Object information monitoring method, device and electronic equipment

Abstract

The present invention discloses a method, device and electronic device for monitoring object information, which detects an object to be measured in a target area, determines a first target area, tracks the object to be measured using the first target area that is easy to track, and determines a second target area that needs to be monitored for the object to be measured based on the first target area, so as to monitor the second target area and obtain the vital sign information of the object to be measured. The monitoring accuracy is effectively improved, and the problem of target detection failure and further missed detection caused by covering or moving the second target area can be effectively solved, which significantly improves the monitoring efficiency. And the tracking trajectory of the object to be measured is obtained by using the target tracking method, and thus the final temperature measurement result of the object to be measured is obtained according to the test values ​​of several frames on the tracking trajectory, which effectively avoids the problem of target jump instability and test value jump caused by single-frame detection, and significantly improves the stability of the test results.

Description

Technical Field

[0001] The present invention relates to the field of measurement technology, and in particular to an object information monitoring method, device and electronic equipment. Background Art

[0002] For some matters that use human characteristics as important detection indicators, it is difficult to determine physical signs in areas where people gather. For example, infectious diseases that use human body temperature as an important detection indicator. Non-contact and fast-responding body temperature measurement devices need to be installed in places where people gather or important entrances and exits (for example, airports, stations, shopping malls, community entrances, and various corporate entrances) to effectively screen people's body temperatures.

[0003] At present, for places with large flow of people, infrared temperature measurement is mainly used to achieve non-contact rapid human body temperature measurement. For example, a temperature measurement method with user cooperation can be used, such as: aiming the face at the camera in front of the designated screen to achieve temperature measurement. However, this method requires active cooperation from the user, and the temperature measurement efficiency is low. In addition, a temperature measurement method without user perception can also be used. For example, when the user passes through the temperature measurement area, a temperature measurement device including an infrared sensor and an image acquisition device is used to detect the temperature measurement area, and the temperature of the user in the temperature measurement area is detected, and an alarm is issued when a person with a high temperature appears. However, this method cannot perform effective detection for people with more facial obstructions, such as temperature measurement failures caused by the inability to perform normal face detection, and is prone to missed detection, inaccurate detection, and failure to determine the corresponding high-temperature person when high temperature is detected. Summary of the invention

[0004] Embodiments of the present invention provide an object information monitoring method, device and electronic equipment.

[0005] According to a first aspect of the present invention, there is provided an object information monitoring method, the method comprising: detecting an object to be measured in a target area; determining a first target area; determining a second target area of ​​the object to be measured corresponding to the first target area, the second target area having a relative position relationship with the first target area; tracking the object to be measured based on the first target area; collecting test values ​​of the second target area at a sampling moment during the target tracking process; and determining the vital sign information of the object to be measured based on the test values.

[0006] According to one embodiment of the present invention, determining the first target area includes: acquiring a first image of the target area; performing image recognition on the first image to obtain an image recognition result; and determining the first target area according to the image recognition result.

[0007] According to one embodiment of the present invention, the image recognition result includes several first target areas and several second target areas; accordingly, determining the second target area of ​​the object to be measured corresponding to the first target area includes: matching the several first target areas and the several second target areas according to the image recognition result and the relative position relationship to obtain a matching result; and determining the second target area of ​​the object to be measured corresponding to the first target area according to the matching result.

[0008] According to one embodiment of the present invention, the determining of the second target area of ​​the object to be tested corresponding to the first target area further includes: when the matching result shows that the first target area fails to match, collecting the test vital sign value of the first target area; and determining the second target area of ​​the object to be tested corresponding to the first target area based on the test vital sign value and the relative position relationship.

[0009] According to one embodiment of the present invention, the image recognition result includes: a feature vector of the first target area in the first image at each sampling moment; accordingly, the target tracking of the object to be measured is performed based on the first target area; including: determining the initial feature vector of the first target area at the previous sampling moment; obtaining the current sampling image at the current sampling moment; predicting the predicted position of the first target area in the current sampling image based on the feature vector of the first target area at the previous sampling moment; determining the current feature vector of the first target area in the predicted position; matching the current feature vector with the initial feature vector; when the current feature vector successfully matches the initial feature vector, determining that the first target area in the sampling image and the first target area at the previous sampling moment are the first target areas for the same object to be measured.

[0010] According to one embodiment of the present invention, the vital sign information of the object to be tested is determined based on the test vital sign value, including one of the following: determining the highest value of the test vital sign values ​​collected at multiple sampling moments as the vital sign information; or determining the average value of the test vital sign values ​​collected at multiple sampling moments as the vital sign information.

[0011] According to an embodiment of the present invention, determining the vital sign information of the subject to be tested according to the test vital sign value further includes: preprocessing the test vital sign values ​​collected at multiple sampling moments.

[0012] According to an embodiment of the present invention, the test value is the test body temperature value of the object to be measured; and the physical sign information is the actual body temperature value of the object to be measured.

[0013] According to a second aspect of the present invention, there is also provided an object information monitoring device, the device comprising: a detection module for detecting an object to be detected in a target area; a first determination module for determining a first target area; a second determination module for determining a second target area of ​​the object to be detected corresponding to the first target area, the second target area having a relative position relationship with the first target area; a tracking module for tracking the object to be detected based on the first target area; an acquisition module for acquiring a test vital sign value of the second target area at a sampling moment during the target tracking process; and an information determination module for determining the vital sign information of the object to be detected based on the test vital sign value.

[0014] According to the third aspect of the present invention, an electronic device is provided, which includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; and the processor is used to call program instructions in the memory to execute the above-mentioned object information monitoring method.

[0015] The object information monitoring method, device and electronic device of the embodiment of the present invention detect the object to be measured in the target area; determine the first target area; determine the second target area of ​​the object to be measured corresponding to the first target area, and the second target area has a relative position relationship with the first target area; based on the first target area, the object to be measured is tracked; at the sampling moment in the target tracking process, the test value of the second target area is collected; according to the test value, the vital sign information of the object to be measured is determined. In this way, the second target area that is easy to track the target is used to track the object to be measured, and the first target area that needs to be monitored by the object to be measured is determined according to the second target area, so as to monitor the first target area and obtain the vital sign information of the object to be measured. The monitoring accuracy is effectively improved, and the problem of missed detection when the first target area fails to be detected can be effectively solved, and the monitoring efficiency is significantly improved. And the tracking trajectory of the object to be measured is obtained by using the target tracking method, thereby obtaining the final temperature measurement result of the object to be measured according to the test values ​​of several frames on the tracking trajectory, effectively avoiding the problem of target jump instability and test value jump caused by single frame detection, and significantly improving the stability of the test result.

[0016] It should be understood that the teachings of the present invention are not required to achieve all of the beneficial effects described above, but specific technical solutions can achieve specific technical effects, and other embodiments of the present invention can also achieve beneficial effects not mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0018] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0019] Figure 1 A schematic diagram of the implementation process of the object information monitoring method according to an embodiment of the present invention is shown;

[0020] Figure 2 A schematic diagram showing an implementation flow of a specific application example of the object information monitoring method according to an embodiment of the present invention is shown;

[0021] Figure 3 A schematic diagram of a model structure of a specific application example of the object information monitoring method according to an embodiment of the present invention is shown;

[0022] Figure 4 A schematic diagram of the implementation process of the object information monitoring device according to an embodiment of the present invention is shown;

[0023] Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0025] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0026] First, the application scenario of the object information monitoring method of the embodiment of the present invention is exemplified. The object information monitoring method of the embodiment of the present invention can be applied to a body temperature measurement device to measure human body temperature. Specifically, a common image acquisition device is used to acquire visible light images to acquire images of the target area. For example, a camera can be used to acquire the body temperature of the object to be measured using a thermal infrared imaging device. Other devices involved in the body temperature measurement device are not described in detail here.

[0027] Of course, the object information monitoring method of the embodiment of the present invention can also be used to monitor other vital signs, such as: monitoring human skin color and performing statistics, monitoring facial features to analyze age, etc. Of course, it can also be applied to other applicable scenarios, and the present invention does not limit this.

[0028] Figure 1 FIG. 1 is a schematic diagram showing the implementation flow of the object information monitoring method according to an embodiment of the present invention. Figure 1 The object information monitoring method of the embodiment of the present invention at least includes the following operation flow: operation 101, detecting the object to be measured in the target area; operation 102, determining the first target area; operation 103, determining the second target area of ​​the object to be measured corresponding to the first target area, and the second target area has a relative position relationship with the first target area; operation 104, tracking the object to be measured based on the first target area; operation 105, collecting the test value of the second target area at the sampling time in the target tracking process; operation 106, determining the vital sign information of the object to be measured according to the test value.

[0029] In operation 101 , an object to be detected in a target area is detected.

[0030] In one embodiment of the present invention, when the object to be detected enters the target area, the object to be detected is automatically detected. Here, the object to be detected in the target area may be one or more.

[0031] In operation 102 , a first target area is determined.

[0032] In one embodiment of the present invention, a first image of the target area is first acquired, and image recognition is performed on the first image to obtain an image recognition result, and then the first target area is determined according to the image recognition result.

[0033] For example, the first image is an image of a target area captured by an image acquisition device of a body temperature measurement device, and the target area may be a designated area of ​​an entrance or exit of a certain area. The first target area is the head and shoulder area of ​​a human body, and the head and shoulder area of ​​a human body can be obtained by performing image recognition on the captured image.

[0034] The first target area is set to the head and shoulder area of ​​the human body because the first target area needs to be used for target tracking of the person to be tested in subsequent operations. When measuring the temperature of the person to be tested, the temperature of the face area needs to be collected. When the person to be tested lowers his head or the face area is covered, the face area cannot be captured. However, the face and shoulders have a certain relative position, and the contour of the head and shoulder area is relatively fixed, so the success rate of capturing the head and shoulder area image is very high. Of course, the entire upper body of the human body or the human body posture of the entire human body can also be used for target tracking to track the person to be tested, and multiple body temperature test values ​​of the person to be tested can be obtained during the target tracking process. The present invention does not specifically limit this.

[0035] In operation 103 , a second target area of ​​the object to be detected corresponding to the first target area is determined, and the second target area has a relative position relationship with the first target area.

[0036] In one embodiment of the present invention, when performing image recognition on the first image of the target area, image recognition results including a plurality of first target areas and a plurality of second target areas are simultaneously identified, and thus, the plurality of first target areas and the plurality of second target areas can be matched according to the image recognition results and the relative position relationship to obtain matching results. Furthermore, the second target area of ​​the object to be measured corresponding to one of the first target areas can be determined according to the matching results.

[0037] For example, the first target area is the head and shoulder area of ​​the human body, and the second target area is the face area of ​​the human body, and the face area is located in the upper half of the head and shoulder area. When a plurality of head and shoulder areas and a plurality of face areas are identified from the first image of the target area, for each head and shoulder area, it is determined that there is a face area in the upper half of the head and shoulder area, and the face area can be determined to be the face area of ​​the person to be tested corresponding to the head and shoulder area.

[0038] In one embodiment of the present invention, when the matching result shows that the first target area fails to match, the test vital sign value of the first target area can also be collected, and the second target area of ​​the object to be tested corresponding to the first target area can be determined based on the test vital sign value and the relative position relationship.

[0039] For example, for a certain head and shoulder area, when several human face areas identified from the first image of the target area cannot match this head and shoulder area, a thermal imaging image of the head and shoulder area can be collected to determine that the area located in the upper half of the head and shoulder area and with a higher temperature is the human face area of ​​the object to be tested corresponding to this head and shoulder area.

[0040] In operation 104 , target tracking is performed on the object to be detected based on the first target area.

[0041] In one embodiment of the present invention, when image recognition is performed on the first image of the target area, the feature vector of the first target area in the first image at each sampling moment can be obtained; accordingly, the initial feature vector of the first target area at the previous sampling moment can be determined; the current sampling image at the current sampling moment is obtained; based on the feature vector of the first target area at the previous sampling moment, the predicted position of the first target area in the current sampling image is predicted; the current feature vector of the first target area in the predicted position is determined; the current feature vector is matched with the initial feature vector; when the current feature vector successfully matches the initial feature vector, it is determined that the first target area in the sampling image and the first target area at the previous sampling moment are the first target areas for the same object to be measured.

[0042] Specifically, a frame of image for the target area can be obtained at each sampling moment. In the image at the previous sampling moment, the feature vector corresponding to the head and shoulder area T1 is W1. According to the feature vector corresponding to the head and shoulder area T1, it is predicted that the position corresponding to the head and shoulder area T1 at the current sampling moment is D1. Then, according to the image recognition result at the current sampling moment, the feature vector of the head and shoulder area T2 corresponding to the position D1 is W2. According to W1 and W2, the IOU (Intersection-over-Union) matching algorithm can be used to determine whether T1 and T2 are head and shoulder areas for the same person to be tested.

[0043] In operation 105 , at a sampling time in the target tracking process, a test value of the second target area is collected.

[0044] In one embodiment of the present invention, for the first target area in each frame image, the test value of the object to be tested corresponding to it is collected, and the test value of the corresponding second target area can be obtained at multiple sampling moments in the target tracking process, so that the actual value of the final second target area is determined based on the multiple test values. This effectively avoids the problems of unstable test data and missed detection during the monitoring process of the target to be tested, and significantly improves the accuracy of the test results.

[0045] In operation 106 , the vital sign information of the subject to be tested is determined according to the test value.

[0046] In one embodiment of the present invention, the test value is the test body temperature value of the subject to be tested; the physical sign information is the actual body temperature value of the subject to be tested. For example, for the body temperature monitoring of the person to be tested, the highest value in the entire monitoring process is taken, and for the detection of certain infectious diseases where the body temperature is greater than the set value as an important judgment indicator, the possibility of missing the person to be tested is minimized.

[0047] In one embodiment of the present invention, the vital sign information of the object to be tested is determined based on the test vital sign value, including one of the following: determining the highest value of the test vital sign values ​​collected at multiple sampling moments as the vital sign information; or determining the average value of the test vital sign values ​​collected at multiple sampling moments as the vital sign information.

[0048] For example, for the temperature monitoring of the person to be tested, the average value of the entire monitoring process is taken to effectively improve the reliability and stability of the temperature detection process of the person to be tested.

[0049] In one embodiment of the present invention, determining the physical sign information of the object to be tested according to the test physical sign value also includes: preprocessing the test physical sign values ​​collected at multiple sampling moments. For example, for the temperature monitoring of the person to be tested, before determining the actual temperature value of the person to be tested, the values ​​collected during the entire monitoring process that are obviously not in line with the human body temperature range, such as 30°C, 45°C, etc., can be deleted.

[0050] Figure 2 A schematic diagram of the implementation flow of a specific application example of the object information monitoring method according to an embodiment of the present invention is shown.

[0051] refer to Figure 2 The object information monitoring method of the embodiment of the present invention at least includes the following operation process:

[0052] Operation 201 : Detect the face region and the head and shoulder region, match the face region and the head and shoulder region, and extract the current target temperature of the face region from the corresponding thermal infrared image.

[0053] Operation 202 : for the head-shoulder region that is not matched with the human face region, predict the position of the human face region corresponding to the head-shoulder region according to the thermal infrared image, and extract the current target temperature of the human face region.

[0054] For example, the image recognition model is used to predict the face area, head and shoulder area and head and shoulder feature vector. First, the head and shoulder area are matched with the face area. Since the face area is definitely in the head and shoulder area, the face area and the head and shoulder area are paired according to the relative position of the face area in the upper part of the head and shoulder area. Then, the highest temperature of the face area is extracted as the temperature of the person to be tested on the thermal infrared image. For the head and shoulder area that cannot be matched with the face area due to occlusion, the area with the highest temperature is located in the head and shoulder area. According to the head and shoulder feature vector, the face area is predicted, and the temperature of the face area is recorded as the test temperature of the person to be tested at the current sampling moment.

[0055] In addition, a tracking frame target pool can be constructed here to identify and store the successfully matched head and shoulder areas and face areas as well as the matched image frames.

[0056] Operation 203: Determine the head-shoulder region and the feature vector of the head-shoulder region of the current frame. The feature vector of the head-shoulder region may be a 128-bit feature vector.

[0057] In operation 204 , the previous frame tracks the object to be detected, and the current frame loses the object to be detected, that is, the current frame does not have a head-shoulder region corresponding to the multi-tracked head-shoulder region in the previous frame.

[0058] In operation 205, a Kalman filter algorithm is used to predict the position of the head and shoulder region where tracking is lost in the current frame.

[0059] In operation 206 , the head-shoulder feature distance between the head-shoulder feature vector of the head-shoulder region at the predicted position and the head-shoulder feature vector of the head-shoulder region tracked in the previous frame is calculated using the IOU algorithm.

[0060] For example, the face area and the head and shoulders area can be matched in the current frame, and the target at the current position predicted by the Kalman filter can be matched with the effective tracking target in the previous frame (for example, the target successfully tracked in the previous frame and the target temporarily lost in the previous frame) to perform 128-dimensional feature matching.

[0061] Operation 207, using the Hungarian matching algorithm, the head and shoulder region and the face region are matched. Since the head and shoulder region is used for target tracking and the face region is used for information collection during the entire object information monitoring process, the head and shoulder region is identified as a tracking frame and the face region is identified as a detection frame.

[0062] Operation 208 : For the object to be detected whose tracking frame temporarily lost in the previous frame is successfully matched with the detection frame of the current frame in operation 207 , the tracking frame target pool is updated.

[0063] Operations 209 to 211, use the IOU matching algorithm to match the unmatched detection frame and the unmatched tracking frame again. Here, the unmatched detection frame refers to the detection frame in the previous frame image that fails to match the corresponding detection frame in the current frame image. Correspondingly, the unmatched tracking frame refers to the tracking frame in the previous frame image that fails to match the corresponding tracking frame in the current frame image. IOU matching is performed on the unmatched detection frame and the unmatched tracking frame until all tracking frames in the current frame image are compared with the detection frame one by one. For the detection frame and tracking frame that still cannot be matched, perform operation 212.

[0064] Operation 212 , in the next frame, the tracking frame is matched again using the Hungarian algorithm, and for the matched tracking frame, the tracking frame parameters are updated, the tracking frame target pool is updated, and the operation 204 is returned to be executed.

[0065] For the unmatched detection frame, operation 214 is performed, and for the inactivated tracking frame, operation 215 is performed.

[0066] In operation 214, for the unmatched tracking frame, operations 216 and 221 are performed to match the unmatched detection frame with the unmatched tracking frame again using the IOU matching algorithm.

[0067] Operation 215 , for the unmatched tracking frame, two cases are processed: for the tracking frame that has been tracked, operation 216 is executed to delete the tracking frame; for the tracking frame that has been lost, operation 218 is executed, and for the lost tracking frame, the process returns to operation 204 .

[0068] Operation 219, when the IOU matching algorithm is performed again in operation 218, if there is still no matching tracking frame, the tracking frame is deleted, and operation 221 is performed to move the unmatched tracking frame into an inactive tracking frame.

[0069] Operation 220 : When the inactivated tracking frame is matched by the detection frame, the tracking frame is activated and stored in the tracking frame target pool, and the process returns to execute operation 204 .

[0070] Through the above object information monitoring method, several persons to be tested who enter the target area are recorded with an accurate tracking trajectory. Each tracking trajectory obtains a stable high temperature as the final temperature measurement result of the person in the trajectory based on the test temperature sampling of several frames on the tracking trajectory. It can effectively avoid the target jump instability and temperature jump caused by single frame detection.

[0071] In addition, target tracking does not use the face area as the tracking target, but uses the head and shoulder area with very high visibility for target tracking. Matching and binding the head and shoulder area with the face area can effectively solve the problem that the face area of ​​the person to be tested on the tracking chain cannot be effectively tracked. It can effectively prevent the problem of monitoring failure caused by the loss of tracking of the object to be tested during the monitoring process, such as: the person to be tested looks down while walking, or the face is blocked, etc.

[0072] Figure 3 A schematic diagram of a model structure of a specific application example of the object information monitoring method according to an embodiment of the present invention is shown.

[0073] The input image is h*w*3 Figure 3 The model shown outputs two outputs of size h1*w1*3*140 and h2*w2*3*140. Among them, 3 represents the three anchor points corresponding to each grid point. So the model finally outputs 3*140 features at each grid point, the first 140 corresponds to the first anchor point, the second 140 corresponds to the second anchor point, and the third 140 corresponds to the third anchor point.

[0074] When training the model, first determine the anchor points of 6 scales, and convert the labels of the training data into h1*w1*3*(6+6+C) and h2*w2*3*(6+6+C) labels according to the anchor points. The first 6 represents dx, dy, dw, dh, prob, cls, which represents the encoding information of the head and shoulders area. The second 6 represents dx, dy, dw, dh, prob, cls, which represents the encoding information of the face area. The last C represents the number of ids of the tracking dataset, using one-hot labels.

[0075] The size of the anchor point can be obtained by clustering the size of the target in the training data. Then, for an image of the object to be tested, for a labeled box, calculate the anchor point of the box corresponding to the grid on the output size map, set the overlap greater than 0.3 as a positive sample, and ensure that an object has at least one anchor point. Determine the anchor point with a higher overlap as a positive sample. Assuming that the head and shoulder area is labeled, enter the encoding value in 1-6 of the 140 dimension, and the other positions are zero. If only the face area is labeled, enter the encoding value in 7-12 of 140, and the other positions are zero. If the head and shoulder tracking box is labeled, enter the encoding value of the labeling box in 1-6 of 140, and enter the one-hot value of the box tracking id in 13-140.

[0076] For the output of the model (6+6+128), 128 is connected to a 1*1*128*C classifier for tracking ID supervision, and the output of the model 128 represents the characteristics of the target. For inputs with only the head and shoulder area, only the loss generated by the encoding information 1-6 and the network output in 140 is calculated, and the loss generated by the detection and tracking of the face area is ignored. For inputs with only the face area, only the loss generated by the encoding information 7-12 in 140 and the network output is calculated, and the loss generated by the detection and tracking of the head and shoulder area is ignored. For the head and shoulder area, the loss generated by the encoding information 1-6 in 140 and the network output and the tracking ID loss of 13-128 are calculated at the same time.

[0077] Through the split supervised signal learning process in the above application example, we can effectively integrate human body data with only head and shoulder regions annotated, human body data with only face regions annotated, and human body data with both face and head and shoulder regions annotated. We can train a model that can use the head and shoulder regions for target tracking and the face region for information detection. When the amount of annotated data is limited, we can quickly perform self-learning on the model and optimize the model performance.

[0078] The object information monitoring method, device and electronic device of the embodiment of the present invention detect the object to be measured in the target area; determine the first target area; determine the second target area of ​​the object to be measured corresponding to the first target area, and the second target area has a relative position relationship with the first target area; based on the first target area, the object to be measured is tracked; at the sampling moment in the target tracking process, the test value of the second target area is collected; according to the test value, the vital sign information of the object to be measured is determined. In this way, the second target area that is easy to track the target is used to track the object to be measured, and the first target area that needs to be monitored by the object to be measured is determined according to the second target area, so as to monitor the first target area and obtain the vital sign information of the object to be measured. The monitoring accuracy is effectively improved, and the problem of missed detection when the first target area fails to be detected can be effectively solved, and the monitoring efficiency is significantly improved. And the tracking trajectory of the object to be measured is obtained by using the target tracking method, thereby obtaining the final temperature measurement result of the object to be measured according to the test values ​​of several frames on the tracking trajectory, effectively avoiding the problem of target jump instability and test value jump caused by single frame detection, and significantly improving the stability of the test result.

[0079] Similarly, based on the above object information monitoring method, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program. When the program is executed by a processor, the processor performs at least the following operation steps: operation 101, detecting the object to be measured in the target area; operation 102, determining the first target area; operation 103, determining a second target area of ​​the object to be measured corresponding to the first target area, and the second target area has a relative position relationship with the first target area; operation 104, based on the first target area, tracking the object to be measured; operation 105, collecting the test value of the second target area at the sampling moment in the target tracking process; operation 106, determining the vital sign information of the object to be measured according to the test value.

[0080] Further, based on the above object information monitoring method, an embodiment of the present invention also provides an object information monitoring device, such as Figure 4 The device 40 includes: a detection module 401, used to detect the object to be measured in the target area; a first determination module 402, used to determine the first target area; a second determination module 403, used to determine a second target area of ​​the object to be measured corresponding to the first target area, and the second target area has a relative position relationship with the first target area; a tracking module 404, used to track the object to be measured based on the first target area; an acquisition module 405, used to acquire the test vital sign value of the second target area at the sampling moment in the target tracking process; an information determination module 406, used to determine the vital sign information of the object to be measured according to the test vital sign value.

[0081] Furthermore, based on the above object information monitoring method, an embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, the device 50 includes at least one processor 501, and at least one memory 502 and a bus 503 connected to the processor 501; wherein the processor 501 and the memory 502 communicate with each other via the bus 503; the processor 501 is used to call the program instructions in the memory 502 to execute the above-mentioned object information monitoring method.

[0082] It should be noted that the above description of the object information monitoring device and the electronic device embodiment is different from the above description of the object information monitoring device and the electronic device embodiment. Figures 1 to 3 The description of the method embodiment shown is similar, with the same Figures 1 to 3 The method embodiment shown in the figure has similar beneficial effects, so it will not be described in detail. For technical details not disclosed in the embodiments of the object information monitoring device and the electronic device of the present invention, please refer to the aforementioned Figures 1 to 3 The method embodiment shown in the figure can be understood by referring to the description, and will not be described in detail for the sake of saving space.

[0083] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0084] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0085] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0086] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0087] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0088] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0089] 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. A method for monitoring object information, the method comprising: Detecting an object to be detected in a target area; determining a first target area; Determine a second target area of ​​the object to be measured corresponding to the first target area, the second target area having a relative position relationship with the first target area; Based on the first target area, tracking the object to be detected; At a sampling moment in the target tracking process, collecting a test value of the second target area; Determining the vital sign information of the subject to be tested according to the test value; Wherein, determining the first target area includes: acquiring a first image of the target area; performing image recognition on the first image to obtain an image recognition result; and determining the first target area according to the image recognition result; Wherein, the image recognition result includes a plurality of first target areas and a plurality of second target areas; Correspondingly, determining the second target area of ​​the object to be measured corresponding to the first target area includes: matching the plurality of first target areas and the plurality of second target areas according to the image recognition result and the relative position relationship to obtain a matching result; determining the second target area of ​​the object to be measured corresponding to the first target area according to the matching result; Among them, the determining of the second target area of ​​the object to be tested corresponding to the first target area also includes: when the matching result shows that the first target area fails to match, collecting the test vital sign value of the first target area; and determining the second target area of ​​the object to be tested corresponding to the first target area based on the test vital sign value and the relative position relationship.

2. The method according to claim 1, wherein the image recognition result comprises: A feature vector of the first target area in the first image at each sampling moment; Accordingly, the target tracking of the object to be detected based on the first target area includes: Determine an initial feature vector of the first target area at a previous sampling time; Get the current sampling image at the current sampling moment; Predicting a predicted position of the first target area in the current sampling image according to a feature vector of the first target area at a previous sampling time; determining a current feature vector of a first target area in the predicted position; Matching the current feature vector with the initial feature vector; When the current feature vector matches the initial feature vector successfully, it is determined that the first target region in the sampled image and the first target region at the previous sampling moment are the first target regions for the same object to be measured.

3. The method according to claim 1, determining the physical sign information of the subject to be tested according to the test physical sign value, comprising one of the following: Determine the highest value of the test vital sign values ​​collected at multiple sampling moments as the vital sign information; or The average value of the test vital sign values ​​collected at multiple sampling moments is determined as the vital sign information.

4. The method according to claim 3, determining the physical sign information of the subject to be tested according to the test physical sign value, further comprising: Preprocess the test vital sign values ​​collected at multiple sampling moments.

5. The method according to any one of claims 1 to 3, The test value is the test body temperature value of the subject to be tested; The physical sign information is the actual body temperature value of the object to be measured.

6. An object information monitoring device, the device comprising: A detection module, used for detecting an object to be detected in a target area; A first determining module, used to determine a first target area; A second determination module, used to determine a second target area of ​​the object to be detected corresponding to the first target area, the second target area having a relative position relationship with the first target area; A tracking module, used for tracking the object to be detected based on the first target area; A collection module, used for collecting the test vital sign value of the second target area at the sampling moment during the target tracking process; An information determination module, used to determine the vital sign information of the subject to be tested according to the test vital sign value; The first determination module is specifically used to obtain a first image of the target area; perform image recognition on the first image to obtain an image recognition result; and determine the first target area according to the image recognition result; Wherein, the image recognition result includes a plurality of first target areas and a plurality of second target areas; correspondingly, the second determination module is specifically used to match the plurality of first target areas and the plurality of second target areas according to the image recognition result and the relative position relationship to obtain a matching result; and determine the second target area of ​​the object to be measured corresponding to the first target area according to the matching result; Among them, the second determination module is also used to collect the test sign value of the first target area when the matching result shows that the first target area fails to match; and determine the second target area of ​​the object to be tested corresponding to the first target area based on the test sign value and the relative position relationship.

7. An electronic device, comprising at least one processor, and at least one memory and bus connected to the processor; wherein: The processor and the memory communicate with each other via the bus; The processor is used to call the program instructions in the memory to execute the object information monitoring method according to any one of claims 1-5.

Images