary number of datasets that comprise repetitions of attack executions with variations of parameters. In total, we provide 8 datasets containing 20 distinct types of log files, of which we label 8 files for 10 unique attack steps. We publish the labeled log datasets and code for testbed setup and simulation online as open-source to enable others to reproduce and extend our results.

A Reliable Sample Selection Strategy for Weakly Supervised Visual Tracking

Reliability is an important property in the applied engineering systems, especially in visual tracking. The supervised visual tracking method uses reliable ground truth that is manually annotated, which is hard to get in many applications. However, weakly supervised visual trackings are limited by the low-quality labels. Therefore, a reliable sample selection strategy is the most important issue for the weakly supervised visual trackings. In this article, we propose an optimal sample selection strategy and apply it to the visual tracking system. The strategy first assesses the reliability of the samples according to the score map, where the score map is the pseudolabel generated by the upstream task to meet the needs of the downstream task. Then, the unreliable pseudolabels are replaced by reliable ground truth or discarded to overcome the degraded modeling problem by filtering low-quality samples. Finally, through comparison with multiple selection strategies, it is verified that the model trained using this strategy has the best performance. The proposed visual tracking model achieves the best performance among multiple assessment metrics in multiple datasets. Experiments verify that the scientific sample quality assessment method is very important. It can guide the improvement of model performance, which is of great help to the weakly supervised learning systems based on data.

Interpolation-Based Framework for Generation of Ground Truth Data for Testing Lane Detection Algorithm for Automated Vehicle

Automated vehicles, predicted to be fully electric in future, are expected to reduce road fatalities and road traffic emissions. The lane departure warning system, an important feature of automated vehicles, utilize lane detection and tracking algorithms. Researchers are constrained to test their lane detection algorithms because of the small publicly available datasets. Additionally, those datasets may not represent differences in road geometries, lane marking and other details unique to a particular geographic location. Existing methods to develop the ground truth datasets are time intensive. To address this gap, this study proposed a framework for an interpolation approach for quickly generating reliable ground truth data. The proposed method leverages the advantage of the existing manual and time-slice approaches. A detailed framework for the interpolation approach is presented and the performance of the approach is compared with the existing methods. Video datasets for performance evaluation were collected in Melbourne, Australia. The results show that the proposed approach outperformed four existing approaches with a reduction in time for generating ground truth data in the range from 4.8% to 87.4%. A reliable and quick method for generating ground truth data, as proposed in this study, will be valuable to researchers as they can use it to test and evaluate their lane detection and tracking algorithms.