Alexey Kudryashov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Alexey Kudryashov has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Valerii Aleksandrovich Bobkov
Institute of Automation and Control Processes, Far Eastern Branch, Russian Academy of Sciences, 690041 Vladivostok, Russia
14 shared publications - Alexander Inzartsev
Far Eastern Federal University, Institute for Marine Technology Problems FEB RAS, Vladivostok, Russia
5 shared publications S. V. Mel’MAn
Far East Branch of the Russian Academy of Sciences
3 shared publicationsV. A. Bobkov
3 shared publicationsS.V. Melman
Far Eastern Branch of the Russian Academy of Sciences, IACP FEB RAS, Institute of Automation and Control Processes, Vladivostok, Russia
2 shared publicationsА.п. Кудряшов
2 shared publications
Latest Publications
- 26 September 2025
- Published by Far Eastern Branch of the Russian Academy of Sciences in Podvodnye issledovaniia i robototehnika
- Vol. 53 (3) , 51-57
The method for recognition underwater artificial objects
The article is devoted to the current problem of detecting underwater presumably artificial objects (AO) within the framework of a seabed monitoring mission using an autonomous unmanned underwater vehicle (AUV) equipped with a stereo camera. Such objects include, along with underwater industrial infrastructure objects, sunken objects, military objects, etc. In particular, a pressing task is to detect objects near pipelines and other communications. Detection of these objects involves their automatic localization and recognition of characteristics indicating the artificial nature of the object’s origin. In contrast to the traditional approach based on comparing input data with an a priori given model of the object, this paper proposes a method for direct recognition using computer vision methods of elementary geometric elements (GE) characteristic of the object in the input 3D point cloud obtained by processing a stereo pair of images. Such GEs include spatial segments (parallelepiped edges), spherical surfaces, as well as color, texture and other features. According to the proposed methodology, direct identification of the detected object with the adoption of decisions on subsequent actions will be carried out by the operator in offline mode based on the analysis of the received images and data from automatic algorithmic processing on board the AUV. The computational experiments performed with model data confirmed the prospects of the proposed method for detecting underwater objects.
- 26 September 2025
- Published by Far Eastern Branch of the Russian Academy of Sciences in Podvodnye issledovaniia i robototehnika
- Vol. 53 (3) , 51-57
The method for recognition underwater artificial objects
The article is devoted to the current problem of detecting underwater presumably artificial objects (AO) within the framework of a seabed monitoring mission using an autonomous unmanned underwater vehicle (AUV) equipped with a stereo camera. Such objects include, along with underwater industrial infrastructure objects, sunken objects, military objects, etc. In particular, a pressing task is to detect objects near pipelines and other communications. Detection of these objects involves their automatic localization and recognition of characteristics indicating the artificial nature of the object’s origin. In contrast to the traditional approach based on comparing input data with an a priori given model of the object, this paper proposes a method for direct recognition using computer vision methods of elementary geometric elements (GE) characteristic of the object in the input 3D point cloud obtained by processing a stereo pair of images. Such GEs include spatial segments (parallelepiped edges), spherical surfaces, as well as color, texture and other features. According to the proposed methodology, direct identification of the detected object with the adoption of decisions on subsequent actions will be carried out by the operator in offline mode based on the analysis of the received images and data from automatic algorithmic processing on board the AUV. The computational experiments performed with model data confirmed the prospects of the proposed method for detecting underwater objects.
- 1 November 2024
- Published by FSB EIHE Omsk State Technical University
COORDINATE REFERENCING OF AN AUTONOMOUS UNDERWATER VEHICLE TO OBJECTS OF A SUBSEA PRODUCTION SYSTEM USING STEREO IMAGES
Recently, the urgency of the problem of inspection of underwater infrastructure (gas and oil pipelines, subsea production systems (SPS), etc.) using autonomous underwater vehicles (AUVs) has increased as an alternative to the traditionally used technology of remote control of an underwater vehicle. Accurate localization of AUVs relative to objects is a key inspection task. However, the difficulties characteristic of the underwater environment do not allow for high-precision navigation based only on the sensors of the standard navigation system (hydroacoustics, inertial measuring unit, etc.). An alternative/addition to the mentioned navigation tools are technologies based on the use of computer vision, which can potentially provide higher accuracy of AUV navigation in comparison with the processing of acoustic measurements in local scenes at short distances to objects. Therefore, in this work, in the context of solving the problem of inspecting objects of an SPSs, we propose a new approach to solving the problem of recognizing underwater objects and the coordinate reference of AUVs to them, based on stereo image processing. Distinctive features of the approach are the use of a non-standard automated technique for generating a geometric model of an object from images of a survey trajectory, the use of different types of characteristic geometric elements (points, segments, angles) when recognizing objects, and the use of original algorithms for comparing the resulting visual data with an a priori model of the object.
- 1 November 2024
- Published by FSB EIHE Omsk State Technical University
COORDINATE REFERENCING OF AN AUTONOMOUS UNDERWATER VEHICLE TO OBJECTS OF A SUBSEA PRODUCTION SYSTEM USING STEREO IMAGES
Recently, the urgency of the problem of inspection of underwater infrastructure (gas and oil pipelines, subsea production systems (SPS), etc.) using autonomous underwater vehicles (AUVs) has increased as an alternative to the traditionally used technology of remote control of an underwater vehicle. Accurate localization of AUVs relative to objects is a key inspection task. However, the difficulties characteristic of the underwater environment do not allow for high-precision navigation based only on the sensors of the standard navigation system (hydroacoustics, inertial measuring unit, etc.). An alternative/addition to the mentioned navigation tools are technologies based on the use of computer vision, which can potentially provide higher accuracy of AUV navigation in comparison with the processing of acoustic measurements in local scenes at short distances to objects. Therefore, in this work, in the context of solving the problem of inspecting objects of an SPSs, we propose a new approach to solving the problem of recognizing underwater objects and the coordinate reference of AUVs to them, based on stereo image processing. Distinctive features of the approach are the use of a non-standard automated technique for generating a geometric model of an object from images of a survey trajectory, the use of different types of characteristic geometric elements (points, segments, angles) when recognizing objects, and the use of original algorithms for comparing the resulting visual data with an a priori model of the object.
- Open Access
- 2 September 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (9) , 1514
A Method for Recognition and Coordinate Reference of Autonomous Underwater Vehicles to Inspected Objects of Industrial Subsea Structures Using Stereo Images
To date, the development of unmanned technologies using autonomous underwater vehicles (AUVs) has become an urgent demand for solving the problem of inspecting industrial subsea structures. A key issue here is the precise localization of AUVs relative to underwater objects. However, the impossibility of using GPS and the presence of various interferences associated with the dynamics of the underwater environment do not allow high-precision navigation based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative technology involves the processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to the technology of acoustic measurement processing. Although there have been results in this direction, further development of methods for extracting spatial information about objects from images recorded by a camera is necessary in the task of calculating the exact mutual position of the AUV and the object. In this study, in the context of the problem of subsea production system inspection, we propose a technology to recognize underwater objects and provide coordinate references to the AUV based on stereo-image processing. Its distinctive features are the use of a non-standard technique to generate a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object. The results of experiments on virtual scenes and with real data showed the effectiveness of the proposed technology.
- 2 September 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (9) , 1514
Open AccessA Method for Recognition and Coordinate Reference of Autonomous Underwater Vehicles to Inspected Objects of Industrial Subsea Structures Using Stereo Images
To date, the development of unmanned technologies using autonomous underwater vehicles (AUVs) has become an urgent demand for solving the problem of inspecting industrial subsea structures. A key issue here is the precise localization of AUVs relative to underwater objects. However, the impossibility of using GPS and the presence of various interferences associated with the dynamics of the underwater environment do not allow high-precision navigation based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative technology involves the processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to the technology of acoustic measurement processing. Although there have been results in this direction, further development of methods for extracting spatial information about objects from images recorded by a camera is necessary in the task of calculating the exact mutual position of the AUV and the object. In this study, in the context of the problem of subsea production system inspection, we propose a technology to recognize underwater objects and provide coordinate references to the AUV based on stereo-image processing. Its distinctive features are the use of a non-standard technique to generate a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object. The results of experiments on virtual scenes and with real data showed the effectiveness of the proposed technology.
- Open Access
- 6 August 2024
- Published by MDPI AG in Preprints.org
A Method for Recognition and Coordinate Reference of Autono-Mous Underwater Vehicle to Inspected Objects of Industrial Sub-Sea Structures Using Stereo Images
To date, the development of unmanned technologies using autonomous underwater vehicles (AUV) has become an urgent demand for solving the problem of inspection of industrial sub-sea structures. A key issue here is precise localization of AUVs relative to underwater objects. However, the well-known challenges of recognizing and coordinating underwater objects (impossibility to use GPS, undercurrents, etc.) do not allow high-precision navigation if based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative is a technology of processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to a technology of acoustic measurement processing. In this study, in the context of the problem of subsea production system inspection, we propose a method to recognize underwater objects and provide coordinate reference of AUV to them, based on stereo-image processing. Its distinctive features are the use of a non-standard technique for generating a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object.
- 6 August 2024
- Published by MDPI AG in Preprints.org
Open AccessA Method for Recognition and Coordinate Reference of Autono-Mous Underwater Vehicle to Inspected Objects of Industrial Sub-Sea Structures Using Stereo Images
To date, the development of unmanned technologies using autonomous underwater vehicles (AUV) has become an urgent demand for solving the problem of inspection of industrial sub-sea structures. A key issue here is precise localization of AUVs relative to underwater objects. However, the well-known challenges of recognizing and coordinating underwater objects (impossibility to use GPS, undercurrents, etc.) do not allow high-precision navigation if based solely on a standard suite of AUV navigation tools (sonars, etc.). An alternative is a technology of processing of optical images that, at short distances, can provide higher accuracy of AUV navigation compared to a technology of acoustic measurement processing. In this study, in the context of the problem of subsea production system inspection, we propose a method to recognize underwater objects and provide coordinate reference of AUV to them, based on stereo-image processing. Its distinctive features are the use of a non-standard technique for generating a geometric model of an object from its views (foreshortening) taken from positions of a pre-made overview trajectory, the use of various characteristic geometric elements when recognizing objects, and the original algorithms for comparing visual data of the inspection trajectory with an a priori model of the object.
- 13 April 2023
- Published by New Technologies Publishing House in Mekhatronika, Avtomatizatsiya, Upravlenie
- Vol. 24 (4) , 206-215-215
Ship Hull Inspection Using Autonomous an Underwater Vehicle with a Stereo Camera
Регулярный визуальный осмотр подводной поверхности корпуса судна в целях проверки его целостности и степени биообрастания необходим для обеспечения безопасности и эффективности эксплуатации судна. В статье предлагается метод автоматизированного решения этой задачи с использованием автономного необитаемого подводного аппарата (АНПА), оснащенного стереокамерой, управляемой поворотным механизмом. Движение АНПА осуществляется по эквидистантам вдоль корпуса судна с одновременной видеосъемкой поверхности корпуса. Траектория движения АНПА рассчитывается с применением метода визуальной навигации (визуальная одометрия). Расчетные данные о локализации аппарата относительно корпуса судна используются в методе управления движением аппарата для обеспечения устойчивого движения аппарата на заданном расстоянии от инспектируемой поверхности. Непосредственное вычисление данных о локализации АНПА делается с помощью предлагаемого оригинального алгоритма, который реализован в виде программного средства "стереодальномер". Работа стереодальномера основана на сопоставлении особенностей на изображениях с помощью детектора SURF с последующим построением 3D-облака точек. Описана методика выполнения автоматической инспекции судна в целом. Фиксируемые стереоизображения используются также для построения 3D-модели осматриваемой поверхности. Применяемый метод построения глобальной пространственной модели поверхности основывается на объединении 3D-облаков точек, получаемых для локальных видов. Построение 3D-облака точек для отдельного вида выполняется на основе сопоставления 2D-точечных особенностей на изображениях стереопары (детектор SURF/вычисление корреляции) с последующим применением метода триангуляции лучей для получения пространственных координат точек. Наличие 3D-модели дает возможность провести детальный визуальный анализ состояния корпуса судна. Проведено имитационное моделирование функционирования разработанных средств на виртуальных сценах. Полученные в результате тестирования количественные и качественные оценки эффективности показали приемлемость предложенной методики для автоматической инспекции подводной части корпуса судна.
- 13 April 2023
- Published by New Technologies Publishing House in Mekhatronika, Avtomatizatsiya, Upravlenie
- Vol. 24 (4) , 206-215-215
Ship Hull Inspection Using Autonomous an Underwater Vehicle with a Stereo Camera
Регулярный визуальный осмотр подводной поверхности корпуса судна в целях проверки его целостности и степени биообрастания необходим для обеспечения безопасности и эффективности эксплуатации судна. В статье предлагается метод автоматизированного решения этой задачи с использованием автономного необитаемого подводного аппарата (АНПА), оснащенного стереокамерой, управляемой поворотным механизмом. Движение АНПА осуществляется по эквидистантам вдоль корпуса судна с одновременной видеосъемкой поверхности корпуса. Траектория движения АНПА рассчитывается с применением метода визуальной навигации (визуальная одометрия). Расчетные данные о локализации аппарата относительно корпуса судна используются в методе управления движением аппарата для обеспечения устойчивого движения аппарата на заданном расстоянии от инспектируемой поверхности. Непосредственное вычисление данных о локализации АНПА делается с помощью предлагаемого оригинального алгоритма, который реализован в виде программного средства "стереодальномер". Работа стереодальномера основана на сопоставлении особенностей на изображениях с помощью детектора SURF с последующим построением 3D-облака точек. Описана методика выполнения автоматической инспекции судна в целом. Фиксируемые стереоизображения используются также для построения 3D-модели осматриваемой поверхности. Применяемый метод построения глобальной пространственной модели поверхности основывается на объединении 3D-облаков точек, получаемых для локальных видов. Построение 3D-облака точек для отдельного вида выполняется на основе сопоставления 2D-точечных особенностей на изображениях стереопары (детектор SURF/вычисление корреляции) с последующим применением метода триангуляции лучей для получения пространственных координат точек. Наличие 3D-модели дает возможность провести детальный визуальный анализ состояния корпуса судна. Проведено имитационное моделирование функционирования разработанных средств на виртуальных сценах. Полученные в результате тестирования количественные и качественные оценки эффективности показали приемлемость предложенной методики для автоматической инспекции подводной части корпуса судна.
- 1 January 2023
- Published by Keldysh Institute of Applied Mathematics
Visual Navigation for the Inspection of Industrial Underwater Structures Using a Virtual Coordinate Network
Inspection of underwater industrial infrastructure facilities using autonomous uninhabited underwater vehicles (AUVs) requires high accuracy of AUV navigation relative to the objects being inspected. Along with traditional navigation aids based on the inertial navigation system and sonars, technologies based on video information processing are being actively developed today. Methods based on visual odometry can provide higher navigation accuracy in conditions of local maneuvering at small distances to objects. However, during long-term movements of the AUV, such methods tend to accumulate errors in the calculation of the trajectory. Therefore, this paper proposes a navigation method that can significantly improve the accuracy of AUV movement in the coordinate space of the inspected object due to the generation and use of a virtual network of coordinate reference to an underwater object.
- 1 January 2023
- Published by Keldysh Institute of Applied Mathematics
Visual Navigation for the Inspection of Industrial Underwater Structures Using a Virtual Coordinate Network
Inspection of underwater industrial infrastructure facilities using autonomous uninhabited underwater vehicles (AUVs) requires high accuracy of AUV navigation relative to the objects being inspected. Along with traditional navigation aids based on the inertial navigation system and sonars, technologies based on video information processing are being actively developed today. Methods based on visual odometry can provide higher navigation accuracy in conditions of local maneuvering at small distances to objects. However, during long-term movements of the AUV, such methods tend to accumulate errors in the calculation of the trajectory. Therefore, this paper proposes a navigation method that can significantly improve the accuracy of AUV movement in the coordinate space of the inspected object due to the generation and use of a virtual network of coordinate reference to an underwater object.
- Open Access
- 13 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (20) , 5123
A Technique to Navigate Autonomous Underwater Vehicles Using a Virtual Coordinate Reference Network during Inspection of Industrial Subsea Structures
Industrial subsea infrastructure inspections using autonomous underwater vehicles (AUV) require high accuracy of AUV navigation relative to the objects being examined. In addition to traditional navigation tools with inertial navigation systems and acoustic navigation equipment, technologies with video information processing are also actively developed today. The visual odometry-based techniques can provide higher navigation accuracy for local maneuvering at short distances to objects. However, in the case of long-distance AUV movements, such techniques typically accumulate errors when calculating the AUV movement trajectory. In this regard, the present article considers a navigation technique that allows for increasing the accuracy of AUV movements in the coordinate space of the object inspected by using a virtual coordinate reference network. Another aspect of the method proposed is to minimize computational costs for AUV moving along the inspection trajectory by referencing the AUV coordinates to the object pre-calculated using the object recognition algorithm. Thus, the use of a network of virtual points for referencing the AUV to subsea objects is aimed to maintain the required accuracy of AUV coordination during a long-distance movement along the inspection trajectory, while minimizing computational costs.
- 13 October 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (20) , 5123
Open AccessA Technique to Navigate Autonomous Underwater Vehicles Using a Virtual Coordinate Reference Network during Inspection of Industrial Subsea Structures
Industrial subsea infrastructure inspections using autonomous underwater vehicles (AUV) require high accuracy of AUV navigation relative to the objects being examined. In addition to traditional navigation tools with inertial navigation systems and acoustic navigation equipment, technologies with video information processing are also actively developed today. The visual odometry-based techniques can provide higher navigation accuracy for local maneuvering at short distances to objects. However, in the case of long-distance AUV movements, such techniques typically accumulate errors when calculating the AUV movement trajectory. In this regard, the present article considers a navigation technique that allows for increasing the accuracy of AUV movements in the coordinate space of the object inspected by using a virtual coordinate reference network. Another aspect of the method proposed is to minimize computational costs for AUV moving along the inspection trajectory by referencing the AUV coordinates to the object pre-calculated using the object recognition algorithm. Thus, the use of a network of virtual points for referencing the AUV to subsea objects is aimed to maintain the required accuracy of AUV coordination during a long-distance movement along the inspection trajectory, while minimizing computational costs.
- 13 September 2022
- Published by Pleiades Publishing Ltd in Programming and Computer Software
- Vol. 48 (5) , 301-311
Object Recognition and Coordinate Referencing of an Autonomous Underwater Vehicle to Objects via Video Stream
This paper is devoted to the important problem of subsea infrastructure inspection using autonomous underwater vehicles (AUVs). The accomplishment of the inspection mission requires high accuracy of AUV coordination with respect to objects, which is not always provided by standard hydroacoustic equipment. That is why we propose an approach based on stereo image processing that can provide submeter accuracy of AUV coordination required under subsea conditions. In the framework of a unified approach based on the use of an a priori formed point model of an object and the application of a structural coherence criterion, we propose and analyze several methods for recognition of underwater objects and coordinate referencing of the AUV to these objects. As a geometric model of an object, we consider its representation based on characteristic points, which determines the spatial structure of the object. In addition to the standard method for object model construction from preliminary measurements, a new method is proposed, which is based on automated technique of model generation from images offline. The proposed object recognition methods use the structural coherence criterion to match 3D point clouds with object models. The 3D point clouds are formed from stereo images captured by a camera using visual navigation. Feature points are generated and matched using the SURF detector and Harris corner detector. To improve the reliability of object identification, we propose joint processing of source images with their vectorized forms. The use of line segments obtained by vectorization significantly increases the number of identified characteristic points when matching a 3D point cloud with a model. Based on the identified points of an object, the matrix of AUV coordinate referencing to this object is computed. The efficiency of the considered methods is estimated and compared. In the computational experiments with model scenes, a virtual geometric model of a distributed subsea production system is used. The experiments on real-world data are carried out under laboratory conditions with the use of a Karmin2 stereo camera (Nerian’s 3D stereo camera, baseline 25 cm).
- 13 September 2022
- Published by Pleiades Publishing Ltd in Programming and Computer Software
- Vol. 48 (5) , 301-311
Object Recognition and Coordinate Referencing of an Autonomous Underwater Vehicle to Objects via Video Stream
This paper is devoted to the important problem of subsea infrastructure inspection using autonomous underwater vehicles (AUVs). The accomplishment of the inspection mission requires high accuracy of AUV coordination with respect to objects, which is not always provided by standard hydroacoustic equipment. That is why we propose an approach based on stereo image processing that can provide submeter accuracy of AUV coordination required under subsea conditions. In the framework of a unified approach based on the use of an a priori formed point model of an object and the application of a structural coherence criterion, we propose and analyze several methods for recognition of underwater objects and coordinate referencing of the AUV to these objects. As a geometric model of an object, we consider its representation based on characteristic points, which determines the spatial structure of the object. In addition to the standard method for object model construction from preliminary measurements, a new method is proposed, which is based on automated technique of model generation from images offline. The proposed object recognition methods use the structural coherence criterion to match 3D point clouds with object models. The 3D point clouds are formed from stereo images captured by a camera using visual navigation. Feature points are generated and matched using the SURF detector and Harris corner detector. To improve the reliability of object identification, we propose joint processing of source images with their vectorized forms. The use of line segments obtained by vectorization significantly increases the number of identified characteristic points when matching a 3D point cloud with a model. Based on the identified points of an object, the matrix of AUV coordinate referencing to this object is computed. The efficiency of the considered methods is estimated and compared. In the computational experiments with model scenes, a virtual geometric model of a distributed subsea production system is used. The experiments on real-world data are carried out under laboratory conditions with the use of a Karmin2 stereo camera (Nerian’s 3D stereo camera, baseline 25 cm).
- Open Access
- 21 September 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (9) , 1038
Method for the Coordination of Referencing of Autonomous Underwater Vehicles to Man-Made Objects Using Stereo Images
The use of an autonomous underwater vehicle (AUV) to inspect underwater industrial infrastructure requires the precise, coordinated movement of the AUV relative to subsea objects. One significant underwater infrastructure system is the subsea production system (SPS), which includes wells for oil and gas production, located on the seabed. The present paper suggests a method for the accurate navigation of AUVs in a distributed SPS to coordinate space using video information. This method is based on the object recognition and computation of the AUV coordinate references to SPS objects. Stable high accuracy during the continuous movement of the AUV in SPS space is realized through the regular updating of the coordinate references to SPS objects. Stereo images, a predefined geometric SPS model, and measurements of the absolute coordinates of a limited number of feature points of objects are used as initial data. The matrix of AUV coordinate references to the SPS object coordinate system is computed using 3D object points matched with the model. The effectiveness of the proposed method is estimated based on the results of computational experiments with virtual scenes generated in the simulator for AUV, and with real data obtained by the Karmin2 stereo camera (Nerian Vision, Stuttgart, Germany) in laboratory conditions.
- 21 September 2021
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 9 (9) , 1038
Open AccessMethod for the Coordination of Referencing of Autonomous Underwater Vehicles to Man-Made Objects Using Stereo Images
The use of an autonomous underwater vehicle (AUV) to inspect underwater industrial infrastructure requires the precise, coordinated movement of the AUV relative to subsea objects. One significant underwater infrastructure system is the subsea production system (SPS), which includes wells for oil and gas production, located on the seabed. The present paper suggests a method for the accurate navigation of AUVs in a distributed SPS to coordinate space using video information. This method is based on the object recognition and computation of the AUV coordinate references to SPS objects. Stable high accuracy during the continuous movement of the AUV in SPS space is realized through the regular updating of the coordinate references to SPS objects. Stereo images, a predefined geometric SPS model, and measurements of the absolute coordinates of a limited number of feature points of objects are used as initial data. The matrix of AUV coordinate references to the SPS object coordinate system is computed using 3D object points matched with the model. The effectiveness of the proposed method is estimated based on the results of computational experiments with virtual scenes generated in the simulator for AUV, and with real data obtained by the Karmin2 stereo camera (Nerian Vision, Stuttgart, Germany) in laboratory conditions.