Target object detection method and device, equipment and storage medium

Abstract

The invention provides a target object detection method and device, equipment and a storage medium, and belongs to the field of detection.The method comprises the steps that an infrared light intensity value radiated by a target object is obtained and compared with a preset light intensity value, and if the infrared light intensity value is smaller than or equal to the preset light intensity value, the target object is detected; controlling the wearable device to turn on the lighting device or reminding a wearer to turn on the lighting device so as to perform infrared light irradiation on the target object; if the infrared light intensity value is greater than a preset light intensity value, controlling an infrared camera to collect an image of a target object to obtain a target image, and determining the type of the target object; if the type of the target object is a target type, acquiring a pixel value of each pixel point of the target object in the target image, and calculating a pixel difference value between each pixel point and an adjacent pixel point; and determining the quality of the target object according to each pixel difference value and a preset pixel difference value of the current object type. And the target object quality detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present application relates to the field of detection technology, and in particular to a target object detection method, device, equipment and storage medium. Background Art

[0002] When buying food, people usually evaluate the food quality by observing the food surface to see if it is intact and smelling the fruit to see if it has an abnormal smell, so as to select food with good appearance and quality for purchase. However, people are disturbed by various factors when selecting and may still select damaged or rotten food.

[0003] Therefore, how to accurately determine the quality of food is a problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of this application is to provide a target object detection method, device, equipment and storage medium, aiming to improve the accuracy and efficiency of judging the quality of food.

[0005] In a first aspect, the present application provides a target object detection method, the target object detection method comprising the following steps:

[0006] Obtaining an infrared light intensity value radiated by a target object, and comparing the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, controlling the wearable device to turn on a lighting device or reminding the wearer to turn on the lighting device to irradiate the target object with infrared light;

[0007] If the infrared light intensity value is greater than the preset light intensity value, controlling the infrared camera to capture an image of the target object, obtaining a target image, and determining the type of the target object;

[0008] If the type of the target object is a target type, obtaining a pixel value of each pixel of the target object in the target image, and calculating a pixel difference between each pixel and an adjacent pixel;

[0009] The quality of the target object is determined according to each of the pixel differences and a preset pixel difference of the current object type.

[0010] In some embodiments, the infrared light intensity value radiated by the target object is collected by an infrared sensor or a camera with an infrared shooting function.

[0011] In some embodiments, determining the type of the target object includes:

[0012] Comparing the target object obtained from the target image with preset data to determine the type of the target object; or,

[0013] Identify the target image using a preset target object recognition model to obtain the type of the target object; or,

[0014] The type of the target object input by the wearer is obtained.

[0015] In some embodiments, obtaining the pixel value of each pixel of the target object in the target image includes:

[0016] Performing image dimension reduction processing on the target image to obtain a target pixel image;

[0017] The pixel value of each pixel in the target pixel image is obtained to obtain the pixel value of each pixel of the target object.

[0018] In some embodiments, the preset pixel difference value includes a preset first pixel difference value, a preset second pixel difference value, and a preset third pixel difference value; and determining the quality of the target object according to each of the pixel difference values ​​and the preset pixel difference value of the current object type includes:

[0019] If all the pixel differences are less than or equal to the preset first pixel difference, it is determined that the quality of the target object is qualified;

[0020] If all the pixel differences are less than or equal to the preset second pixel difference, and there is a pixel difference greater than the preset first pixel difference, determining that the quality of the target object is a defective product;

[0021] If there is a pixel difference greater than the preset second pixel difference, the quality of the target object is determined to be a defective product.

[0022] In some embodiments, before obtaining the infrared light intensity value radiated by the target object, the method further includes:

[0023] Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising a target image and a quality of a sample target object;

[0024] The preset first pixel difference value and the preset second pixel difference value are determined according to the target image and the quality of the sample target object in each of the sample data.

[0025] In some embodiments, controlling the infrared camera to capture the image of the target object to obtain the target image includes:

[0026] Determining whether the target object is within the field of view of the infrared camera;

[0027] If the target object is not within the field of view of the infrared camera, a prompt message indicating that the target object is not within the field of view is output to remind the wearer to switch the acquisition posture;

[0028] When it is determined that the target object is within the field of view of the infrared camera, a target image is obtained by capturing an image of the target object by the infrared camera.

[0029] In a second aspect, the present application further provides a target object detection device, the target object detection device comprising an acquisition module, a control module and a determination module, wherein:

[0030] The acquisition module is used to acquire the infrared light intensity value radiated by the target object;

[0031] The control module is used to compare the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, control the wearable device to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light;

[0032] The control module is further configured to control the infrared camera to capture the image of the target object to obtain a target image if the infrared light intensity value is greater than the preset light intensity value;

[0033] The determination module is used to determine the type of the target object;

[0034] The acquisition module is further used to acquire the pixel value of each pixel of the target object in the target image and calculate the pixel difference between each pixel and an adjacent pixel if the type of the target object is a target type;

[0035] The determination module is further configured to determine the quality of the target object according to each of the pixel differences and a preset pixel difference of the current object type.

[0036] In a third aspect, the present application also provides a wearable device, comprising an infrared camera, a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the target object detection method as described above are implemented.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the target object detection method as described above are implemented.

[0038] The present application provides a method, device, equipment and storage medium for detecting a target object. The present application obtains the infrared light intensity value radiated by the target object and compares the infrared light intensity value with the preset light intensity value. If the infrared light intensity value is less than or equal to the preset light intensity value, the wearable device is controlled to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light; if the infrared light intensity value is greater than the preset light intensity value, the infrared camera is controlled to collect the image of the target object, obtain the target image, and determine the type of the target object; if the type of the target object is the target type, the pixel value of each pixel of the target object in the target image is obtained, and the pixel difference between each pixel and the adjacent pixel is calculated; the quality of the target object is determined according to the pixel difference between each pixel and the preset pixel difference of the current object type. In the present application, according to the pixel difference between each pixel in the target image of the target object, it is possible to accurately determine whether the target object has rotten bad pixels, which greatly improves the efficiency and accuracy of the target object quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A schematic diagram of a process flow of a target object detection method provided in an embodiment of the present application;

[0041] Figure 2 A schematic diagram of the structure of a wearable device provided for implementing this embodiment;

[0042] Figure 3 A schematic diagram of the structure of a pixel point provided for implementing this embodiment;

[0043] Figure 4 A schematic block diagram of a target object detection device provided in an embodiment of the present application;

[0044] Figure 5 A schematic block diagram of the structure of a wearable device provided in an embodiment of the present application.

[0045] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0048] With the improvement of living standards, people's demand for food (fruits and vegetables, etc.) is also increasing, and at the same time, the quality requirements for food are getting higher and higher. When buying food, people generally evaluate the quality of food by observing whether the surface of the food is intact and smelling whether the fruit smells abnormal, so as to select food with good appearance and quality for purchase. However, people are disturbed by various factors when choosing, and they still choose damaged or rotten food, which causes people to waste money and greatly reduces people's trust in merchants.

[0049] To solve the above problems, the embodiments of the present application provide a target object detection method, device, equipment and storage medium. The target object detection method includes obtaining the infrared light intensity value radiated by the target object, and comparing the infrared light intensity value with a preset light intensity value. If the infrared light intensity value is less than or equal to the preset light intensity value, the wearable device is controlled to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light; if the infrared light intensity value is greater than the preset light intensity value, the infrared camera is controlled to capture the image of the target object, obtain the target image, and determine the type of the target object; if the type of the target object is the target type, the pixel value of each pixel of the target object in the target image is obtained, and the pixel difference between each pixel and the adjacent pixel is calculated; the quality of the target object is determined according to each pixel difference and the preset pixel difference of the current object type.

[0050] Among them, the target object detection method can be applied to wearable devices, including AR helmets, MR helmets, VR glasses, VR helmets, etc.

[0051] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0052] Please refer to Figure 1 , Figure 1A flowchart of a target object detection method provided in an embodiment of the present application.

[0053] like Figure 1 As shown, the target object detection method includes steps S101 to S104.

[0054] Step S101, obtain the infrared light intensity value radiated by the target object, and compare the infrared light intensity value with a preset light intensity value. If the infrared light intensity value is less than or equal to the preset light intensity value, control the wearable device to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light.

[0055] The target objects include but are not limited to fruits and vegetables, etc. The preset light intensity value can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the preset light intensity value can be set to 500 illumination.

[0056] In some embodiments, the infrared light intensity value radiated by the target object is collected by an infrared sensor or a camera with an infrared shooting function.

[0057] It should be noted that the wearable device is provided with an infrared camera, which is used to collect images of the target object, for example, Figure 2 As shown, an infrared camera 20 is provided on the frame of the wearable device 10. Of course, the infrared camera 20 can also be provided at other positions of the wearable device 10, and this embodiment of the present invention does not specifically limit this.

[0058] In some embodiments, when an instruction to perform quality inspection on a target object is obtained, an infrared camera is turned on, and the infrared light intensity value radiated by the target object is detected by the infrared camera. When the infrared light intensity value radiated by the target object is greater than or equal to a preset light intensity value, an image of the target object captured by the infrared camera is obtained.

[0059] It should be noted that the method for obtaining the quality inspection instruction can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the quality inspection instruction can be a quality inspection instruction issued by the wearer of the wearable device by touching a button.

[0060] In some embodiments, when it is detected that the infrared light intensity value radiated by the target object is less than the preset light intensity value, fill light prompt information is generated; a prompt action corresponding to the fill light prompt information is executed to remind the wearer to irradiate the target object with infrared light according to the fill light prompt information. By executing the prompt action corresponding to the fill light prompt information, the wearer can irradiate the target object with infrared light in a timely manner, and by supplementing the target object with infrared light, the accuracy of target object detection can be improved.

[0061] It should be noted that the fill light prompt information includes but is not limited to the "supplement infrared light" text prompt information and the "supplement infrared light" voice prompt information, etc., wherein the prompt action corresponding to the "supplement infrared light" text prompt information is to display the fill light prompt information on the display interface, and the prompt action corresponding to the "supplement infrared light" voice prompt information is to broadcast the fill light prompt voice. For example, if the fill light prompt information is the "supplement infrared light" text prompt information, the fill light prompt information will be displayed on the display interface of the wearable device to remind the wearer to irradiate the target object with infrared light according to the fill light prompt information. For another example, if the fill light prompt information is the "supplement infrared light" voice prompt information, the fill light prompt voice will be broadcast on the target object to remind the wearer to irradiate the target object with infrared light according to the fill light prompt voice.

[0062] In some embodiments, the wearable device also includes a lighting device, and when the infrared light intensity value is less than or equal to a preset light intensity value, the wearable device is controlled to turn on the lighting device to irradiate the target object with infrared light.

[0063] In some embodiments, when it is detected that the infrared light intensity value radiated by the target object is less than the preset light intensity value, fill light prompt information is generated; the fill light prompt information is displayed on the display interface of the wearable device to remind the wearer to irradiate the target object with infrared light according to the fill light prompt information. By displaying the fill light prompt information on the display interface of the wearable device, the wearer can irradiate the target object with infrared light in a timely manner, and by supplementing the target object with infrared light, the accuracy of target object detection can be improved.

[0064] In some embodiments, the wearer sees the fill light prompt information and emits infrared light through the lighting device so that the target object absorbs the infrared light. The infrared light intensity value radiated by the target object is obtained at a preset time interval, and when the infrared light intensity value is greater than or equal to the preset light intensity value, an instruction to turn off the fill light prompt information is generated; according to the instruction to turn off the fill light prompt information, the display interface displaying the fill light prompt information is turned off, and the image of the target object captured by the infrared camera is captured. Among them, the preset time interval can be set according to the actual situation, and the embodiment of the present invention does not make specific limitations on this. For example, the preset time interval can be set to 3 seconds. By detecting the infrared light intensity value radiated by the target object at the preset time interval, the efficiency of the target object quality detection can be improved.

[0065] It should be noted that the infrared device and infrared equipment can be selected according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the infrared device and infrared equipment can be an infrared lamp.

[0066] It is understandable that the target object can absorb the infrared light radiated by the infrared device, and the target object can also radiate infrared light at the same time. The higher the temperature of the target object, the stronger the infrared light radiated. When absorbing the infrared light radiated by the same infrared device, the darker the color of the object, the lower the infrared light intensity radiated. For example, when a white object and a black object are in adjacent positions and are irradiated by the same infrared device, the infrared light intensity value radiated by the white object is higher.

[0067] In some embodiments, when it is detected that the infrared light intensity value radiated by the target object is greater than or equal to a preset threshold, an infrared image of the target object captured by an infrared camera is acquired. The infrared camera can accurately capture the infrared image of the target object.

[0068] Step S102: If the infrared light intensity value is greater than the preset light intensity value, control the infrared camera to collect the image of the target object, obtain the target image, and determine the type of the target object.

[0069] In some embodiments, if the infrared light intensity value is greater than a preset light intensity value, the infrared camera is controlled to capture an image of the target object to obtain a target image. The infrared camera can accurately capture an image of the target object.

[0070] In some embodiments, the target object obtained from the target image is compared with preset data to determine the type of the target object; or, the target image is recognized by a preset neural network model to obtain the type of the target object; or, the type of the target object input by the wearer is obtained.

[0071] In some embodiments, the target image is identified by a target object recognition model, and the type of the target object is determined to be the target type, wherein the target object recognition model is a pre-trained artificial intelligence model. The target object recognition model can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the target object recognition model can be a neural network model. By identifying the target image by the target object recognition model, the type of the target object can be accurately determined.

[0072] In some embodiments, when the target object recognition model is a neural network model, the method for training the preset target object recognition model can be: obtaining a sample data set, the sample data set includes multiple sample data, each sample data includes a target image and a type of mark in the target image; obtaining a sample data from the sample data set as the target sample data; inputting the target sample data into the preset neural network model for training to obtain a predicted type; determining whether the preset neural network model converges according to the type of mark and the predicted type, and if the preset neural network model does not converge, continuing to perform the steps of obtaining a sample data from the sample data set as the target sample data; inputting the target sample data into the preset neural network model for training to obtain a predicted type, until the preset neural network model converges to obtain the preset target object recognition model. Wherein, the preset neural network model includes but is not limited to a convolutional neural network model, a recurrent convolutional neural network model, and a recurrent convolutional neural network model, etc.

[0073] In some embodiments, according to the type of mark and the type of prediction, the method for determining whether the preset neural network model converges can be: according to the type of mark and the type of prediction, determine the loss value of the preset neural network model; when the loss value is greater than or equal to the preset loss value, determine that the preset neural network model has not converged; when the loss value is less than the preset loss value, determine that the preset neural network model has not converged. Among them, the preset loss value can be set to 0.02. By calculating the loss value of the model, it is possible to accurately determine whether the preset loss value converges, which greatly improves the accuracy of the model.

[0074] In some embodiments, the loss value of the preset neural network model can be determined based on the marked type and the predicted type by calculating the cosine similarity between the marked type and the predicted type to obtain a similarity value, and subtracting the similarity value from the unit 1 to obtain a loss value.

[0075] Step S103: If the type of the target object is a target type, a pixel value of each pixel of the target object in the target image is obtained, and a pixel difference between each pixel and an adjacent pixel is calculated.

[0076] Among them, the target types include fruit types and vegetable types, etc.

[0077] In some embodiments, the target image is identified by using a preset target object recognition model, and when it is determined that the type of the target object is the target type, the pixel value of each pixel point in the target object in the target image is obtained.

[0078] In some embodiments, the target image is subjected to image dimensionality reduction processing to obtain a target pixel image; the pixel value of each pixel in the target pixel image is obtained to obtain the pixel value of each pixel of the target object. By performing dimensionality reduction processing on the target image, the efficiency of pixel comparison can be effectively improved, thereby improving the efficiency of target object quality detection.

[0079] For example, the target image of the target object collected has a pixel size of 1600*1200, and the target image is subjected to 100-fold dimensionality reduction processing to obtain a target pixel image with a pixel size of 160*120. It should be noted that the multiple of the dimensionality reduction processing of the target image can be set according to actual conditions, and the embodiment of the present invention does not specifically limit this, for example, the dimensionality reduction multiple is 5 times, 10 times, 20 times, 50 times, 100 times, and the like.

[0080] It should be noted that the greater the infrared light absorbed by the object, the smaller the infrared light intensity value radiated by the object, and the smaller the infrared light intensity value, the smaller the pixel value in the target image. It is understandable that the infrared light intensity value radiated by the damaged area of ​​the target object is smaller than the infrared light intensity value radiated by the normal area.

[0081] In some embodiments, the pixel value of each pixel in the target image is subtracted from the pixel value of the adjacent pixel to obtain the pixel difference between each pixel and each adjacent pixel. By subtracting the pixel value of the pixel from the pixel value of each adjacent pixel, the pixel difference between the pixel and the adjacent pixel can be accurately obtained.

[0082] For example, Figure 3 As shown, the pixel differences between pixel 5 and pixel 1, pixel 2, pixel 3, pixel 4, pixel 6, pixel 7, pixel 8 and pixel 9 are calculated respectively to obtain multiple pixel differences of pixel 5.

[0083] Step S104: Determine the quality of the target object according to each of the pixel differences and a preset pixel difference of the current object type.

[0084] The preset pixel difference includes a preset first pixel difference and a preset second pixel difference. The preset first pixel difference and the preset second pixel difference are pre-stated based on a sample data set. In some embodiments, the preset first pixel difference and the preset second pixel difference can also be set according to actual conditions. For example, the preset first pixel difference of fruit is 100, and the preset second pixel difference is 200.

[0085] It should be noted that the quality of the object to be tested includes qualified products, defective products and inferior products, among which the qualified products indicate that the object to be tested is of quality suitable for normal use or consumption, the defective products indicate that the object to be tested has slight defects, and the inferior products indicate that the object to be tested is unqualified.

[0086] In some embodiments, a sample data set is obtained, the sample data set includes a plurality of sample data, each sample data includes a target image and quality of a target object of a target type object; a preset first pixel difference value and a preset second pixel difference value are determined according to the target image and quality of the target object in each sample data. By performing statistics on the sample data set, the preset first pixel difference value and the preset second pixel difference value can be accurately obtained, which greatly improves the efficiency and accuracy of target object quality detection.

[0087] In some embodiments, each sample data is classified according to the quality of the target object to obtain a qualified product quality sample data set, a defective product quality sample data set, and a low-quality product quality sample data set; the maximum pixel difference of the target image of the target object of each sample data in the qualified product quality sample data set is determined to obtain the first maximum pixel difference of each sample data in the qualified product quality sample data set; the mean of each first maximum pixel difference is calculated to obtain the pixel difference of the qualified product quality sample; the maximum pixel difference of the target image of the target object of each sample data in the defective product quality sample data set is determined to obtain the second maximum pixel difference of each sample data in the defective product quality sample data set; Perform mean calculation on each second maximum pixel difference to obtain the pixel difference of the defective product quality target object; determine the maximum pixel difference of the target image of the target object of each sample data in the inferior product quality sample data set to obtain the third maximum pixel difference of each sample data in the inferior product quality sample data set; perform mean calculation on each third maximum pixel difference to obtain the pixel difference of the inferior product quality target object; determine the mean of the pixel difference of the qualified product quality target object and the pixel difference of the defective product quality target object as the preset first pixel difference; determine the mean of the pixel difference of the defective product quality target object and the pixel difference of the inferior product quality target object as the preset second pixel difference.

[0088] In some embodiments, if all pixel differences are less than or equal to a preset first pixel difference, the quality of the target object is determined to be a qualified product; if all pixel differences are less than or equal to a preset second pixel difference, and there is a pixel difference greater than the preset first pixel difference, the quality of the target object is determined to be a defective product; if there is a pixel difference greater than the preset second pixel difference, the quality of the target object is determined to be a defective product.

[0089] Exemplarily, the first pixel difference is preset to be 100, and the second pixel difference is preset to be 200; the multiple pixel difference values ​​of each pixel point of the target object are all 100, and the quality of the target object is determined to be a qualified product. For another example, when the multiple pixel difference values ​​of each pixel point of the target object are less than or equal to 200, and at least one pixel difference value of the pixel point is greater than 100, the quality of the target object is determined to be a defective product. For another example, when at least one pixel difference value of the pixel point is greater than 200, the quality of the target object is determined to be a low-quality product.

[0090] It can be understood that when there is decay in the target object, the rotten points absorb more infrared light, and thus the infrared light intensity value radiated by the rotten points is smaller, and the infrared light intensity value radiated by the normal points is larger, resulting in the pixel difference between the normal points and the rotten points being greater than the preset second pixel difference, and thus the quality of the target object can be accurately determined to be inferior.

[0091] The target object detection method provided in the above embodiment obtains the infrared light intensity value radiated by the target object, and compares the infrared light intensity value with the preset light intensity value. If the infrared light intensity value is less than or equal to the preset light intensity value, the wearable device is controlled to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light; if the infrared light intensity value is greater than the preset light intensity value, the infrared camera is controlled to capture the image of the target object, obtain the target image, and determine the type of the target object; if the type of the target object is the target type, the pixel value of each pixel of the target object in the target image is obtained, and the pixel difference between each pixel and the adjacent pixel is calculated; the quality of the target object is determined according to each pixel difference and the preset pixel difference of the current object type. In the present application, according to the pixel difference between each pixel in the target image of the target object, it is possible to accurately determine whether the target object has rotten bad pixels, which greatly improves the efficiency and accuracy of target object quality detection.

[0092] See also Figure 4 , Figure 4 A schematic block diagram of a target object detection device provided in an embodiment of the present application.

[0093] like Figure 4 As shown, the target object detection device 200 includes an acquisition module 210, a control module 220 and a determination module 230, wherein:

[0094] The acquisition module 210 is used to acquire the infrared light intensity value radiated by the target object;

[0095] The control module 220 is used to compare the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, control the wearable device to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light;

[0096] The control module 220 is further configured to control the infrared camera to capture the image of the target object to obtain a target image if the infrared light intensity value is greater than the preset light intensity value;

[0097] The determination module 230 is used to determine the type of the target object;

[0098] The acquisition module 210 is further configured to acquire the pixel value of each pixel of the target object in the target image and calculate the pixel difference between each pixel and an adjacent pixel if the type of the target object is a target type;

[0099] The determination module 230 is further configured to determine the quality of the target object according to each of the pixel differences and a preset pixel difference of the current object type.

[0100] In some embodiments, the infrared light intensity value radiated by the target object is collected by an infrared sensor or a camera with an infrared shooting function.

[0101] In some embodiments, the determination module 230 is further configured to:

[0102] Comparing the target object obtained from the target image with preset data to determine the type of the target object; or,

[0103] Identify the target image using a preset target object recognition model to obtain the type of the target object; or,

[0104] The type of the target object input by the wearer is obtained.

[0105] In some embodiments, the acquisition module 210 is further used to:

[0106] Performing image dimension reduction processing on the target image to obtain a target pixel image;

[0107] The pixel value of each pixel in the target pixel image is obtained to obtain the pixel value of each pixel of the target object.

[0108] In some embodiments, the determination module 230 is further configured to:

[0109] If all the pixel differences are less than or equal to the preset first pixel difference, it is determined that the quality of the target object is qualified;

[0110] If all the pixel differences are less than or equal to the preset second pixel difference, and there is a pixel difference greater than the preset first pixel difference, determining that the quality of the target object is a defective product;

[0111] If there is a pixel difference greater than the preset second pixel difference, the quality of the target object is determined to be a defective product.

[0112] In some embodiments, the determination module 230 is further configured to:

[0113] Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising a target image and a quality of a sample target object;

[0114] The preset first pixel difference value and the preset second pixel difference value are determined according to the target image and the quality of the sample target object in each of the sample data.

[0115] In some embodiments, the determination module 230 is further configured to:

[0116] Determining whether the target object is within the field of view of the infrared camera;

[0117] If the target object is not within the field of view of the infrared camera, a prompt message indicating that the target object is not within the field of view is output to remind the wearer to switch the acquisition posture;

[0118] When it is determined that the target object is within the field of view of the infrared camera, a target image is obtained by capturing an image of the target object by the infrared camera.

[0119] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned target object detection device can refer to the corresponding process in the aforementioned target object detection method embodiment, and will not be repeated here.

[0120] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a wearable device provided in an embodiment of the present application.

[0121] like Figure 5 As shown, the wearable device 300 includes an infrared camera 302, a processor 303 and a memory 304 connected via a system bus 301, wherein the memory 304 may include a storage medium and an internal memory.

[0122] The storage medium may store a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor may execute any target object detection method.

[0123] The processor 303 is used to provide computing and control capabilities to support the operation of the entire wearable device.

[0124] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any target object detection method.

[0125] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the present application scheme, and does not constitute a limitation on the wearable device to which the present application scheme is applied. The specific wearable device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0126] It should be understood that the processor 303 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0127] In one embodiment, the processor 303 is used to run a computer program stored in the memory to implement the following steps:

[0128] Obtaining an infrared light intensity value radiated by a target object, and comparing the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, controlling the wearable device to turn on a lighting device or reminding the wearer to turn on the lighting device to irradiate the target object with infrared light;

[0129] If the infrared light intensity value is greater than the preset light intensity value, controlling the infrared camera to capture an image of the target object, obtaining a target image, and determining the type of the target object;

[0130] If the type of the target object is a target type, obtaining a pixel value of each pixel of the target object in the target image, and calculating a pixel difference between each pixel and an adjacent pixel;

[0131] The quality of the target object is determined according to each of the pixel differences and a preset pixel difference of the current object type.

[0132] In one embodiment, the infrared light intensity value radiated by the target object is collected by an infrared sensor or a camera with an infrared shooting function.

[0133] In one embodiment, the processor 303, in implementing the determining of the type of the target object, is configured to implement:

[0134] Comparing the target object obtained from the target image with preset data to determine the type of the target object; or,

[0135] Identify the target image using a preset target object recognition model to obtain the type of the target object; or,

[0136] The type of the target object input by the wearer is obtained.

[0137] In one embodiment, when the processor 303 implements the step of obtaining the pixel value of each pixel of the target object in the target image, it is configured to implement:

[0138] Performing image dimension reduction processing on the target image to obtain a target pixel image;

[0139] The pixel value of each pixel in the target pixel image is obtained to obtain the pixel value of each pixel of the target object.

[0140] In one embodiment, the processor 303 implements the preset pixel difference including a preset first pixel difference, a preset second pixel difference and a preset third pixel difference; and determines the quality of the target object according to each of the pixel differences and the preset pixel difference of the current object type, to implement:

[0141] If all the pixel differences are less than or equal to the preset first pixel difference, it is determined that the quality of the target object is qualified;

[0142] If all the pixel differences are less than or equal to the preset second pixel difference, and there is a pixel difference greater than the preset first pixel difference, determining that the quality of the target object is a defective product;

[0143] If there is a pixel difference greater than the preset second pixel difference, the quality of the target object is determined to be a defective product.

[0144] In one embodiment, before obtaining the infrared light intensity value radiated by the target object, the processor 303 is further configured to:

[0145] Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising a target image and a quality of a sample target object;

[0146] The preset first pixel difference value and the preset second pixel difference value are determined according to the target image and the quality of the sample target object in each of the sample data.

[0147] In one embodiment, the processor 303 controls the infrared camera to capture the image of the target object to obtain the target image, so as to achieve:

[0148] Determining whether the target object is within the field of view of the infrared camera;

[0149] If the target object is not within the field of view of the infrared camera, a prompt message indicating that the target object is not within the field of view is output to remind the wearer to switch the acquisition posture;

[0150] When it is determined that the target object is within the field of view of the infrared camera, a target image is obtained by capturing an image of the target object by the infrared camera.

[0151] It should be noted that technicians in the relevant field can clearly understand that for the convenience and brevity of description, the specific working process of the wearable device described above can refer to the corresponding process in the aforementioned target object detection method embodiment, and will not be repeated here.

[0152] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the target object detection method of the present application.

[0153] Wherein, the computer-readable storage medium may be an internal storage unit of the wearable device described in the aforementioned embodiment, such as a hard disk or memory of the wearable device. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium may also be an external storage device of the wearable device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the wearable device.

[0154] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0155] It should also be understood that the term "and / or" used in the present specification refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0156] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application.

Claims

1. A target object detection method, characterized in that: The method comprises: Obtaining an infrared light intensity value radiated by a target object, and comparing the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, controlling the wearable device to turn on a lighting device or reminding the wearer to turn on the lighting device to irradiate the target object with infrared light; If the infrared light intensity value is greater than the preset light intensity value, controlling the infrared camera to capture an image of the target object, obtaining a target image, and determining the type of the target object; If the type of the target object is a target type, obtaining a pixel value of each pixel of the target object in the target image, and calculating a pixel difference between each pixel and an adjacent pixel; The quality of the target object is determined according to each of the pixel differences and a preset pixel difference of the current object type.

2. The target object detection method according to claim 1, characterized in that: The infrared light intensity value radiated by the target object is collected by an infrared sensor or a camera with an infrared shooting function.

3. The target object detection method according to claim 1, characterized in that: The determining the type of the target object includes: Comparing the target object obtained from the target image with preset data to determine the type of the target object; or, Identify the target image using a preset target object recognition model to obtain the type of the target object; or, The type of the target object input by the wearer is obtained.

4. The target object detection method according to claim 1, characterized in that: The obtaining of the pixel value of each pixel of the target object in the target image comprises: Performing image dimension reduction processing on the target image to obtain a target pixel image; The pixel value of each pixel in the target pixel image is obtained to obtain the pixel value of each pixel of the target object.

5. The target object detection method according to claim 1, characterized in that: The preset pixel difference value includes a preset first pixel difference value, a preset second pixel difference value and a preset third pixel difference value; The determining the quality of the target object according to each of the pixel differences and a preset pixel difference of the current object type includes: If all the pixel differences are less than or equal to the preset first pixel difference, it is determined that the quality of the target object is qualified; If all the pixel differences are less than or equal to the preset second pixel difference, and there is a pixel difference greater than the preset first pixel difference, determining that the quality of the target object is a defective product; If there is a pixel difference greater than the preset second pixel difference, the quality of the target object is determined to be a defective product.

6. The target object detection method according to claim 5, characterized in that: Before obtaining the infrared light intensity value radiated by the target object, the method further includes: Acquire a sample data set, the sample data set comprising a plurality of sample data, each of the sample data comprising a target image and a quality of a sample target object; The preset first pixel difference value and the preset second pixel difference value are determined according to the target image and the quality of the sample target object in each of the sample data.

7. The target object detection method according to any one of claims 1 to 6, characterized in that: The controlling the infrared camera to collect the image of the target object to obtain the target image includes: Determining whether the target object is within the field of view of the infrared camera; If the target object is not within the field of view of the infrared camera, a prompt message indicating that the target object is not within the field of view is output to remind the wearer to switch the acquisition posture; When it is determined that the target object is within the field of view of the infrared camera, a target image is obtained by capturing an image of the target object by the infrared camera.

8. A target object detection device, characterized in that: The target object detection device includes an acquisition module, a control module and a determination module, wherein: The acquisition module is used to acquire the infrared light intensity value radiated by the target object; The control module is used to compare the infrared light intensity value with a preset light intensity value, and if the infrared light intensity value is less than or equal to the preset light intensity value, control the wearable device to turn on the lighting device or remind the wearer to turn on the lighting device to irradiate the target object with infrared light; The control module is further configured to control the infrared camera to capture the image of the target object to obtain a target image if the infrared light intensity value is greater than the preset light intensity value; The determination module is used to determine the type of the target object; The acquisition module is further used to acquire the pixel value of each pixel of the target object in the target image and calculate the pixel difference between each pixel and an adjacent pixel if the type of the target object is a target type; The determination module is further configured to determine the quality of the target object according to each of the pixel differences and a preset pixel difference of the current object type.

9. A wearable device, characterized in that: The wearable device includes an infrared camera, a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the target object detection method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the target object detection method according to any one of claims 1 to 7 are implemented.

Images