A skill test scoring system and method for intelligent mobile vehicles

Abstract

The present invention provides a skill test scoring system and method for an intelligent mobile vehicle, comprising an acquisition module, an image processing module, a sound processing module, an image database, an image comparison module, a sound database, a sound comparison module, a comprehensive scoring module, a storage module and a display module, wherein the signal sending end of the acquisition module is connected to the signal receiving end of the image processing module and the signal receiving end of the sound processing module respectively. The present invention processes the image video through the image processing module, performs contrast enhancement, color correction and sharpening processing on the image video, and then converts the low-resolution image into a high-resolution image, removes random noise in the video image, maintains the details and clarity of the image, and combines the image processing algorithm to clarify the blurred moving target to obtain a clearer and more accurate image, thereby improving the quality of the image and ensuring the accuracy of the final score.

Description

Technical Field

[0001] The present invention relates to a system and a method thereof, in particular to a skill test scoring system and a method thereof for an intelligent mobile vehicle, and belongs to the technical field of scoring systems. Background Art

[0002] The smart mobile car with skill test scoring system is a robot that combines automated assessment and intelligent mobile technology. This smart mobile car can be used for scoring various skill tests, greatly improving the accuracy and efficiency of scoring.

[0003] Smart mobile vehicles usually have the following features:

[0004] Autonomous navigation: The smart mobile vehicle has autonomous navigation capabilities and can move according to a pre-set path or map;

[0005] Sensors and cameras: By integrating various sensors and cameras, the smart mobile car can monitor the candidates' skill performance in real time and use algorithms to automatically score them;

[0006] Skill scoring system: The smart mobile vehicle is equipped with a skill scoring system, which can be customized and configured according to different skill test requirements. The scoring system can analyze and evaluate the candidate's skill performance and give corresponding scores and feedback;

[0007] Data analysis and feedback: Smart mobile vehicles can collect and analyze test data, provide feedback and suggestions to candidates, and help them improve their skills and scores;

[0008] By using this intelligent mobile car, the examination institution can improve the examination efficiency, reduce the examination cost, and provide more fair, objective and accurate evaluation results for students and candidates. With the development of technology, the camera of the intelligent car can be used with the scoring system to evaluate the information such as the posture and body movements of the candidates. In the existing technology, the camera is often used to collect the posture and movement information of the candidates;

[0009] For example, the technologies disclosed in CN201410014189.X "Skills Test Scoring System" and CN201910203914.0 "An Artificial Intelligence Machine Learning Experiment Skill Scoring System" both collect the examinee's movements by collecting videos, but this method has the following technical problems:

[0010] (1) The final scoring effect will be affected by the image quality: when the examinee's movements are captured by video acquisition devices such as cameras, the quality of the image will affect the final scoring effect, and some small movements are difficult to capture and identify;

[0011] (2) It is difficult to accurately collect the voice of the examinee: The examinee’s movements are collected through video. This method has certain limitations. When the test questions include oral language, it will affect the collection of the examinee’s data and the final score.

[0012] To this end, a skill test scoring system and method for an intelligent mobile vehicle are proposed. Summary of the invention

[0013] In view of this, the present invention provides a skill test scoring system and method for an intelligent mobile vehicle to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0014] The technical solution of the embodiment of the present invention is implemented as follows: a skill test scoring system for an intelligent mobile vehicle, comprising an acquisition module, an image processing module, a sound processing module, an image database, an image comparison module, a sound database, a sound comparison module, a comprehensive scoring module, a storage module and a display module, wherein a signal sending end of the acquisition module is respectively connected to a signal receiving end of the image processing module and a signal receiving end of the sound processing module, a signal sending end of the image processing module is connected to a signal receiving end of the image comparison module, a signal sending end of the image comparison module is connected to a signal receiving end of the comprehensive scoring module, and a signal sending end of the comprehensive scoring module is connected to a signal receiving end of the storage module and a signal receiving end of the display module;

[0015] The signal sending end of the sound processing module is connected to the signal receiving end of the sound comparison module, the signal sending end of the sound comparison module is connected to the signal receiving end of the comprehensive scoring module, the signal sending end of the sound database is connected to the signal receiving end of the sound comparison module, and the signal sending end of the image database is connected to the signal receiving end of the image comparison module;

[0016] The acquisition module includes a high-definition camera, a high-frame rate camera and a microphone, the signal sending end of the high-definition camera and the signal sending end of the high-frame rate camera are both connected to the signal receiving end of the image processing module, and the signal sending end of the microphone is connected to the signal receiving end of the sound processing module;

[0017] The acquisition module is used to collect the examinee's posture, movements and voice information, and the high frame rate camera is used to capture the minute details of the examinee's video;

[0018] The image processing module includes an image enhancement module, a super-resolution module, a denoising module, a motion compensation module and an optical compensation module;

[0019] The image enhancement module is used to perform contrast enhancement, color correction and sharpening processing on the video image;

[0020] The super-resolution module is used to convert a low-resolution image into a high-resolution image;

[0021] The denoising module is used to remove random noise in the video image to maintain the details and clarity of the image;

[0022] The motion compensation module is used to detect and track moving targets in video images, and at the same time, in combination with image processing algorithms, to make blurred moving targets clear;

[0023] The optical compensation module is used to perform optical compensation on the color, brightness and contrast in the video image to obtain a clearer and more accurate image.

[0024] Further preferably, the sound processing module includes a noise reduction module, an equalizer module, a compressor module and a filter module;

[0025] The noise reduction module is used to reduce the noise in the environment so that the microphone can obtain high-quality audio data. The method for reducing the test-taker's audio by the noise reduction module includes the following steps:

[0026] S1: Use a microphone to collect voice data when the examinee answers questions;

[0027] S2: Use sound waveform recognition technology to analyze the voice samples of candidates when answering questions and identify the noise components;

[0028] S3: generating a reverse signal according to the identified noise component;

[0029] S4: Mix the voice of the examinee answering the questions and the reverse signal, and output the voice of the examinee answering the questions after noise reduction.

[0030] Further preferably, the equalizer module is used to adjust the amplitude of the low, medium and high tones in the examinee's voice, and to enhance or weaken a specific frequency range.

[0031] Further preferably, the compressor module is used to analyze the amplitude of the examinee's voice data signal and attenuate the signal exceeding a certain threshold to keep the sound within a certain range;

[0032] The filter module is used to eliminate noise, adjust the frequency response of the examinee's voice data and filter out unnecessary frequencies.

[0033] Further preferably, the image comparison module is used to pull images from the image database and compare them with the examinee's image, and compare the similarities and differences of the images by extracting features. The image comparison method includes the following steps:

[0034] D1: Extract features from the candidate's image video to extract information that can represent the features of the image;

[0035] D2: Use the cosine similarity comparison method to compare the features of the two images and calculate the similarity and difference between them;

[0036] D3: Based on the comparison results, output the similarity and difference between the correct image and the candidate's image.

[0037] Further preferably, the sound comparison module is used to extract standard audio from the sound database and compare it with the candidate's audio, and compare the similarities and differences between the two audios.

[0038] Further preferably, the comprehensive scoring module includes an online scoring module and an automatic scoring module, the automatic scoring module is used to automatically score the examinees according to the differences between audios and the differences between images, the display module is used to display the scores, and the display module is also used to display test questions and feedback information.

[0039] Further preferably, the signal receiving end of the online scoring module is connected to a login module, and the login module is used for the judges to log in to the online scoring module to perform online scoring on the examinees.

[0040] In addition, the present invention also provides a method for scoring a skill test of an intelligent mobile vehicle, comprising the following steps:

[0041] Step 1: Obtain the posture, movement and voice data information of the examinee when answering questions;

[0042] Step 2: Process the image data and voice data of the examinee;

[0043] Step 3: Compare the differences and similarities between the examinee data and the standard data;

[0044] Step 4: Select manual or automatic scoring to score the candidates;

[0045] Step 5: The display module shows the candidates’ scores and provides feedback on the suggestions.

[0046] Further preferably, in step 4, the examinee's score is automatically stored in the storage module.

[0047] The embodiment of the present invention has the following advantages due to the adoption of the above technical solution:

[0048] 1. The present invention uses a high frame rate camera to capture the minute details of the examinee's video, such as the movements of the face, mouth, and hands, and then processes it through an image processing module to perform contrast enhancement, color correction, and sharpening on the image video. The low-resolution image is then converted into a high-resolution image, and random noise in the video image is removed to maintain the details and clarity of the image. At the same time, the image processing algorithm is combined to clarify the blurred moving target to obtain a clearer and more accurate image, thereby improving the image quality and ensuring the accuracy of the final score.

[0049] 2. The present invention collects the candidate's voice through a microphone, reduces the noise in the environment through a noise reduction module, enables the microphone to obtain high-quality audio data, adjusts the amplitude of the low, medium and high tones in the candidate's voice, and enhances or weakens a specific frequency range, attenuates signals exceeding a certain threshold, keeps the sound within a certain range, thereby improving the clarity of the voice and achieving accurate collection of the candidate's voice.

[0050] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a structural diagram of the skill test scoring system of the intelligent mobile vehicle of the present invention;

[0053] Figure 2 The present invention is a flowchart of the steps of the skill test scoring method for the intelligent mobile vehicle. DETAILED DESCRIPTION

[0054] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0055] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0056] Embodiment 1

[0057] In the prior art, when the examinee's movements are collected by video collection devices such as cameras, the quality of the image will affect the final scoring effect, and it is difficult to capture and identify some minor movements;

[0058] They all use video capture to capture the examinee's movements. This method has certain limitations. When the test questions include oral language, it will affect the collection of examinee data and affect the final score.

[0059] To do this, see Figure 1 , an embodiment of the present invention provides a skill test scoring system for an intelligent mobile vehicle, including an acquisition module, an image processing module, a sound processing module, an image database, an image comparison module, a sound database, a sound comparison module, a comprehensive scoring module, a storage module and a display module, wherein a signal sending end of the acquisition module is respectively connected to a signal receiving end of the image processing module and a signal receiving end of the sound processing module, a signal sending end of the image processing module is connected to a signal receiving end of the image comparison module, a signal sending end of the image comparison module is connected to a signal receiving end of the comprehensive scoring module, and a signal sending end of the comprehensive scoring module is connected to a signal receiving end of the storage module and a signal receiving end of the display module;

[0060] The signal sending end of the sound processing module is connected to the signal receiving end of the sound comparison module, the signal sending end of the sound comparison module is connected to the signal receiving end of the comprehensive scoring module, the signal sending end of the sound database is connected to the signal receiving end of the sound comparison module, and the signal sending end of the image database is connected to the signal receiving end of the image comparison module;

[0061] The acquisition module includes a high-definition camera, a high-frame rate camera and a microphone. The signal sending end of the high-definition camera and the signal sending end of the high-frame rate camera are both connected to the signal receiving end of the image processing module, and the signal sending end of the microphone is connected to the signal receiving end of the sound processing module;

[0062] The acquisition module is used to collect the examinee's posture, movements and voice information, and the high frame rate camera is used to capture the minute details of the examinee's video;

[0063] The image processing module includes an image enhancement module, a super-resolution module, a denoising module, a motion compensation module and an optical compensation module;

[0064] The image enhancement module is used to perform contrast enhancement, color correction and sharpening processing on video images;

[0065] The super-resolution module is used to convert low-resolution images into high-resolution images;

[0066] The denoising module is used to remove random noise in video images and maintain image details and clarity;

[0067] The motion compensation module is used to detect and track moving targets in video images, and at the same time, it combines image processing algorithms to make blurred moving targets clear;

[0068] The optical compensation module is used to perform optical compensation on the color, brightness and contrast of the video image to obtain a clearer and more accurate image.

[0069] In one embodiment, the sound processing module includes a noise reduction module, an equalizer module, a compressor module, and a filter module;

[0070] The noise reduction module is used to reduce the noise in the environment so that the microphone can obtain high-quality audio data. The method for reducing the candidate's audio by the noise reduction module includes the following steps:

[0071] S1: Use a microphone to collect voice data when the examinee answers questions;

[0072] S2: Use sound waveform recognition technology to analyze the voice samples of candidates when answering questions and identify the noise components;

[0073] S3: generating a reverse signal according to the identified noise component;

[0074] S4: Mix the voice of the examinee when answering the questions and the reverse signal, and output the voice of the examinee when answering the questions after noise reduction. The equalizer module is used to adjust the amplitude of the low, medium and high tones in the examinee's voice, and enhance or weaken a specific frequency range. The compressor module is used to analyze the amplitude of the examinee's voice data signal, and attenuate the signal exceeding a certain threshold to keep the sound within a certain range.

[0075] The filter module is used to eliminate noise, adjust the frequency response of the candidate's voice data and filter out unnecessary frequencies, and then process the voice data through the noise reduction module, equalizer module, compressor module and filter module to improve the clarity of the voice data.

[0076] In one embodiment, the image comparison module is used to compare the image in the image database with the examinee's image, and compare the similarities and differences of the images by extracting features. The image comparison method includes the following steps:

[0077] D1: Extract features from the candidate's image video to extract information that can represent the features of the image;

[0078] D2: Use the cosine similarity comparison method to compare the features of the two images and calculate the similarity and difference between them;

[0079] D3: Based on the comparison results, output the similarity and difference between the correct image and the candidate's image;

[0080] The sound comparison module is used to pull the standard audio from the sound database and compare it with the candidate's audio, comparing the similarities and differences between the two audios. The image comparison module can compare the candidate's action image with the standard action, and the sound comparison module can compare the candidate's voice data with the standard voice in order to score it.

[0081] In one embodiment, the comprehensive scoring module includes an online scoring module and an automatic scoring module. The automatic scoring module is used to automatically score the examinees according to the differences between the audios and the differences between the images. The display module is used to display the scores. The display module is also used to display the test questions and feedback information. The signal receiving end of the online scoring module is connected to a login module. The login module is used for the judges to log in to the online scoring module and score the examinees online. By setting up two scoring methods, it is convenient to use. When manpower is insufficient, the examinees can be scored through the automatic scoring module, and the examinees can be scored manually in real time through the online scoring module.

[0082] In view of the related problems in the traditional technology, this specific implementation is based on the skill test scoring system of the intelligent mobile vehicle provided above, and adopts the following technical means or features to achieve the solution:

[0083] (1) The final scoring effect will be affected by the image quality: A high-frame rate camera is used to capture the tiny details of the examinee's video, such as the movements of the face, mouth, and hands, and then processed by the image processing module. The image video is contrast enhanced, color corrected, and sharpened. The low-resolution image is then converted into a high-resolution image, and random noise in the video image is removed to maintain the image details and clarity. At the same time, the image processing algorithm is used to clarify the blurred moving target to obtain a clearer and more accurate image, thereby improving the image quality and ensuring the accuracy of the final score.

[0084] (2) The problem of being unable to accurately collect the candidate's voice: The candidate's voice is collected through a microphone, and the noise in the environment is reduced through a noise reduction module, so that the microphone can obtain high-quality audio data, adjust the amplitude of the low, medium and high tones in the candidate's voice, and enhance or weaken specific frequency ranges. Signals exceeding a certain threshold are attenuated to keep the sound within a certain range, thereby improving the clarity of the voice and achieving accurate collection of the candidate's voice.

[0085] Embodiment 2

[0086] In this second embodiment, please refer to Figure 2, a skill test scoring method for an intelligent mobile vehicle, comprising the following steps:

[0087] Step 1: Obtain the posture, movement and voice data information of the examinee when answering questions;

[0088] Step 2: Process the image data and voice data of the examinee;

[0089] Step 3: Compare the differences and similarities between the examinee data and the standard data;

[0090] Step 4: Select manual or automatic scoring to score the candidates;

[0091] Step 5: The display module shows the candidates’ scores and provides feedback on the suggestions.

[0092] In one embodiment, in step four, the examinee's score is automatically stored in the storage module, and the data is stored by the storage module so that the data can be retrieved at any time.

[0093] When the present invention is working, the posture and movements of the examinee during the examination are collected through a high-definition camera, the voice of the examinee is collected through a microphone, and the minute details of the examinee's video, such as the movements of the face, mouth, and hands, are captured through a high-frame rate camera. Then the action image is transmitted to the image processing module, and the voice data is transmitted to the sound processing module. The image processing module performs contrast enhancement, color correction and sharpening on the examinee's image video, and then converts the low-resolution image into a high-resolution image, removes random noise in the video image, maintains the details and clarity of the image, and combines the image processing algorithm to clarify the blurred moving target to obtain a clearer and more accurate image, and then enhances the features through the image comparison module. Take, compare the similarities and differences of images, and finally transmit them to the comprehensive scoring module. The voice data uses the noise reduction module to reduce the noise in the environment, so that the microphone can obtain high-quality audio data, adjust the amplitude of the low, medium and high tones in the candidate's voice, enhance or weaken the specific frequency range, attenuate the signal exceeding a certain threshold, keep the sound within a certain range, and thus improve the clarity of the voice. Then use the sound comparison module to compare the similarities and differences between the audios. Finally, use the comprehensive scoring module to score the candidates, and then use the display module to display the candidate results. Automatic scoring can be achieved through the automatic scoring module, and online manual scoring of the candidates can be achieved by logging in to the online scoring module through the login module.

[0094] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various 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. A skill test scoring system for an intelligent mobile vehicle, comprising an acquisition module, an image processing module, a sound processing module, an image database, an image comparison module, a sound database, a sound comparison module, a comprehensive scoring module, a storage module and a display module, characterized in that: The signal sending end of the acquisition module is respectively connected to the signal receiving end of the image processing module and the signal receiving end of the sound processing module, the signal sending end of the image processing module is connected to the signal receiving end of the image comparison module, the signal sending end of the image comparison module is connected to the signal receiving end of the comprehensive scoring module, and the signal sending end of the comprehensive scoring module is connected to the signal receiving ends of the storage module and the display module; The signal sending end of the sound processing module is connected to the signal receiving end of the sound comparison module, the signal sending end of the sound comparison module is connected to the signal receiving end of the comprehensive scoring module, the signal sending end of the sound database is connected to the signal receiving end of the sound comparison module, and the signal sending end of the image database is connected to the signal receiving end of the image comparison module; The acquisition module includes a high-definition camera, a high-frame rate camera and a microphone, the signal sending end of the high-definition camera and the signal sending end of the high-frame rate camera are both connected to the signal receiving end of the image processing module, and the signal sending end of the microphone is connected to the signal receiving end of the sound processing module; The acquisition module is used to collect the examinee's posture, movements and voice information, and the high frame rate camera is used to capture the minute details of the examinee's video; The image processing module includes an image enhancement module, a super-resolution module, a denoising module, a motion compensation module and an optical compensation module; The image enhancement module is used to perform contrast enhancement, color correction and sharpening processing on the video image; The super-resolution module is used to convert a low-resolution image into a high-resolution image; The denoising module is used to remove random noise in the video image and maintain the details and clarity of the image; The motion compensation module is used to detect and track moving targets in video images, and at the same time, in combination with image processing algorithms, to make blurred moving targets clear; The optical compensation module is used to perform optical compensation on the color, brightness and contrast in the video image to obtain a clearer and more accurate image; The sound processing module includes a noise reduction module, an equalizer module, a compressor module and a filter module; The noise reduction module is used to reduce the noise in the environment so that the microphone can obtain high-quality audio data. The method for reducing the test-taker's audio by the noise reduction module includes the following steps: S1: Use a microphone to collect voice data when the examinee answers questions; S2: Use sound waveform recognition technology to analyze the voice samples of candidates when answering questions and identify the noise components; S3: generating a reverse signal according to the identified noise component; S4: Mix the voice of the examinee answering the questions and the reverse signal, and output the voice of the examinee answering the questions after noise reduction; The equalizer module is used to adjust the amplitude of the low, medium and high tones in the examinee's voice, and to enhance or weaken the frequency so that it remains within a certain threshold range; The compressor module is used to analyze the amplitude of the candidate's voice data signal and attenuate the signal exceeding a certain threshold to keep the sound within a certain range; The filter module is used to eliminate noise, adjust the frequency response of the examinee's voice data and filter out the frequency of non-examinee's voice data.

2. The skill test scoring system for an intelligent mobile vehicle according to claim 1, characterized in that: The image comparison module is used to compare the image in the image database with the examinee's image, and compare the similarities and differences of the images by extracting features. The image comparison method includes the following steps: D1: Extract features from the candidate's image video to extract information that can represent the features of the image; D2: Use the cosine similarity comparison method to compare the features of the two images and calculate the similarity and difference between them; D3: Based on the comparison results, output the similarity and difference between the correct image and the candidate's image.

3. The skill test scoring system for an intelligent mobile vehicle according to claim 2 is characterized in that: The sound comparison module is used to pull the standard audio from the sound database and compare it with the candidate's audio, and compare the similarities and differences between the two audios.

4. The skill test scoring system for an intelligent mobile vehicle according to claim 3 is characterized in that: The comprehensive scoring module includes an online scoring module and an automatic scoring module. The automatic scoring module is used to automatically score the examinees according to the differences between the audios and the differences between the images. The display module is used to display the scores. The display module is also used to display test questions and feedback information.

5. The skill test scoring system for an intelligent mobile vehicle according to claim 4 is characterized in that: The signal receiving end of the online scoring module is connected to a login module, and the login module is used for the judges to log in to the online scoring module and perform online scoring on the examinees.

6. A method for scoring a skill test for an intelligent mobile vehicle, applied to the skill test scoring system for an intelligent mobile vehicle as claimed in any one of claims 1 to 5, characterized in that: The following steps are involved: Step 1: Obtain the posture, movement and voice data information of the examinee when answering questions; Step 2: Process the image data and voice data of the examinee; Step 3: Compare the differences and similarities between the examinee data and the standard data; Step 4: Select manual or automatic scoring to score the candidates; Step 5: The display module shows the candidates’ scores and provides feedback on the suggestions.

7. The method for scoring a skill test for an intelligent mobile vehicle according to claim 6, characterized in that: In step 4, the examinee's score is automatically stored in the storage module.

Images