Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

116 results about "Side-scan sonar" patented technology

Side-scan sonar (also sometimes called side scan sonar, sidescan sonar, side imaging sonar, side-imaging sonar and bottom classification sonar) is a category of sonar system that is used to efficiently create an image of large areas of the sea floor.

Underwater historical relic integrated detector based on remote operated vehicle (ROV) platform

InactiveCN106814408AAccurate real-time detectionEfficient real-time detectionTransmission systemsSatellite radio beaconingTransceiverMagnetic anomaly
The invention discloses an underwater cultural relic integrated detection device based on an ROV platform, which includes a deck device and an underwater integrated detection device, and belongs to the technical field of marine detection. Deck installations include the mother ship, GPS system, ultra-short baseline transceiver and ROV console. The underwater detection device integrates magnetometer, multi-beam sonar, side-scan sonar, high-definition camera, shallow stratum profiler (shallow profiler) and ultra-short baseline acoustic beacon on the ROV platform. The magnetometer is used to measure the magnetic anomalies in the detection area and roughly determine the location of the underwater cultural relics. The shallow profiler is used to describe the cross-sectional structure of the underwater strata, which is used to detect the location of cultural relics buried below the mud surface. Multi-beam sonar and side-scan sonar are used to provide high-resolution underwater acoustic images, combined with high-definition cameras to detect the location of cultural relics on mud surfaces. The device of the invention integrates and fuses various sensor information, realizes the visualized and refined real-time detection of underwater cultural relics, and improves the detection efficiency of underwater cultural relics archaeological operations.
Owner:ZHEJIANG UNIV

Underwater side-scan sonar collecting and releasing device arranged under boat bow deck

The invention relates to an underwater side-scan sonar collecting and releasing device arranged under a boat bow deck. The device is characterized in that the boat bow is provided with a slot so as to be convenient for arranging the sonar on the boat bow, the slot can also be used for collecting an underwater sonar, and after the sonar is collected, the sonar can be covered; the sonar is arranged on a collecting and releasing rod, and the collecting and releasing rod is driven through a transmission device comprising an electromotor, a speed reducer, a stainless steel chain, and the like to rotate so as to send the sonar into water; after the sonar reaches a boat bow working position vertical to the bottom of the boat, an electrical push rod pushes a positioning pin to insert into a positioning hole so as to improve the rigidity of the sonar collecting and releasing rod; and the rotation angle of collecting and releasing the sonar is measured by an encoder connected to a rotation shaft. The imaging quality of the sonar arranging device is high, and the device can realize the quick collection and release of the underwater sonar; after the sonar is placed, the positioning pin is inserted, which can effectively guarantee the working precision of the sonar; the sonar can be guaranteed to be correctly collected and released through the encoder; and by integrating the three points, the detection precision of the sonar can be effectively and greatly improved, and the device is convenient to use.
Owner:SHANGHAI UNIV

Underwater pipeline detector based on underwater robot

The invention relates to an underwater pipeline detector based on an underwater robot. The underwater pipeline detector comprises an overwater control device and an underwater detection device, wherein the overwater control device is connected with the underwater detection device through an umbilical cable; the underwater detection device is arranged on the underwater robot, and is used for detecting position and burial depth of a seabed pipeline; and the overwater control device is used for controlling operation of the underwater detection device. Compared with the prior art, the underwater pipeline detector solves the difficulty that the position and the burial depth of the pipeline cannot be detected by means of an acoustic wave pipeline instrument detection method, multi-beam side-scan sonar detection, magnetic detection, ROV camera shooting, diving photographing by a diver and the like in a deep water region and under a turbid condition. Through adopting the method of combining the overwater equipment with the underwater equipment, and regarding ROV as a carrier, the underwater pipeline detector enters the deep water region, carries out non-destructive detection by adopting an electromagnetic induction principle, and overcomes the pipeline detection difficulties of small pipe diameter, sludge and sand layer coverage and turbid water region.
Owner:GUANGDONG KENUO SURVEYING ENG CO LTD

Automatic ship draught detection system based on multi-beam side-scan sonar technology

The invention relates to an automatic ship draught detection system based on the multi-beam side-scan sonar technology. The automatic ship draught detection system comprises an underwater sonar scanning subsystem, a sonar signal processing subsystem and a master control subsystem. The underwater sonar scanning subsystem comprises a sonar transducer and a rotating motor, wherein the sonar transducer is provided with a 360-degree rotating shaft, and the rotating motor is used for driving the sonar transducer to rotate. The sonar signal processing subsystem comprises a watertight electronic cabin and a digital signal processing module located in the watertight electronic cabin, and data and command transmission between the sonar signal processing subsystem and the master control subsystem is carried out through a watertight cable. The rotating motor of the underwater sonar scanning subsystem is fixed in the watertight electronic cabin and connected with the digital signal processing module. The master control subsystem comprises a master control computer and a power supply unit, and display and control software of the automatic ship draught detection system operates on the master control computer. The automatic ship draught detection system has the advantages of being small in investment, easy to install and maintain and high in measuring accuracy, and the measurement process is convenient and fast to carry out and efficient.
Owner:STATE GRID CORP OF CHINA +2

High-frequency closely-spaced piezoelectric film hydrophone array and production method thereof

The invention relates to the technical field of underwater sound transducers, in particular to a high-frequency hydrophone array applicable to underwater phased array camera and a production method thereof, and solves the technical problems that a large cardinal number of high-frequency hydrophone array elements need to be accurately located and disposed in a limited array area and charge sensed by efficient coupling array elements is required to pick up and receive high-frequency weak underwater sound signals. A piezoelectric device PVDF (polyvinylidene fluoride) film, a rigid backing and PCBs (printed circuit board) are jointed; the high-frequency PVDF hydrophone backing is made of copper to increase sensitivity; multiple layers of PCBs are used as a substrate; a large number of array element backings are integrally pre-processed; the array element backing clusters are positioned and fitted to the PCB substrate; the backing units are separated by secondary processing; decoupling bars are added among the separated units; the piezoelectric film is adhered to form an array; finally, watertight sealing is performed to form the high-frequency piezoelectric film hydrophone array. The high-frequency hydrophone array is applicable to high-frequency sonar receiving arrays for imaging sonar, multi-beam sonar, side-scan sonar and the like.
Owner:THE 715TH RES INST OF CHINA SHIPBUILDING IND CORP

Side-scan sonar image feature extraction method based on full convolutional neural network

The invention provides a side-scan sonar image feature extraction method based on a full convolutional neural network. The method comprises the following steps: carrying out the data augmentation through an original sonar image, and set needed by model training and testing; manually labeling the edge area of the submarine topography of each image in the sample set, distinguishing a target and a background, and obtaining a model training and testing label graph; an FCNs model is constructed; inputting the submarine topographic map and the corresponding label map into a network, training the network by adopting a small-batch gradient descent method of a driving quantity item, and storing an optimal network model; comparing convergence and stability of the network under a random gradient descent method and a small-batch gradient descent method; and extracting terrain edge contour features, outputting a feature extraction result, and carrying out qualitative evaluation on the result. According to the method, complex preprocessing is not needed, and the sonar feature extraction method is high in speed, high in efficiency and high in speckle noise resistance; the performance of the network is improved, and the convergence and stability of each network model of the FCNs are ensured.
Owner:HARBIN ENG UNIV

Method using side-scan sonar to measure tonnage of ship

The invention relates to a method using a side-scan sonar to measure the tonnage of a ship. The method comprises the following steps: when a photoelectric sensor detects that ship passing signals exist, a tow fish arranged under water is started; the tow fish scans the side of a measured water area to acquire an underwater acoustic image of an underwater part of the ship; the sailing speed and the passing time of the ship are simultaneously measured, and the length of a ship body is calculated according to the product of the ship speed and the passing time; an underwater acoustic image of a measured area is acquired by a computer connected with the tow fish; then image processing is conducted on the underwater acoustic image of the measured area, so as to extract an acoustic shielding shadow of the measured ship; the draft depth of the ship body and the width of the ship body below a water line are acquired according to a combination of a projection relationship and measured environmental parameters; the total tonnage of the ship is calculated according to the length of the ship body, the draft depth, the width of the ship body below the water line, and a square model coefficient of the ship marked on a ship-borne certificate; and the difference between the total tonnage and the net tonnage of the ship marked on the ship-borne certificate equals to the actual-load tonnage of the ship.
Owner:CHANGZHOU INST OF TECH

Automatic classification method of side scan sonar image targets based on transfer learning and depth learning

The invention belongs to the field of automatic recognition and classification of underwater targets, in particular to an automatic classification method of side scan sonar image targets based on transfer learning and depth learning. The method includes acquiring a conventional optical image data set with segmentation annotations; carrying out the contour segmentation by using the annotated imagescorresponding to each image in the data set; selecting a convolution neural network structure for training to obtain the source domain target classification network; fozening the parameters of the front part of the fully trained source domain target classification network, and setting the parameters of the back part of the classification network to the trainable state; continuing to train the setclassification network using the training set; when the training is complete, using the verification set to evaluate the performance of the classification network. The method uses the transfer learning method to transfer the convolution neural network trained with non-side scan sonar images, and pre-processes the source domain data set according to the similarity principle, so as to improve the transfer learning efficiency and prevent the negative transfer phenomenon.
Owner:HARBIN ENG UNIV

Method for processing navigation track of side scan sonar tow-fish based on navigation track line file

The invention discloses a method for processing navigation track of a side scan sonar tow-fish based on a navigation track line file, which comprises the following steps: firstly, extracting navigation track point coordinate information in the navigation track line file, adopting a Bessel's interpolation model to smoothly process the navigation track point coordinate information, fitting a practical navigation track of a tow-fish, then counting the number of the received scan lines when the tow-fish runs between adjacent navigation track coordinate points according to time information, and finally acquiring instantaneous coordinates when the tow-fish runs through equidistant interpolation. The method makes full use of the navigation track line file, simplifies the navigation track processing process, and effectively solves the problem of uneven scan line distribution due to unstable ship speed and asynchronous scanning and positioning. Simultaneously, the method can acquire good correcting effect on scan line intersection caused by the change of the progression direction of the tow-fish. The method for processing the navigation track of the sonar tow-fish can effectively eliminate various gaps generated during geographic coding of side scan sonar data so as to acquire clear and continuous submarine landform images.
Owner:ZHEJIANG UNIV

Target detection method of side scan sonar

The invention discloses a target detection method of a side scan sonar. The target detection method of the side scan sonar can effectively reduce an image noise and a small noise caused by factors such as scatter from water surface or water and furthermore has advantages of high processing efficiency and high detection accuracy. According to the target detection method, a weighted average template based on a 3*3 window is used for performing low-pass filtering on the image of the side scan sonar, thereby effectively eliminating a scattering noise caused by reasons of water surface scattering or in-water scattering in the image, and reducing processing stress and complexity for subsequent processing. Then a K means algorithm is utilized for classifying the pixels of the sonar image to a target kind and a shadow kind and generating two kinds of different images, thereby facilitating subsequent processing to the target and the shadow and improving processing efficiency. Furthermore a pyramid increase/reduction algorithm is used for eliminating the small noise in the image. Finally phony targets are further eliminated according to the area of a suspected target, the area of a corresponding suspected shadow and a ratio between the area of the suspected target and the area of the corresponding suspected shadow, thereby improving detection accuracy.
Owner:710TH RES INST OF CHINA SHIPBUILDING IND CORP

Underwater target rapid extraction method for side-scan sonar imaging

The present invention discloses an underwater target rapid extraction method for side-scan sonar imaging. The method can perform real-time analysis on a side-scan sonar image and quickly extract an underwater target. According to the method, adaptive non-linear complex diffusion model filtering is performed on a side-scan sonar image of which the multiplicative noises are prominent, so that a noise problem in the side-scan sonar image can be improved; the de-noised sonar image is pre-segmented, and the target region, seabed reverberation region and shade region of the side-scan sonar image are automatically determined; the contours of the pre-segmentation results are redefined, so that time for constantly re-defining an initial level set in level set model evolution can be decreased in a segmentation process; a variation level set model-based evolution and segmentation are performed on the target region and the shade region; and binarization is performed on a target to be extracted, clear segmentation results of the three regions are displayed for an operator. According to the underwater target rapid extraction method for the side-scan sonar imaging of the invention, target extraction is performed on a real-time side-scan sonar, and therefore, the method has the advantages of high detection real-time performance, high detection stability and high accuracy, provides a reliable guarantee for underwater detection and target tracking.
Owner:HOHAI UNIV CHANGZHOU

Construction control method for dimension stone deepwater precise throwing and filling

The invention provides a construction control method for dimension stone deepwater precise throwing and filling, and belongs to the field of construction of dimension stone deepwater throwing and filling. The method comprises the following steps that a throwing and filling ship achieves positioning through a mooring system and GPSes, the cable force of a cable system of the mooring system is detected in real time through a force measurement system, and a stranded cable of the mooring system is controlled so that the throwing and filling ship can be in position precisely; a transportation ship moors alongside and is connected with the throwing and filling ship in a binding manner, and dimension stone is transported to the throwing and filling ship; the underwater original foundation bed surface position is measured and recorded through a dimension stone throwing and filling measurement and control system, a chute system is used for carrying out throwing and filling on the dimension stone, the plane position and elevation of throwing and filling of the dimension stone are monitored and recorded in real time through the dimension stone throwing and filling measurement and control system, when the designed elevation of throwing and filling is achieved, throwing and filling are stopped, the stranded cable is controlled through the force measurement system so that the throwing and filling ship can move to the next ship position, and the above throwing and filling work is repeated; and after the throwing and filling work is finished, multiple beams and side-scan sonar are combined for remeasuring the construction result. The method is suitable for the working conditions of the high flow speed and the large water depth and can precisely control throwing and filling of the dimension stone.
Owner:NO 2 ENG CO LTD OF CCCC FIRST HARBOR ENG

Data-driving-based AUV (Autonomous Underwater Vehicle) undersea target search navigation system and method

The invention discloses a data-driving-based AUV (Autonomous Underwater Vehicle) undersea target search navigation system and method. The system comprises a task information processing module, a side-scan sonar, a target characteristic extraction module, a height gauge, a first-stage path generation module, a second-stage path generation module, a third-stage path generation module, an independentdecision-making module and an AUV actuating mechanism; the task information processing module receives task information and processes the task information in combination with a position state of an AUV to acquire dynamic grid chart coordinates; the first-stage path generation module generates a first-stage path point set; the side-scan sonar detects a sonar image; the target characteristic extraction module transmits coordinates of a target region to the second-stage path generation module to generate a second-stage path point set; height data measured by the height gauge are transmitted to the third-stage path generation module to generate a third-stage path point set; and finally, the independent decision-making module acquires an AUV path based on the three point sets and transmits theAUV path to the AUV actuating mechanism. The data-driving-based AUV undersea target search navigation system can search an undersea target and realize collision preventation of set-height navigationand can improve the undersea target search efficiency.
Owner:OCEAN UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products