CN-121995523-A - Underwater vehicle-oriented acousto-optic fusion detection method and system

CN121995523ACN 121995523 ACN121995523 ACN 121995523ACN-121995523-A

Abstract

The application provides an underwater vehicle-oriented acousto-optic fusion detection method and system, wherein the method comprises the steps of acquiring preliminary detection information of suspicious targets in an underwater region, and dynamically selecting a perception strategy according to the preliminary detection information; and carrying out cooperative processing on data from different detection loads based on the perception strategy, and continuously updating the detection information of the suspicious target through a processing result. According to the application, the underwater camera, the laser camera and the forward-looking sonar are integrated on the bow section of the aircraft to construct a multi-source load collaborative detection framework, the system firstly utilizes the wide-area coverage capacity of the forward-looking sonar to carry out comprehensive sweep on an underwater area, the preliminary position information of a suspicious target is quickly locked, and the perception strategy is dynamically adjusted according to the target distance. The method effectively solves the contradiction between limited distance of optical equipment and insufficient resolution of sonar equipment in the traditional underwater detection, and remarkably improves the target recognition accuracy and system robustness in complex water area environments.

Inventors

AN PING
Wang aobo
ZHOU TONGYU
DUAN ZHENGQI

Assignees

中国航天空气动力技术研究院

Dates

Publication Date: 20260508
Application Date: 20251211

Claims (10)

1. An underwater vehicle-oriented acousto-optic fusion detection method is characterized by comprising the following steps: Acquiring preliminary detection information of a suspicious target in an underwater area, and dynamically selecting a perception strategy according to the preliminary detection information; and carrying out cooperative processing on data from different detection loads based on the perception strategy, and continuously updating the detection information of the suspicious target through a processing result.
2. The method according to claim 1, wherein obtaining preliminary detection information of suspicious objects in the underwater region, and dynamically selecting a perception strategy according to the preliminary detection information specifically comprises: acquiring preliminary position information of a suspicious target in an underwater area by utilizing a forward-looking sonar carried by an aircraft, calculating to obtain a target distance according to the preliminary position information, and selecting and switching to an acousto-optic hybrid sensing mode of cooperative work of the forward-looking sonar and an underwater camera or a single load sensing mode of only forward-looking sonar work according to a comparison result of the target distance and a preset short-distance threshold; If the target distance is smaller than or equal to a preset short-distance threshold value, starting the acousto-optic hybrid sensing mode; and if the target distance is larger than the preset short-distance threshold value, starting the single load sensing mode.
3. The method according to claim 2, wherein the collaborative processing of data from different detection loads based on the sensing strategy and the continuous updating of the detection information of the suspicious object by the processing result specifically comprises: Under the acousto-optic hybrid perception mode, the underwater camera and the forward-looking sonar are utilized to carry out cooperative work, the image enhancement processing is carried out on the optical image acquired by the underwater camera, the object detection is carried out on the enhanced optical image, and an optical detection result is obtained; And in the single load sensing mode, detecting by using the forward-looking sonar, and updating the detection information of the suspicious target based on a detection result.
4. The method of claim 3, wherein the image enhancement processing comprises employing at least one of a dark channel prior defogging algorithm, a histogram equalization processing, or a depth learning based deblurring method.
5. A method according to claim 3, wherein the fusion weight determined by the dynamic weight distribution method is calculated according to the image quality weight, the distance weight and the target detection confidence weight; Wherein, the calculation formula is: Equation 1; Equation 2; Equation 3; Equation 4; Equation 5; Wherein w represents the fusion weight, Representing the corresponding coefficient of the coefficient, Representing the image quality weight, u representing the image quality threshold, An image quality evaluation index is indicated, The distance weight is represented as a function of the distance, And Representing the minimum and maximum weights of the distance weights respectively, Representing the distance adaptation coefficient, ‌ k representing the slope parameter, The distance is indicated by the distance between the two points, Representing the distance from the center point, And c represents the confidence level of the target detection result.
6. A method according to claim 3, wherein updating the target confidence level based on the fusion result comprises: The confidence of the successfully matched and fused target is increased by a preset reward value, the confidence of the unsuccessfully matched target is reduced by a preset penalty value, and the confidence value is constrained in the interval [0,1 ].
7. The method of claim 6, wherein the detection result includes three-dimensional position coordinates of the target, updated target confidence and target class information; The three-dimensional position coordinates are obtained by performing triangular positioning or coordinate fusion on successfully matched acoustic ranging information and the pixel positions of optical imaging.
8. An underwater vehicle-oriented acousto-optic fusion detection system, comprising: The dynamic perception control module is used for acquiring preliminary detection information of suspicious targets in the underwater area and dynamically selecting a perception strategy according to the preliminary detection information; And the multisource fusion detection module is used for carrying out cooperative processing on data from different detection loads based on the perception strategy, and continuously updating the detection information of the suspicious target through a processing result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program implementing the steps of the underwater vehicle oriented acousto-optic fusion detection method as claimed in any one of claims 1 to 7 when executed by the processor.
10. A computer-readable storage medium, wherein a program for implementing information transfer is stored on the computer-readable storage medium, and the program, when executed by a processor, implements the steps of the acousto-optic fusion detection method for an underwater vehicle according to any of claims 1 to 7.

Description

Underwater vehicle-oriented acousto-optic fusion detection method and system Technical Field The invention relates to the technical field of underwater vehicle detection, in particular to an underwater vehicle-oriented acousto-optic fusion detection method and system. Background The traditional underwater detection system mostly adopts a single detection load, and has obvious limitations that although sonar equipment has long-distance detection capability, the resolution is limited, and optical equipment can provide high-precision images, but is easily influenced by water quality and has limited detection distance. In the prior art, the acousto-optic cooperation mostly adopts fixed weight fusion, and the perception strategy cannot be dynamically adjusted according to the target distance, so that the short-distance target detail is insufficient or the long-distance target is missed. Therefore, research and development of an acousto-optic fusion detection method, in particular to an acousto-optic fusion detection method for an underwater vehicle, has important significance for the development of autonomous detection technology of the underwater vehicle and the improvement of the intelligent level of the underwater vehicle. Disclosure of Invention The invention aims to provide an underwater vehicle-oriented acousto-optic fusion detection method and system, and aims to solve the problems in the prior art. The embodiment of the invention provides an underwater vehicle-oriented acousto-optic fusion detection method, which comprises the following steps: Acquiring preliminary detection information of a suspicious target in an underwater area, and dynamically selecting a perception strategy according to the preliminary detection information; and carrying out cooperative processing on data from different detection loads based on the perception strategy, and continuously updating the detection information of the suspicious target through a processing result. The embodiment of the invention provides an underwater vehicle-oriented acousto-optic fusion detection system, which comprises: The dynamic perception control module is used for acquiring preliminary detection information of suspicious targets in the underwater area and dynamically selecting a perception strategy according to the preliminary detection information; And the multisource fusion detection module is used for carrying out cooperative processing on data from different detection loads based on the perception strategy, and continuously updating the detection information of the suspicious target through a processing result. The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the computer program realizes the steps of the acousto-optic fusion detection method facing the underwater vehicle when being executed by the processor. The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with an information transmission implementation program, and the program is executed by a processor to realize the steps of the acousto-optic fusion detection method facing the underwater vehicle. The embodiment of the invention has the beneficial effects that the embodiment of the invention provides the acousto-optic fusion detection method for the underwater vehicle, and the wide-area scanning of the forward-looking sonar is combined with the detail capturing of the optical equipment to realize the high-efficiency target detection in the full-distance range. Drawings For a clearer description of one or more embodiments of the present description or of the solutions of the prior art, the drawings that are necessary for the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description that follow are only some of the embodiments described in the description, from which, for a person skilled in the art, other drawings can be obtained without inventive faculty. FIG. 1 is a flow chart of an acousto-optic fusion detection method for an underwater vehicle according to an embodiment of the present invention; Fig. 2 is a schematic diagram of an acousto-optic fusion detection system for an underwater vehicle according to an embodiment of the present invention. Detailed Description In order to enable a person skilled in the art to better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be