Target recognition system based on artificial intelligence

Abstract

The invention discloses a target recognition system based on artificial intelligence. The system comprises a target image acquisition module, a large sample database module, an AI controller module and a recognition result display module. The system has the beneficial effects that the system is provided with the target image acquisition module, the large sample database module, the AI controller module and the identification result display module; therefore, the AI controller module can compare the ship name identification image of the ship acquired by the target image acquisition module with the feature character data of the large sample database module so as to identify the ship name identification of the ship, and the identification result display module can display the ship name identification of the ship. The target identification of the ship name identifier is realized, and the target identification mode of the ship name identifier is easy to realize and accurate.

Description

Technical Field

[0001] The present invention relates to the field of ship name identification target recognition systems, and in particular to a target recognition system based on artificial intelligence. Background Art

[0002] Water shipping is one of the most important modes of transportation in human society and has played a vital role in promoting economic globalization. At present, with the continuous increase in the number of ships, waterways are becoming more and more crowded. A series of incidents such as overloaded transportation and illegal escape are also threatening human life and property safety. Therefore, the state will register and manage ship names and identification to achieve the purpose of managing ships in large quantities.

[0003] At present, when specifically identifying the ship name mark target, although the recognition technology is introduced to perform the target recognition operation on the ship name mark, the existing recognition technology can only extract the features of the acquired target image and compare it with the character data in the database, and the character data in the database is limited and cannot be updated in time, which results in a low accuracy rate for the target recognition of the ship name mark and cannot meet the use needs of the ship name mark target recognition. Summary of the invention

[0004] The purpose of the present invention is to provide a target recognition system based on artificial intelligence in order to solve the above-mentioned problems. The system is provided with a target image acquisition module, a large sample database module, an AI controller module and a recognition result display module. The AI ​​controller module can compare the ship name identification image acquired by the target image acquisition module with the characteristic character data of the large sample database module to identify the ship name identification. At the same time, the recognition result display module can display the identified ship name identification, thereby realizing target recognition of the ship name identification. See the following description for details.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The present invention provides an artificial intelligence-based target recognition system, which includes a target image acquisition module for acquiring a ship name identification image of a ship and processing the segmented target recognition image area;

[0007] A large sample database module is used to store feature character data and upload the feature character data to network training for updating and iteration;

[0008] The AI ​​controller module is used to extract character features from the target recognition image area and perform character feature recognition and comparison with the characteristic character data in the data storage unit to obtain the ship name identification result, and transmit the obtained ship name identification result to the outside;

[0009] The recognition result display module is used to effectively display the obtained ship name identification results.

[0010] Preferably, the target image acquisition module includes an image acquisition unit, an image processing unit, and an image segmentation unit, for acquiring a ship name identification image of a ship through the image acquisition unit, performing shaping processing on the acquired ship name identification image through the image processing unit, and segmenting the shaped ship name identification image through the image segmentation unit to obtain an image area to be subjected to target identification.

[0011] Preferably, the target image acquisition module also includes an image output unit, which is used to output the segmented target recognition image area to the AI ​​controller module and the large sample database module through the image output unit for character feature recognition and comparison.

[0012] Preferably, the large sample database module includes a data storage unit, a data networking training unit, and a data transceiver unit, which is used to transmit the feature character data in the data storage unit to the AI ​​controller module and the target recognition image area through the data transceiver unit for character feature recognition and comparison, and upload the feature character data to the network training through the data networking training unit for updating and iteration.

[0013] Preferably, the AI ​​controller module includes an image access unit, a data extraction unit, a data comparison unit, a data calling unit, and a data return unit. The image access unit is connected to the image output unit of the target image acquisition module to access the target recognition image area and extract character features through the image access unit and the data extraction unit. The data calling unit and the data return unit are both connected to the data transceiver unit of the large sample database module to call and return the feature character data in the data storage unit through the data calling unit and the data return unit. The character features extracted from the target recognition image area are compared with the feature character data in the data storage unit through the data comparison unit to obtain the ship name identification result.

[0014] Preferably, the AI ​​controller module also includes a result output unit, which is used to transmit the obtained ship name identification result to the recognition result display module for result display.

[0015] Preferably, the recognition result display module includes a result input unit, and the result input module is connected to the result output unit of the AI ​​controller module to receive the ship name identification result transmitted by the AI ​​controller module through the result input unit.

[0016] Preferably, the recognition result display module also includes a display unit and a voice broadcast unit, which are used to display and voice broadcast the ship name identification result in real time through the display unit and the voice broadcast unit respectively.

[0017] By adopting the above-mentioned target recognition system based on artificial intelligence, when the ship name mark target is recognized, since the target image acquisition module, the large sample database module, the AI ​​controller module and the recognition result display module are provided, the ship name mark image of the ship acquired by the target image acquisition module can be compared with the characteristic character data of the large sample database module through the AI ​​controller module to identify the ship name mark, and the recognized ship name mark can be displayed through the recognition result display module, thereby realizing the target recognition of the ship name mark, and the target recognition method of the ship name mark is easy to realize and accurate, and at the same time, with the help of the data networking training unit of the large sample database module, the existing characteristic character data and the returned characteristic character data can be uploaded to the network training method, so that the characteristic character data in the data storage unit of the large sample database module can be updated and iterated, and since the characteristic character data in the data storage unit of the large sample database module are intelligently trained and updated in time, the target recognition accuracy of the ship name mark can be effectively improved.

[0018] The beneficial effects are as follows: 1. The present invention is provided with a target image acquisition module, a large sample database module, an AI controller module and a recognition result display module, so that the ship name identification image of the ship acquired by the target image acquisition module can be compared with the characteristic character data of the large sample database module through the AI ​​controller module to identify the ship name identification, and at the same time, the identified ship name identification can be displayed through the recognition result display module, thereby realizing the target recognition of the ship name identification, and the target recognition method of the ship name identification is easy to realize and accurate;

[0019] 2. The target image acquisition module is provided with an image acquisition unit, an image processing unit, an image segmentation unit and an image output unit, so that the image acquisition unit can acquire the ship name identification image of the ship, the image processing unit can perform shaping processing on the acquired ship name identification image, the image segmentation unit can segment the shaped ship name identification image to obtain the image area to be identified, and the image output unit can output the segmented target identification image area to the AI ​​controller module and the large sample database module for character feature recognition and comparison, thereby realizing the acquisition and effective processing of the ship name identification image, and ensuring that the AI ​​controller module can successfully complete the target identification of the ship name identification;

[0020] 3. The large sample database module is provided with a data storage unit, a data networking training unit, and a data transceiver unit, so that the characteristic character data in the data storage unit can be transmitted to the AI ​​controller module through the data transceiver unit to perform character feature recognition and comparison with the target recognition image area, thereby ensuring that the AI ​​controller module can successfully complete the target recognition of the ship name identification. At the same time, the characteristic character data in the data storage unit can be updated and iterated by uploading the existing characteristic character data and the returned characteristic character data to the network training through the data networking training unit. Since the characteristic character data in the data storage unit is intelligently trained and updated in time, the target recognition accuracy of the ship name identification can be effectively improved;

[0021] 4. The AI ​​controller module is provided with an image access unit, a data extraction unit, a data comparison unit, a data calling unit, a data return unit and a result output unit, so that the target recognition image area can be accessed and character feature extraction can be performed through the image access unit and the data extraction unit, the characteristic character data in the data storage unit can be called and returned through the data calling unit and the data return unit, the character feature extracted from the target recognition image area can be compared with the characteristic character data in the data storage unit through the data comparison unit to obtain the ship name identification result, and the obtained ship name identification result can be transmitted to the recognition result display module for result display through the result output unit, so that the intelligent recognition of the ship name identification is realized, ensuring that the AI ​​controller module can successfully complete the target recognition of the ship name identification;

[0022] 5. The recognition result display module is provided with a result input unit, a display unit and a voice broadcast unit, so that the result input unit can receive the ship name identification result transmitted by the AI ​​controller module, and the display unit and the voice broadcast unit can respectively display and voice broadcast the ship name identification result in real time, thereby realizing the effective display of the ship name identification result and facilitating the intuitive acquisition of the ship name identification result. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 is the overall system block diagram of the present invention;

[0025] Figure 2 is a schematic block diagram of a target image acquisition module of the present invention;

[0026] Figure 3 is a schematic block diagram of a large sample database module of the present invention;

[0027] Figure 4 is a schematic block diagram of an AI controller module of the present invention;

[0028] Figure 5 It is a schematic block diagram of the recognition result display module of the present invention. DETAILED DESCRIPTION

[0029] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0030] See also Figure 1-Figure 5As shown, the present invention provides a target recognition system based on artificial intelligence, which includes a target image acquisition module for acquiring a ship name identification image and processing and segmenting the target recognition image area. Specifically, the target image acquisition module includes an image acquisition unit, an image processing unit, and an image segmentation unit. The ship name identification image of the ship acquired by the image acquisition unit is shaped by the image processing unit, and the shaped ship name identification image is segmented by the image segmentation unit to obtain an image area to be subjected to target recognition. Preferably, the target image acquisition module also includes an image output unit for outputting the segmented target recognition image area to the AI ​​controller module and the large sample database module through the image output unit for character feature recognition and comparison. The purpose of such a setting is to achieve the acquisition and effective processing of the ship name identification image, and ensure that the AI ​​controller module can successfully complete the target recognition of the ship name identification.

[0031] See also Figure 1 and Figure 3 As shown, the system also includes a large sample database module for storing feature character data and uploading the feature character data to network training for updating and iteration. Specifically, the large sample database module includes a data storage unit, a data networking training unit, and a data transceiver unit. The feature character data in the data storage unit is transmitted to the AI ​​controller module through the data transceiver unit to compare with the target recognition image area for character feature recognition, and the feature character data is uploaded to the network training for updating and iteration through the data networking training unit. The advantage of this arrangement is that first, the feature character data in the data storage unit can be transmitted to the AI ​​controller module through the data transceiver unit to compare with the target recognition image area for character feature recognition, ensuring that the AI ​​controller module can successfully complete the target recognition of the ship name identification. At the same time, the feature character data in the data storage unit can be updated and iterated by uploading the existing feature character data and the returned feature character data to the network training through the data networking training unit. Since the feature character data in the data storage unit is intelligently trained and updated in time, the target recognition accuracy of the ship name identification can be effectively improved.

[0032] See also Figure 1 and Figure 4As shown, the system also includes an AI controller module, which is used to extract character features from the target recognition image area and perform character feature recognition and comparison with the feature character data in the data storage unit to obtain the ship name identification result of the ship, and transmit the obtained ship name identification result to the outside. Specifically, the AI ​​controller module includes an image access unit, a data extraction unit, a data comparison unit, a data call unit, and a data return unit. The image access unit is connected to the image output unit of the target image acquisition module to access the target recognition image area through the image access unit and the data extraction unit and perform character feature extraction. The data call unit and the data return unit are both connected to the large sample database module The AI ​​controller module is connected to a data transceiver unit for calling and returning the feature character data in the data storage unit through the data calling unit and the data returning unit, and performing character feature recognition and comparison between the character features extracted from the target recognition image area and the feature character data in the data storage unit through the data comparison unit to obtain the ship name identification result. Preferably, the AI ​​controller module also includes a result output unit for transmitting the obtained ship name identification result to the recognition result display module for result display through the result output unit. The purpose of such a setting is to realize the intelligent recognition of the ship name identification and ensure that the AI ​​controller module can successfully complete the target recognition of the ship name identification.

[0033] See also Figure 1 and Figure 5 As shown, the system also includes a recognition result display module for effectively displaying the obtained ship name identification result. Specifically, the recognition result display module includes a result input unit, and the result input module is connected to the result output unit of the AI ​​controller module to receive the ship name identification result transmitted by the AI ​​controller module through the result input unit. Preferably, the recognition result display module also includes a display unit and a voice broadcast unit to respectively display and voice broadcast the ship name identification result in real time through the display unit and the voice broadcast unit. The reason for this arrangement is to achieve effective display of the ship name identification result, so as to facilitate intuitive acquisition of the ship name identification result.

[0034] By adopting the above structure, when the ship name identification target is recognized, since the target image acquisition module, the large sample database module, the AI ​​controller module and the recognition result display module are provided, the ship name identification image of the ship acquired by the target image acquisition module can be compared with the characteristic character data of the large sample database module through the AI ​​controller module to identify the ship name identification, and the recognized ship name identification can be displayed through the recognition result display module, thereby realizing the target recognition of the ship name identification, and the target recognition method of the ship name identification is easy to realize and accurate, and at the same time, with the help of the data networking training unit of the large sample database module, the existing characteristic character data and the returned characteristic character data can be uploaded to the network training method, so that the characteristic character data in the data storage unit of the large sample database module can be updated and iterated, and since the characteristic character data in the data storage unit of the large sample database module is intelligently trained and timely updated, the target recognition accuracy of the ship name identification can be effectively improved.

[0035] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An artificial intelligence-based target recognition system, characterized in that: The system includes a target image acquisition module, which is used to acquire the ship name identification image of the ship and process the target recognition image area obtained by segmentation; A large sample database module is used to store feature character data and upload the feature character data to network training for updating and iteration; The AI ​​controller module is used to extract character features from the target recognition image area and perform character feature recognition and comparison with the characteristic character data in the data storage unit to obtain the ship name identification result, and transmit the obtained ship name identification result to the outside; The recognition result display module is used to effectively display the obtained ship name identification results.

2. The target recognition system based on artificial intelligence according to claim 1, characterized in that: The target image acquisition module includes an image acquisition unit, an image processing unit, and an image segmentation unit, which is used to acquire a ship name identification image of a ship through the image acquisition unit, perform shaping processing on the acquired ship name identification image through the image processing unit, and segment the shaped ship name identification image through the image segmentation unit to obtain an image area to be subjected to target recognition.

3. The target recognition system based on artificial intelligence according to claim 2, characterized in that: The target image acquisition module also includes an image output unit, which is used to output the segmented target recognition image area to the AI ​​controller module and the large sample database module through the image output unit for character feature recognition and comparison.

4. The target recognition system based on artificial intelligence according to claim 3, characterized in that: The large sample database module includes a data storage unit, a data networking training unit, and a data transceiver unit, which is used to transmit the feature character data in the data storage unit to the AI ​​controller module and the target recognition image area through the data transceiver unit for character feature recognition and comparison, and upload the feature character data to the network training through the data networking training unit for updating and iteration.

5. The target recognition system based on artificial intelligence according to claim 4, characterized in that: The AI ​​controller module includes an image access unit, a data extraction unit, a data comparison unit, a data calling unit, and a data return unit. The image access unit is connected to the image output unit of the target image acquisition module to access the target recognition image area and extract character features through the image access unit and the data extraction unit. The data calling unit and the data return unit are both connected to the data transceiver unit of the large sample database module to call and return the feature character data in the data storage unit through the data calling unit and the data return unit. The character features extracted from the target recognition image area are compared with the feature character data in the data storage unit through the data comparison unit to obtain the ship name identification result.

6. An artificial intelligence based target recognition system according to any one of claims 2 to 5, characterized in that: The AI ​​controller module also includes a result output unit, which is used to transmit the obtained ship name identification result to the recognition result display module for result display.

7. The target recognition system based on artificial intelligence according to claim 6, characterized in that: The recognition result display module includes a result input unit, which is connected to the result output unit of the AI ​​controller module and is used to receive the ship name identification result transmitted by the AI ​​controller module through the result input unit.

8. The target recognition system based on artificial intelligence according to claim 7, characterized in that: The recognition result display module also includes a display unit and a voice broadcast unit, which are used to display and voice broadcast the ship name identification result in real time through the display unit and the voice broadcast unit respectively.

Images