Wind energy offers a sustainable solution to reduce carbon emissions but presents risks to bird populations, particularly through potential collisions with turbine blades. The Bird Protection System, BPS, employing stereo vision, aims to mitigate these risks by detecting and tracking birds and estimating their distance from turbines. The precision of distance estimation remains challenging due to quantization uncertainty and environmental factors such as lighting, background complexity, and asynchronous camera frames, which can lead to unstable and imprecise measurements. This paper explores methods to enhance the accuracy and reliability of bird tracking systems by addressing one of the key technical challenges: precise disparity estimation. We investigate three methods: based on the detected object’s bounding box center, the object’s center of gravity, and the image alignment technique that uses cross-correlation. The methods use an object’s image extracted from the background and resized to ensure a subpixel refinement. Our findings show that the center of gravity and cross-correlation methods with resizing significantly enhance tracking stability and precision, and the former is also computationally efficient, rendering it useful for real-time applications, such as BPS. 

Understanding program structure, control flow, and problem decomposition is essential in programming education, but many students find algorithmic thinking challenging. Conventional educational approaches frequently prioritize syntax at the expense of logical reasoning and provide minimal personalized feedback. This paper outlines the design and initial assessment of FlowBro, an AI-driven educational tool intended to enhance algorithmic thinking in early programming education. The tool integrates a flowchart visualization, sequential code simulation, and an intelligent assistant that offers contextual hints, debugging tips, and educational support while maintaining a focus on minimalism by not disclosing complete solutions. The system enables students to engage with Python code, follow its execution, and obtain tailored assistance aligned with their specific objectives. A qualitative evaluation with educators in the field revealed the tool's potential advantages, especially in large classes and self-directed learning contexts, while also pointing out challenges concerning the reliability of AI feedback and the necessity for more extensive testing. This study presents a streamlined framework for merging AI with visual learning in programming education, while also suggesting pathways for its future enhancement and empirical testing.

Wireless sensor networks often use a distributed configuration and rely on self-organizing mechanisms to integrate local information into a global context. This paper considers the 3-hop path as the basic component of a multi-hop path; the 3-hop path has two types of planar topological structures,‘S’-shaped and ‘U’-shaped. This paper provides a deduction of all possible topological structures when a 4-hop structure is merged into a 3-hop structure. Additionally, it offers an iterative method for determining the overall direct distance between the start and end points of an n-hop path along a polyline, given that each node is aware of the distances to nearby nodes.

Euler's four-point formula is utilized in the proposed method to perform two key functions: identifying whether a 3-hop path is ‘U’-shaped or ‘S’-shaped and calculating the straight-line distance within a virtual quadrilateral. The above method is combined with the distance vector routing (DV-Hop) algorithm, and the resulting algorithm is called Path's Straight Distance DV-Hop (PSDDV-Hop).

PSDDV-Hop significantly increases the accuracy of localization by eliminating the polyline bending errors in the distance estimation for an n-hop path. Several issues related to the implementation of PSDDV-Hop are analyzed, and corresponding solutions are provided, including a method of estimating the straight-line distance within no more than 3-hop and the replacement of nonlinear distance–area functions with linear fitting to reduce complexity and compensate for estimation bias. Two distinct strategies for setting the communication radius are introduced to accommodate diverse scenarios. Ultimately, the experiments confirm that PSDDV-Hop provides greater accuracy in localization across diverse network configurations. 

In modern autonomous systems, measurement repeatability and precision are crucial for robust decision-making algorithms. Stereovision, which is widely used in safety applications, provides information about an object’s shape, orientation, and 3D localisation. The camera’s lens distortion is a common source of systematic measurement errors, which can be estimated and then eliminated or at least reduced using a suitable correction/calibration method. In this study, a set of cameras equipped with Basler lenses (C125-0618-5M F1.8 f6mm) and Sony IMX477R matrices are calibrated using a state-of-the-art Zhang–Duda–Frese method. The resulting distortion coefficients are used to correct the images. The calibrations are evaluated with the aid of two novel methods for lens distortion measurement. The first one is based on linear regression with images of a vertical and horizontal line pattern. Based on the evaluation tests, outlying cameras are eliminated from the test set by applying the 2 (Formula presented.) criterion. For the remaining cameras, the MSE was reduced up to 75.4 times, to 1.8 px−6.9 px. The second method is designed to evaluate the impact of lens distortion on stereovision applied to bird tracking around wind farms. A bird’s flight trajectory is synthetically generated to estimate changes in disparity and distance before and after calibration. The method shows that at the margins of the image, lens distortion might introduce errors into the object’s distance measurement of +17%−+20% for cameras with the same distortion and from −41% up to (Formula presented.) for camera pairs with different lens distortions. These results highlight the importance of having well-calibrated cameras in systems that require precision, such as stereovision bird tracking in bird–turbine collision risk assessment systems.

With the expansion of green energy, more and more data show that wind turbines can pose a significant threat to some endangered bird species. The birds of prey are more frequently exposed to collision risk with the wind turbine blades due to their unique flight path patterns. This paper shows how data from a stereovision system can be used for an efficient classification of detected objects. A method for distinguishing endangered birds from common birds and other flying objects has been developed and tested. The research focused on the selection of a suitable feature extraction methodology. Both motion and visual features are extracted from the Bioseco BPS system and retested using a correlation-based and a wrapper-type approach with genetic algorithms (GAs). With optimal features and fine-tuned classifiers, birds can be distinguished from aeroplanes with a 98.6% recall and 97% accuracy, whereas endangered birds are delimited from common ones with 93.5% recall and 77.2% accuracy.

The study addresses the challenge of bird collisions with wind turbines by developing an autonomous risk assessment method. The research uses data from the stereoscopic Bird Protection System (BPS) to anticipate potential collision threats by analysing flight parameters and distance from turbines. The danger factor depends on the flight characteristics of the identified bird species and the parameters of the wind turbine control system. The paper proposes an online quantitative risk assessment model that operates in real time, with the aim of minimising unnecessary turbine shutdowns while improving bird conservation. The model is validated through field data from bird flights. The findings suggest that adaptive management of turbine operations based on real-time bird flight data can significantly reduce collision risks without compromising energy production efficiency. The research underscores the balance between ecological considerations and the economic viability of wind energy, proposing an adaptive strategy that reduces unnecessary turbine stoppages while ensuring the safety of avian species. 

A new method using burial measurements for risk assessment of subsea cable installations is proposed. Only methods comparing the design boundaries have previously been used to verify subsea cable installments. The disadvantage of utilizing design boundaries is the possibility of not fulfilling the risk requirements since the assumed burial depth of the cable and its measurement data can differ, leading to the challenge of assessing how the difference and its uncertainty affect burial risk. We proposed and tested the method for a scenario using seagoing vessel traffic data and sensor characteristics. The analysis is limited to white measurement noise but shows a deviation in risk estimation between the design-and measurement-based assessments. The presented result enables the approximation of the risk assessment for projects of varying specifications. The proposed statistical method is a less conservative way to assess the correct installment of a cable and possibly to evaluate verification specifications. © 2022 IEEE.

Aviation reports indicate that between 1988 and 2019 there were 292 human deaths and 327 injuries that had been reported from wildlife strikes with airplanes. To minimize these numbers, a new approach to airport Wildlife Hazard Management (WHM) is presented in the following article. The proposed solution is based on the data fusion of thermal and vision streams, which are used to improve the reliability and adaptability of the real-time WHM system. The system is designed to operate under all environmental conditions and provides advance information on the fauna presence on the airport runway. The proposed sensor fusion approach was designed and developed using user-driven design methodology. Moreover, the developed system has been validated in real-case scenarios and previously installed at an airport. Performed tests proved detection capabilities during day and night of dog-sized animals up to 300 meters. Moreover, by using machine learning algorithms during daylight, the system was able to classify person-sized objects with over 90 % efficiency up to 300 meters and dog-sized objects up to 200 meters. The general accuracy of the threat level based on the three safety zones was 94 %. © 2022 Kauno Technologijos Universitetas. All rights reserved.

Available methods using the burial measurements to assess the subsea cable installations risks compare measurements to the design boundaries. The disadvantage of using this is that the assumed cable burial depths and their measurements can differ. However, it is unclear how the uncertainty in depth affects burial risk; hence, there is a need to verify the burial operations using a proper method to handle this aspect of risk reliability. We proposed a conservative cable burial scenario test, which evaluates the highest deviation between the measured risk and the design risk to indicate differences in risk based on the measurements. The result shows that the most significant deviation could be up to 55%. It proves that measurement uncertainty significantly affects the final risk evaluation. Moreover, this deviation in verifiable risk is not considered in today's boundary-level verification methodology. © 2022 IEEE.

In 2020, over 10,000 bird strikes were reported in the USA, with average repair costs exceeding $200 million annually, rising to $1.2 billion worldwide. These collisions of avifauna with airplanes pose a significant threat to human safety and wildlife. This article presents a system dedicated to monitoring the space over an airport and is used to localize and identify moving objects. The solution is a stereovision based real-time bird protection system, which uses IoT and distributed computing concepts together with advanced HMI to provide the setup’s flexibility and usability. To create a high degree of customization, a modified stereovision system with freely oriented optical axes is proposed. To provide a market tailored solution affordable for small and medium size airports, a user-driven design methodology is used. The mathematical model is implemented and optimized in MATLAB. The implemented system prototype is verified in a real environment. The quantitative validation of the system performance is carried out using fixed-wing drones with GPS recorders. The results obtained prove the system’s high efficiency for detection and size classification in real-time, as well as a high degree of localization certainty. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.