81 results about "Underwater vision" patented technology

The invention discloses an underwater vision-inertia-acoustic odometer positioning method fused with a DVL, and belongs to the technical field of robot navigation positioning. According to the method, firstly, an underwater image acquired by a camera and carrier motion data acquired by an IMU and a DVL are used as input information to carry out time alignment and space coordinate system conversion; performing feature point extraction on the image to construct a visual re-projection residual error, and dynamically adjusting a weight ratio of visual information based on the number of feature points and the re-projection residual error; calculating IMU data increment between adjacent frames based on pre-integration to construct an inertial residual error; calculating the displacement change between image frames according to the speed information measured by the DVL to construct a DVL residual error; establishing a nonlinear least square optimization function based on Bayesian maximum posteriori estimation; vision, inertia and acoustic speed measurement data are fused at the rear end through a sliding window mechanism, a multi-constraint joint optimization model is constructed, and the robustness and accuracy of a vision-inertia-acoustic odometer system in the underwater environment are improved.

The invention discloses a monocular and binocular cooperative localization and mapping method and device for underwater refraction compensation, and the method comprises the steps: extracting checkerboard angular points, compensating an underwater light path through employing a two-time vector correction model based on a Snell law, and precisely calibrating the internal and external parameters of a binocular camera. According to the method, an underwater real light path is effectively restored, and calibration errors caused by medium refraction are remarkably reduced. Then epipolar correction is performed on the corrected left and right images, so that the geometric consistency of stereo matching is ensured; and finally, monocular and binocular poses are fused, and seven-degree-of-freedom similarity transformation global alignment is applied, so that the problem of monocular scale uncertainty is effectively solved, and high-precision and high-robustness three-dimensional mapping is realized by means of binocular real scale introduction. Key links such as camera pre-calibration, refraction compensation, image correction, monocular tracking, binocular depth measurement, scale alignment and the like are connected in series to form an integrated process, so that the underwater vision positioning and mapping precision is improved.

The invention discloses an underwater vision sharpening method based on a polarization information guide diffusion model, and belongs to the technical field of underwater image processing. The method comprises the following steps: constructing an underwater polarization image data set under natural conditions and laboratory conditions; constructing an underwater vision clearness network based on a polarization information guide diffusion model, wherein the underwater vision clearness network comprises a serial conditional diffusion process, a cross-modal enhancement network and a conditional denoising network; and training the underwater vision sharpness network by using the underwater polarization image data set, and outputting a clear underwater image based on the trained underwater vision sharpness network. The underwater image sharpening method can effectively avoid the problem of imaging defects caused by an existing underwater image sharpening method under the condition of high turbidity, can restore a turbid area while removing color cast, improves the underwater image quality, and has effectiveness and robustness.

The invention belongs to the technical field of bolt remote operation, and discloses a reactor internal control rod guide cylinder bolt remote loosening and grabbing device which comprises a tool rotating positioning seat, and a bolt loosening and grabbing tool and an underwater vision auxiliary positioning module which are arranged on the same circumference are installed on the tool rotating positioning seat. And the distance between the circumference diameter and the axis of the control rod guide cylinder is equal to the diameter of the guide cylinder bolt. A bolt loosening and grabbing tool, an underwater vision auxiliary positioning module, guide cylinder bolts and a bolt locking cap are all arranged on the circumference of the same size and form a 90-degree position relation with one another, when the underwater vision auxiliary positioning module is aligned with a certain guide cylinder bolt through the underwater vision technology, the current circumferential position is set to be zero, and the position of the guide cylinder bolt is adjusted to be zero. When the bolts are loosened, the grabbing tool completes initial position calibration, and the positions of all the bolts can be accurately found by rotating the encoder on the positioning seat through the tool.

The invention relates to the technical field of underwater visual perception and intelligent detection, and provides a multi-stage feature fusion detection method for a low-illumination underwater target, and the method comprises the steps: obtaining an underwater low-illumination image; the low-illumination image is input to an illumination estimation module, the image is decomposed based on the Retinex theory, an illumination image is extracted, and the low-illumination image and the illumination image are fused pixel by pixel to generate an enhanced input image; inputting the enhanced input image into an image enhancement module for feature extraction and reconstruction; and mapping the image subjected to feature extraction and reconstruction into an image format to obtain a final enhanced result image. According to the invention, the problems of high redundancy interference and low robustness in the prior art are solved.

The invention discloses a digital twinning-based hydrodynamic model display method, system and device and a storage medium, and the method comprises the steps: obtaining a simulation result of a hydrodynamic model from local storage or network data service, and storing the simulation result in a data structure of a digital twinning system; a water body three-dimensional model is generated through the grid Shp file, vertex flow field and water level data are calculated based on a model simulation result, and after normalization, the vertex flow field and water level data are mapped to a color channel and vertex height of the water body three-dimensional model; a water surface dynamic effect is enhanced by adopting a water surface ripple normal mapping and flow velocity color mapping, and PostProcessVolume is created to simulate interface refraction and underwater visual effects of the water surface and air. The three-dimensional flow field and water level change of the hydrodynamic model can be displayed, visualization of underwater simulation results is supported, and the sense of reality of the flow effect is improved; and in combination with network data service and a local file access mode, the data loading and updating speed is increased, and the method is suitable for various data access environments.

The invention discloses an underwater visual positioning method based on a deep learning visual inertial odometer. The method comprises the following steps: constructing a system comprising a deep learning visual odometer model and a nonlinear optimization rear end; the method comprises the following steps: acquiring underwater video frames through an underwater robot provided with a monocular camera, training a model, processing the underwater video frames to be positioned through the trained model, outputting successfully associated feature point information, issuing the feature point information through a communication interface, and carrying out nonlinear optimization on node data of a rear-end subscription communication interface. And the pose of the monocular camera is output after processing, and underwater visual positioning is realized. According to the method, deep learning is introduced into feature point extraction and matching, so that sufficient matching feature point position information can be obtained in an underwater weak texture and unstable illumination environment, a nonlinear optimization loss function can be converged more quickly, and more accurate camera pose information is obtained; and the better visual positioning capability of the underwater mobile robot can be realized.

The invention provides a pseudo-supervised diffusion type underwater image enhancement method based on cross-modal semantic guidance, and the method comprises the following steps: obtaining an original degraded image and an actual reference picture of a UIEB, inputting the original degraded image into a multi-modal large model LLaVA to generate a semantic prompt, and selecting a plurality of different existing underwater enhancement methods, the method comprises the following steps: respectively obtaining a plurality of groups of enhanced images, integrating the enhanced images and semantic prompts into image-text pairs, inputting the image-text pairs into a Zip-CLIP model, calculating the similarity of the image-text pairs to generate a plurality of groups of similarity heat maps, inputting the similarity heat maps and high-order semantic information into a special convolutional neural network architecture, generating a pseudo tag as a weak supervision signal for diffusion model training, and carrying out diffusion model training. And a final enhancement result is obtained. According to the method, through the characteristics of cross-modal semantic alignment and gradual reconstruction of the diffusion model, the image detail reduction and structure retention capability is remarkably improved, a more reliable visual basis is provided for an underwater visual task, and theoretical innovation and practical values are both achieved.

The invention belongs to the technical field of underwater vision measurement, and relates to an underwater binocular vision system refraction parameter self-calibration method, which comprises the following steps of: firstly, constructing a space equation containing a water body refractive index, a refraction interface normal vector, an interface distance and a light path coefficient based on a Snell law; constructing a generalized state vector including an environment parameter, a structure parameter and a path parameter; a system residual equation is established by using different-plane light intersection constraint of binocular vision, and nonlinear iterative least square solution is carried out by constructing a generalized Jacobian matrix so as to realize adaptive calibration of an underwater vision system; according to the method, on the premise that water body parameters do not need to be predicted and high-precision mechanical calibration is not needed, the water body refractive index and the system structure parameters are synchronously solved, self-adaptive calibration of the underwater vision system is achieved, and the three-dimensional measurement precision and robustness in the complex water environment are remarkably improved.

The invention provides a calibration device and method of an underwater vision measurement system. The calibration device of the underwater vision measurement system comprises a base, a standard object movement mechanism, a vision measurement system movement mechanism, a standard object, a vision measurement system, a water tank, a control box and a control terminal. The water tank is located under the base and used for containing liquid to form an underwater environment, and the internal space is a calibration space. The base is composed of a lower structure, a supporting column and an upper structure, and the lower structure is used for being connected with the ground. The supporting column is connected between the lower structure and the upper structure. The standard object movement mechanism and the vision measurement system movement mechanism are arranged on the upper structure in parallel. According to the underwater calibration device, the water tank is used for simulating the underwater environment, and the dual-motion mechanism, the control box, the control terminal and other devices are matched with one another, so that the problems that an existing underwater calibration device cannot perform large-range multi-pose calibration, cannot be linked with an underwater vision measurement system and cannot simulate the underwater special environment are solved.

The invention relates to a trailing suction dredger excavation depth measuring method and system, and the method comprises the steps: obtaining multi-mode sensor data of a water area bottom layer, the multi-mode sensor data comprising multi-beam sonar data, laser scanning data and underwater visual image data; carrying out dynamic identification on the multi-modal sensor data, and generating a bottom layer feature identification result of the water area; utilizing the real-time water flow and sediment flow model to predict the flow trend of the bottom sediment of the water area, and generating a water flow prediction result; and dynamically adjusting a depth measurement strategy based on the underlying feature recognition result and the water flow prediction result, and optimizing measurement data in real time through a data correction algorithm in the measurement process to generate a depth measurement result. The method has the effect of improving the digging depth measurement precision of the trailing suction hopper dredger.

The invention belongs to the technical field of computer vision and ocean detection, and discloses an underwater target detection and tracking system, which comprises an underwater image enhancement module used for preprocessing an original underwater video image and outputting an enhanced image; the improved YOLOv11 target detection module comprises an improved YOLOv11, and the improved YOLOv11 is adopted to receive the enhanced image so as to position the underwater target in real time and output a target bounding box; and the target tracking module based on Transform is used for receiving the video clip of the bounding box and extracting the spatial-temporal characteristics, and realizing target association and trajectory prediction based on the target bounding box and the spatial-temporal characteristics. The invention also discloses an underwater target detection and tracking method. According to the system and the method provided by the invention, the accuracy and the robustness of underwater vision tasks including target detection and tracking can be remarkably improved on the premise of ensuring the real-time performance.

The invention discloses an underwater robot visual positioning method, device and equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring an original image acquired by a camera, and preprocessing the original image to obtain a processed image; determining a target depth map corresponding to the processed image by using depth estimation; positioning and removing a moving target from the processed image through a dynamic object detection model to obtain a static scene image; the dynamic object detection model is a neural network model obtained by training underwater images in advance; and estimating the pose of the underwater robot in real time through a synchronous positioning and mapping algorithm based on the target depth map and the static scene image, constructing a dense point cloud map, and updating a pose map of the underwater robot. And accurate underwater visual positioning can be realized with low cost.

The application discloses a kind of big visual field image side telecentric underwater visual docking imaging optical systems, the optical system includes in sequence: spherical cover window, front group lens, variable diaphragm, rear group lens and filter;Front group lens includes in sequence: front group first lens, front group second lens, front group third lens, front group fourth lens;Rear group lens includes in sequence: rear group first lens, rear group second lens, rear group third lens, rear group fourth lens;Variable diaphragm is located between front group fourth lens and rear group first lens;Object side imaging light beam is imaged on strobe camera target surface in sequence through spherical cover window, front group lens, variable diaphragm, rear group lens and filter.The application has big visual field, short focal length, variable F number and image side telecentricity and the like characteristics, clear imaging is realized by rear group focusing and variable F number, can be used for the close-range underwater visual docking recovery of cross-domain aircraft, ensure that imaging is clear during docking process, and the position solution error caused by image side focusing can be eliminated.

The present invention discloses an underwater cable-tethered beacon long-distance optical navigation system and method, comprising: a blue-green beacon array connected to a power control in a control cabin to form a cable-tethered optical navigation node; the control cabin and the optical navigation node are mounted on a cable-tethered branch to form a map navigation landmark; a submarine cable is connected to onshore and underwater base stations; an underwater camera and a visual recognition module in an underwater robot cabin form an underwater visual recognition system, which receives camera video signals and outputs navigation information to the underwater robot controller; and an optical long-distance navigation algorithm based on the optical navigation node, which obtains navigation information for SLAM positioning through node light source feature extraction, heading calculation, and data fusion. The present invention meets the large-scale, long-distance navigation requirements of underwater robots, has strong adaptability and good stability, and is suitable for long-term navigation and positioning of underwater robots in cable-tethered systems.

The present invention provides a 3D reconstruction method for underwater damage of marine equipment based on vision and IMU fusion. The method includes the steps of performing, in an underwater environment, internal parameter calibration of the left and right cameras of a stereo camera and extrinsic parameter calibration between the left and right cameras of the stereo camera and a platform IMU; calibrating the extrinsic parameter matrices of the drive IMU coordinate system and the laser sensor coordinate system on each axis of the drive system; identifying and roughly locating the damaged area based on the 3D reconstruction of the underwater vision; planning an optimal path for the underwater mobile platform, performing local obstacle avoidance based on the 3D reconstructed point cloud, and controlling the underwater mobile platform to move near the damaged area; planning a trajectory for a drainage system and draining water using the drainage system; and determining the laser position of a laser sensor using drive IMU data to realize a precise 3D reconstruction of the damaged area based on the laser sensor data. This method provides a highly accurate 3D reconstruction of the damaged area, assisting other equipment in autonomous repair and improving the work efficiency of the marine equipment.

The invention relates to the technical field of underwater docking, and discloses an AUV (Autonomous Underwater Vehicle) underwater dynamic docking visual positioning method using a vector line light source, which comprises the following steps: constructing a visual marker consisting of the vector line light source consisting of four groups of lasers with changeable emission angles; obtaining the relative distance between the docking AUV and the target AUV, determining an emission angle adjustment rule based on the relative distance, and adjusting the emission angles of the four groups of lasers according to the rule; acquiring a reference image of the vector line light source by using a camera carried by the docking AUV, and performing adaptive enhancement on the reference image by taking a relative distance as an adaptive condition; performing information completion on the enhanced image, and extracting key points from the enhanced image after information completion; and carrying out relative position and attitude calculation on the extracted key points by using a PNP algorithm to obtain a final result of underwater visual positioning. According to the method, the underwater dynamic docking visual positioning precision is improved, and the docking dynamics and the fault-tolerant rate are improved in dynamic docking.

The invention relates to the technical field of computers, and discloses an underwater vision closed-loop detection method, device and equipment and a medium, global feature information and local feature information of an obtained key frame image are extracted at the same time through a convolutional neural network, and the local feature information of the key frame image is extracted on the basis of the global feature information of the current key frame. Quantifying global similarity and time relevance between the current key frame and other key frames to construct a closed-loop database; meanwhile, on the basis of global feature information and inter-frame adjacency characteristics of the current key frame, a closed-loop candidate frame is searched from a closed-loop database, the closed-loop candidate frame is verified according to local feature information of the current key frame and local feature information of the closed-loop candidate frame, and when verification is passed, the current key frame is verified; taking the closed-loop candidate frame as a target closed-loop frame of the current key frame; the closed-loop detection process is constrained through image similarity, time relevance and inter-frame adjacency, and the underwater vision closed-loop precision and recall rate are improved.

The application discloses a method for constructing an underwater static perception model based on terrain fine grid division, and belongs to the underwater visual perception field. The underwater terrain data is finely divided into grids, and the underwater submersible is mapped to the corresponding grid position, so that the static perception model is constructed. In combination with the lake surrounding environment, the lake bottom terrain and the safe navigation depth, a near-non-safe area grid set is constructed, the future grid where the underwater submersible is located is calculated in real time, and if there is an intersection with the non-safe area grid set, an alarm is sent. The model can accurately perceive the underwater static environment and guarantee the safe operation of the underwater submersible.

The invention provides an implicit entropy learning-based underwater visual image efficient reconstruction method and system, and the method comprises the steps: obtaining an input image which is an original image collected by an underwater robot; performing feature extraction on the input image to obtain a high-latitude feature, extracting and obtaining an auxiliary feature, and performing quantization operation on the high-latitude feature and the auxiliary feature; the auxiliary quantization features are coded to generate an auxiliary feature code stream, the auxiliary quantization features are obtained through decoding and recovery, potential context information is decoded and extracted, and an implicit entropy modeling module fuses the context information into distribution prediction of the high-latitude quantization features; encoding the high-latitude quantitative features to generate a high-latitude feature code stream; and decoding and restoring the high-latitude feature code stream to obtain a high-latitude quantization feature, and performing feature decoding on the high-latitude quantization feature by using a decoder to obtain a reconstructed image. According to the method, the problems of insufficient compression performance, poor reconstruction quality and the like of a traditional image compression algorithm in an underwater complex environment can be solved.

This disclosure relates to a method and system for underwater calibration of composite polarization states based on an equal focal length refraction model. The method includes: approximating the incident angle of light under small-angle conditions by simultaneously applying geometrical optics imaging equations and Snell's law of refraction, obtaining the transformation relationship between the coordinates of the underwater imaging point and the coordinates of the theoretical imaging point in air, and establishing an equal focal length refraction mathematical model for the underwater camera and projector; designing a composite polarization state encoded sinusoidal projection calibration pattern based on this model; utilizing the polarized light projection characteristics, encoding the horizontally polarized light of the green channel of the calibration pattern into horizontal cosine fringes, and the vertically polarized light of the blue channel into vertical sine fringes; superimposing the cosine and sine fringes to generate two sets of orthogonal polarization state fringe patterns, and performing phase calculation and reprojection error optimization based on the equal focal length refraction mathematical model to achieve parameter calibration. This method can significantly improve the calibration accuracy and efficiency of underwater visual measurements.

The invention provides an unmanned monitoring ship based on sonar vision meteorological water quality fusion and a monitoring method thereof, a multi-beam sonar and an underwater camera are used to collect an acoustic image and a visual image of an underwater target, and an embedded main control board is used to realize synchronous registration and fusion of sonar echoes and images. Target detection and recognition are completed based on a deep learning model; meanwhile, a composite water quality probe, an anemorumbometer, a temperature and humidity sensor and an air pressure sensor are used for collecting water body parameters and meteorological parameters in real time to assist in analyzing the water quality change trend; the communication module transmits fusion data to an upper computer in real time through a 5G network, and remote monitoring and intelligent decision making are achieved. According to the invention, through heterogenous information fusion of sonar and underwater vision, the penetrating power of acoustic detection and the high resolution of visual perception are considered, and high-precision detection of fish data in a turbid environment is realized; according to the cross-modal fusion network based on Transform, the target recognition rate and the positioning precision in a complex environment are improved.

This invention discloses an improved YOLO26 underwater target detection method with joint image enhancement. A dedicated underwater image enhancement unit is designed as a pre-task, strengthening image feature representation through a dynamic histogram stretching module and an attention mechanism to output high-quality enhanced images. The YOLO26 network structure is improved by designing a multi-frequency feature reconstruction module and an optimized detection network, achieving collaborative optimization of upstream and downstream tasks between the enhancement and detection units. This method optimizes image quality through enhanced downsampling and upsampling paths. The improved YOLO26 detection network achieves efficient detection and accurate localization of large, medium, and small underwater targets. While ensuring real-time performance and lightweight design, it significantly improves target detection performance under complex underwater conditions, adapting to underwater visual perception scenarios such as underwater search and rescue, marine exploration, and underwater equipment inspection. It provides a practical, generalizable, and easily deployable technical solution for underwater intelligent visual inspection.

The present invention discloses an underwater visual positioning method based on deep learning visual inertial odometry. The method includes: constructing a system including a deep learning visual odometry model and a non-linear optimization backend; obtaining underwater video frames through an underwater robot equipped with a monocular camera and training the model, then processing the underwater video frames to be positioned through the trained model, outputting the information of successfully associated feature points and publishing them through a communication interface, and the non-linear optimization backend subscribing to the node data of the communication interface, processing and outputting the pose of the monocular camera to achieve underwater visual positioning. The method of the present invention can obtain sufficient position information of matching feature points in the underwater weak texture and unstable lighting environment by introducing deep learning in feature point extraction and matching, enabling the non-linear optimization loss function to converge more quickly, thereby obtaining more accurate camera pose information and achieving better visual positioning ability of underwater mobile robots.

The utility model discloses an underwater vision inspection robot integrated with a suspension balance stabilizing device, which relates to the technical field of inspection robots and comprises a machine body and a balance component, a main water tank is mounted on the inner side of the machine body, and the balance component for improving stability is arranged at the upper end of the main water tank. And the balance assembly comprises a power box, a mounting groove, a first telescopic corrugated pipe, a balance water tank and a water passing pipe, the mounting groove is formed in the power box, the outer side of the power box is connected with the first telescopic corrugated pipe, the end of the first telescopic corrugated pipe is connected with the balance water tank, and the water passing pipe is mounted at the lower end of the side edge of the balance water tank. According to the underwater vision inspection robot integrated with the suspension balance stabilizing device, movement of the balance water tanks is controlled through stretching and retracting of the electric push rods in the first telescopic corrugated pipe, the annularly-distributed balance water tanks convey different water amounts in the water passing pipe, suspension balance of the robot body is assisted by the four balance water tanks, and the use stability of the robot body is improved.

The application provides an underwater visual image efficient reconstruction method and system based on implicit entropy learning, comprising: acquiring an input image, the input image being an original image collected by an underwater robot; performing feature extraction on the input image to obtain high-latitude features, extracting auxiliary features, and performing quantization operation on the high-latitude features and the auxiliary features; encoding the auxiliary quantized features to generate an auxiliary feature code stream, decoding and restoring the auxiliary quantized features, decoding and extracting potential context information, and fusing the context information into distribution prediction of the high-latitude quantized features by an implicit entropy modeling module; encoding the high-latitude quantized features to generate a high-latitude feature code stream; decoding and restoring the high-latitude feature code stream to obtain high-latitude quantized features, and performing feature decoding on the high-latitude quantized features by using a decoder to obtain a reconstructed image. The application can solve the problems of insufficient compression performance and poor reconstruction quality of traditional image compression algorithms in underwater complex environments.

The application discloses a kind of underwater visual positioning methods of illumination robustness based on prior information, belong to underwater visual positioning technical field.The present application focuses on underwater visual positioning research, for the poor stability of underwater visual positioning under the condition of severe illumination change, a kind of underwater visual positioning method based on prior information is designed, the physical properties of environmental brightness information and cooperative target are fully utilized, by screening interest area, dynamic threshold and other methods, effectively solve the problem of target missed detection, false detection and other problems caused by high image background brightness or uneven brightness, improve the segmentation accuracy of target contour, so as to optimize the calculation accuracy of target image coordinates and spatial coordinates;In underwater experiment, the method of the application is verified, reliable detection and accurate positioning of UUV target are realized all day long, all weather, and the robustness of the method of the application to environmental brightness change is verified.

The invention relates to the technical field of image processing, in particular to an underwater image enhancement method based on a color channel interactive attention mechanism. Comprising the following steps: performing color channel separation on an original underwater image to obtain R, G and B single-channel images; extracting sparse features of each channel through a sparse feature estimation module; realizing cross-channel feature interaction and information fusion by using a channel interaction attention module; fusion parameters are generated through an environment sensing module, and the interaction feature fusion effect is optimized; and reconstructing the fused features into corresponding channel images, and splicing to obtain an enhanced underwater image. According to the method, the color balance, the structure consistency and the detail retention capability of the underwater image are effectively improved, and the method is suitable for underwater vision application scenes such as underwater robots and ocean exploration.

This invention discloses an underwater visual-inertial odometry method based on dynamic sparse attention, belonging to the fields of computer vision and robot navigation. An initial visual feature sequence is obtained from two adjacent underwater images. The dark channel map of the underwater image is calculated and encoded as a transmittance-aware embedding. The transmittance-aware embedding is fused with the position encoding to form a 3D position embedding. The 3D position embedding is added to the initial visual feature sequence and input into a visual encoder composed of N stacked dynamic sparse attention modules, outputting a visual feature sequence. An inertial feature sequence is introduced, and a bidirectional cross-attention mechanism is used to achieve deep interaction and alignment between visual and inertial features. An adaptive gating mechanism is used for weighted fusion, and finally, a regression network is used to predict the six-DOF pose. This invention effectively improves the robustness and accuracy of pose estimation in complex underwater environments by introducing physically prior-guided 3D position embedding, dynamic sparse attention, and deep adaptive fusion.