Truck compartment living body detection method, device, equipment and storage medium

Abstract

The present application is in the field of biometric technology, and provides a method, device, equipment and storage medium for detecting living things in a truck compartment, wherein the method comprises: controlling an infrared sensor to collect infrared signals in a truck compartment in real time, analyzing the infrared signals to obtain analysis results, and when it is determined that the analysis results meet conditions, controlling a camera to shoot the inside of the truck compartment to obtain a video inside the compartment, and when it is determined that there is a living thing in the truck compartment based on the video inside the compartment, outputting an alarm signal, thereby performing a preliminary judgment and analysis of the inside of the truck compartment through the infrared sensor, and when it is determined that the analysis results meet conditions, further combining the camera and image algorithm for refined analysis, thereby realizing automatic detection of living things in the truck compartment while improving detection accuracy and efficiency, and at a lower cost.

Description

Technical Field

[0001] The present application relates to the field of biometric identification technology, and more specifically, to a method, device, equipment and storage medium for detecting living things in a truck compartment. Background Art

[0002] Vehicles are used more and more frequently in people's daily lives. According to regulations, freight drivers are not allowed to carry living things such as people or livestock in truck compartments. Therefore, detecting vital signs in the vehicle has become an important measure to protect people's lives and property safety.

[0003] However, the reality is that there is a widespread phenomenon of drivers illegally transporting living things. Therefore, a monitoring method is needed to monitor whether there are living things in the car to provide reminders and warnings. Currently, liveness detection is generally performed by manpower, which is costly and inefficient. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for liveness detection in a truck compartment to improve the efficiency of liveness detection in a truck compartment.

[0005] In order to achieve the above-mentioned invention object, the present application provides a method for detecting living bodies in a truck compartment, which is applied to a terminal device, wherein the terminal device is communicatively connected to a monitoring device, wherein the monitoring device includes an infrared sensor and a camera, and the method includes:

[0006] Controlling the infrared sensor to collect infrared signals in the truck compartment in real time;

[0007] Analyzing the infrared signal to obtain an analysis result;

[0008] When it is determined that the analysis result meets the condition, controlling the camera to shoot the interior of the truck to obtain an interior video;

[0009] When it is determined based on the in-vehicle video that there is a living body in the truck compartment, an alarm signal is output.

[0010] Preferably, determining that the analysis result satisfies a condition includes:

[0011] When it is determined according to the analysis result that the coverage area of ​​the collected infrared signal is greater than a preset area, it is determined that the analysis result meets the condition.

[0012] Preferably, the infrared sensor includes a plurality of sub-infrared sensors, and the plurality of sub-infrared sensors are horizontally distributed in a matrix or at equal intervals, and the controlling the infrared sensor to collect infrared signals in the truck compartment in real time includes:

[0013] Each of the sub-infrared sensors is controlled to collect infrared signals in the truck compartment in real time to obtain multiple infrared signals.

[0014] Preferably, the analysis result includes whether the number of infrared signals is greater than a preset threshold, and determining, according to the analysis result, that the coverage area of ​​the collected infrared signals is greater than a preset area includes:

[0015] When it is determined according to the analysis result that the number of the infrared signals is greater than a preset threshold, it is determined that the coverage area of ​​the collected infrared signals is greater than a preset area.

[0016] Preferably, the controlling the infrared sensor to collect infrared signals in the truck compartment in real time includes:

[0017] When the truck is detected to be started, the infrared sensor is controlled to rotate along a preset angle, and after each rotation of one unit angle, the infrared sensor is controlled to collect infrared signals in the truck compartment in real time to obtain infrared signals of multiple angles of the infrared sensor.

[0018] Preferably, determining the presence of a living body in the truck compartment according to the in-vehicle video includes:

[0019] Extracting all video frames of the in-car video to obtain multiple video frames;

[0020] Performing grayscale processing on each of the video frames to obtain multiple first video frames;

[0021] For every two adjacent first video frames, subtract the pixel value of the first video frame with the later shooting time node from the pixel value of the first video frame with the earlier shooting time node to obtain the pixel difference between the two first video frames;

[0022] Calculate the average of the pixel differences between every two first video frames to obtain an average pixel difference;

[0023] Determining whether the average pixel difference is greater than a preset average pixel difference;

[0024] If so, it is determined that there is a living body in the truck compartment.

[0025] In one embodiment, the infrared sensor and the camera are arranged on the top of the truck compartment, and the infrared sensor and the camera are arranged opposite to each other.

[0026] The present application also provides a truck compartment living body detection device, which is applied to a terminal device, wherein the terminal device is communicatively connected with a monitoring device, wherein the monitoring device includes an infrared sensor and a camera, and the device includes:

[0027] A control module, used to control the infrared sensor to collect infrared signals in the truck compartment in real time;

[0028] An analysis module, used for analyzing the infrared signal to obtain an analysis result;

[0029] A determination module, configured to control the camera to shoot the interior of the truck compartment to obtain an interior video when it is determined that the analysis result meets a condition;

[0030] The alarm module is used to output an alarm signal when it is determined that there is a living body in the truck compartment based on the in-vehicle video.

[0031] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0032] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0033] The present application provides a method, device, equipment and storage medium for detecting living things in a truck compartment. By controlling an infrared sensor to collect infrared signals in the truck compartment in real time, the infrared signals are analyzed to obtain analysis results. When it is determined that the analysis results meet the conditions, a camera is controlled to shoot the inside of the truck compartment to obtain a video inside the compartment. When it is determined that there is a living thing in the truck compartment based on the video inside the compartment, an alarm signal is output, thereby performing a preliminary judgment and analysis of the truck compartment through the infrared sensor. When it is determined that the analysis results meet the conditions, a camera and an image algorithm are further combined to perform a refined analysis. While realizing automatic detection of living things in the truck compartment, the detection accuracy and efficiency are improved, and the cost is low. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of a flow chart of a method for detecting living body in a truck compartment according to an embodiment of the present application;

[0035] Figure 2 This is a schematic diagram of the installation of a monitoring device in a truck compartment according to an embodiment of the present application;

[0036] Figure 3 This is a schematic diagram of the structure of an infrared sensor according to an embodiment of the present application;

[0037] Figure 4 A schematic diagram of the sensing range of an infrared sensor according to an embodiment of the present application;

[0038] Figure 5 This is a schematic block diagram of the structure of a liveness detection device for a truck compartment according to an embodiment of the present application;

[0039] Figure 6 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0040] 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

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] The present application proposes a method for detecting live bodies in a truck compartment, the execution subject of which is a terminal device. The method for detecting live bodies in a truck compartment is used to solve the technical problems of the current method of performing live body detection in the compartment by manpower, which is high in cost and low in efficiency.

[0043] refer to Figure 1 , and combined with Figure 2-4 As shown, in one embodiment, the present application provides a method for detecting live bodies in a truck compartment, which is applied to a terminal device, wherein the terminal device is communicatively connected to a monitoring device, wherein the monitoring device includes an infrared sensor and a camera, and the method for detecting live bodies in a truck compartment includes:

[0044] S11, controlling the infrared sensor to collect infrared signals in the truck compartment in real time;

[0045] S12, analyzing the infrared signal to obtain an analysis result;

[0046] S13, when it is determined that the analysis result meets the condition, controlling the camera to shoot the interior of the truck to obtain an interior video;

[0047] S14. When it is determined based on the in-vehicle video that there is a living body in the truck compartment, an alarm signal is output.

[0048] As described in step S11 above, when it is necessary to detect a living body in a truck compartment, the terminal device responds to the start instruction, controls the infrared sensor installed in the truck compartment to detect the truck compartment, and collects the infrared signal in the truck compartment in real time. When the infrared sensor collects the infrared signal from the truck compartment, it sends the infrared signal to the terminal device, and the terminal device receives the infrared signal and pre-processes the infrared signal. The pre-processing method includes analog-to-digital conversion, noise reduction processing, etc. Among them, the start instruction includes the start signal of the truck, the opening signal that reaches the predetermined time or the closing signal of the switch, etc.; the infrared sensor is used to receive part of the infrared radiation of the living body in the truck compartment, and can sense whether an object with a temperature higher than the set value exists in the effective range monitored by the infrared sensor. When there is a living body in the truck compartment, the body temperature of the living body will generate infrared radiation, and the infrared sensor will receive the infrared radiation generated by the living body and generate an alarm signal. Among them, the living body includes a human or an animal.

[0049] As described in step S12 above, after receiving the infrared signal, the terminal device analyzes the infrared signal to determine the approximate location of the living body by analyzing which infrared sensor the infrared signal comes from; or analyzes the number of infrared sensors that have collected the infrared signal; or analyzes the intensity of the infrared signal. Accordingly, the analysis result includes the source of the infrared signal, the specific number of infrared sensors that have collected the infrared signal, and the specific intensity of the infrared signal.

[0050] When the number of infrared sensors that have collected infrared signals is greater than a preset threshold or the intensity of the infrared signals is greater than a preset intensity, it indicates that there is a high probability of a living body in the truck compartment. The preset threshold can be customized, such as 3.

[0051] As described in step S13 above, when the terminal device determines that the analysis result meets the condition, it can be that the number of infrared sensors that collect infrared signals is greater than a preset threshold or the intensity of the infrared signal is greater than a preset intensity, then the analysis result is determined to meet the condition, and at this time, the camera installed in the truck compartment is controlled to shoot the inside of the truck compartment to obtain a section of in-car video, and the camera sends the section of in-car video to the terminal device. The section of in-car video can be a continuous, uninterrupted video, or it can be a video obtained by splicing multiple videos taken at preset intervals and obtained by splicing the multiple videos.

[0052] Among them, the shooting duration of the in-vehicle video can be customized, such as set to 5 minutes. The camera can be installed on the four sides of the interior of the truck compartment, or on the top of the interior of the truck compartment, and the present invention does not make specific limitations.

[0053] As described in the above step S14, after the terminal device receives the in-vehicle video, it pre-processes the in-vehicle video. The pre-processing method includes noise reduction processing, resolution adjustment, etc., and then analyzes the pre-processed in-vehicle video to further determine whether there is a living body in the truck compartment. When it is determined that there is a living body in the truck compartment based on the in-vehicle video, the terminal device outputs an alarm signal.

[0054] Specifically, the terminal device can extract feature points from the video frames of the in-vehicle video, and compare the extracted feature points with the pre-collected image features of animals or human bodies. When it is determined that there are video frames in the in-vehicle video that match the image features of animals or human bodies, it is determined that there is a living body in the truck compartment, and the terminal device outputs an alarm signal. Among them, the image features of animals or human bodies can be pre-stored in the database, including feature points such as hands, heads or feet.

[0055] In one embodiment, if a living body is detected in the truck compartment, the terminal device processes the data obtained by the camera to generate a corresponding alarm message and sends the alarm message to the traffic police central control platform to remind the traffic police personnel that there is a truck illegally transporting living bodies; at the same time, the terminal device activates other sensors to detect the environmental parameters of the vehicle, including temperature, oxygen concentration, etc. Different temperature thresholds can be set in advance, and the terminal device analyzes and processes the current temperature obtained by the temperature sensor within each threshold range and generates corresponding alarm messages of different levels, and also sends the alarm message to the traffic police central control platform through the communication module. For example, the first temperature threshold is set to 30°, and the second temperature threshold is set to 40°. When the current temperature in the truck compartment is greater than 30°, a first-level alarm message is generated accordingly, and when the current temperature in the truck compartment is greater than 40°, a second-level alarm message is generated accordingly; or, when the current temperature in the truck compartment is greater than 30° and the current air quality in the truck compartment meets the third threshold, in a specific implementation, the current air quality meeting the third threshold may include the current oxygen concentration in the truck compartment being lower than 19.5%, the CO2 concentration reaching 1000PPM and / or the CO concentration reaching 50ppm, and a third-level alarm message is generated accordingly, so that the traffic police central control platform can make corresponding response strategies according to different levels of alarm information. In addition, for example, the second-level alarm message includes the contents such as the temperature in the car is too high and the life of the living body will be endangered if not handled in time, and the third-level alarm message includes the contents such as the temperature in the car is extremely high and the living body target in the truck compartment is in a life-threatening state. In addition, the terminal device sends the corresponding alarm information to the traffic police central control platform and can set the number of alarm sending times and sending methods according to the level of the alarm information. The sending methods include voice broadcast and / or vibration, which are not specifically limited in the present invention.

[0056] The present application provides a method for detecting living things in a truck compartment. The method controls an infrared sensor to collect infrared signals in the truck compartment in real time, analyzes the infrared signals, and obtains analysis results. When it is determined that the analysis results meet conditions, the camera is controlled to shoot the inside of the truck compartment to obtain a video inside the compartment. When it is determined that there is a living thing in the truck compartment based on the video inside the compartment, an alarm signal is output, thereby performing a preliminary judgment and analysis of the truck compartment through the infrared sensor. When the analysis results meet conditions, the camera and image algorithm are further combined to perform a refined analysis. While realizing automatic detection of living things in the truck compartment, the detection accuracy and efficiency are improved, and the cost is low.

[0057] In one embodiment, determining that the analysis result meets a condition may specifically include:

[0058] When it is determined according to the analysis result that the coverage area of ​​the collected infrared signal is greater than a preset area, it is determined that the analysis result meets the condition.

[0059] This embodiment requires the installation of monitoring equipment in the truck compartment, and the monitoring equipment includes a camera and an infrared sensor. The camera can take pictures of the situation in the compartment, and the infrared sensor can sense whether an object with a temperature higher than a set value exists within the effective range of the infrared sensor. The infrared sensing range and the camera shooting range basically overlap. The monitoring equipment can be placed at the top of the compartment, preferably covering the entire range of the compartment.

[0060] This embodiment is different from an infrared imager. Due to its high price, an infrared imager is not suitable for vehicle-mounted equipment. The infrared sensor has a limited sensing range (directly in front) and a limited angle space, that is, it can only sense the distance in front, so it cannot return information such as the volume of the sensed object. Therefore, this embodiment combines the infrared sensor with the camera, and only when the coverage area of ​​the infrared signal is greater than the preset area, it is determined that the analysis result meets the conditions, and then the camera is started to shoot the inside of the truck compartment, so as to further determine whether there is a living body in the truck compartment through the image algorithm, thereby ensuring the efficiency of live body detection and the accuracy of live body detection.

[0061] In one embodiment, reference Figure 2 As shown, the infrared sensor and the camera are arranged on the top of the truck compartment, and the infrared sensor and the camera are arranged opposite to each other.

[0062] In one embodiment, reference Figure 3 As shown, the infrared sensor includes a plurality of sub-infrared sensors, and the plurality of sub-infrared sensors are horizontally distributed in a matrix or at equal intervals. The control of the infrared sensor to collect infrared signals in the truck compartment in real time may specifically include:

[0063] Each of the sub-infrared sensors is controlled to collect infrared signals in the truck compartment in real time to obtain multiple infrared signals.

[0064] The infrared sensor of this embodiment can be designed as a multi-sensor joint arrangement, that is, multiple sub-infrared sensors are arranged at regular intervals, so that the sensing range can be expanded. Because living things are generally large in size (people, or a large number of poultry and pets in cages, etc.), they occupy a large space. Therefore, the volume range can be judged by multiple sensors. The sensing with a large volume range indicates that there is a higher probability of a living thing in the car. On the contrary, if only one sensor alarms, it may be a misjudgment or interference from other factors such as external light. Among them, multiple sub-infrared sensors can be arranged on the roof surface in a matrix, or multiple sub-infrared sensors can be arranged at intervals in one direction. The number of sub-infrared sensors depends on the area of ​​the living thing of interest.

[0065] When it is necessary to detect whether there is a living organism in the compartment, each sub-infrared sensor is controlled to collect infrared signals in the compartment of the truck in real time, and multiple infrared signals are obtained. The more sub-infrared sensors that alarm, the greater the possibility of the presence of a living organism.

[0066] In one embodiment, the analysis result includes whether the number of infrared signals is greater than a preset threshold, and determining, according to the analysis result, that the coverage area of ​​the collected infrared signals is greater than the preset area may specifically include:

[0067] When it is determined according to the analysis result that the number of the infrared signals is greater than a preset threshold, it is determined that the coverage area of ​​the collected infrared signals is greater than a preset area.

[0068] In this embodiment, when it is necessary to detect whether there is a living body in the compartment, each sub-infrared sensor is controlled to collect infrared signals in the compartment of the truck in real time to obtain multiple infrared signals, each infrared signal corresponds to an infrared sensor, so when the number of infrared signals is greater, the number of sub-infrared sensors that alarm is also greater, indicating that the possibility of the existence of a living body is greater. Therefore, when it is determined according to the analysis results that the number of infrared signals is greater than the preset threshold, it is determined that the coverage area of ​​the collected infrared signals is greater than the preset area, indicating that the possibility of the existence of a living body is greater, and at this time, the camera is started to shoot the inside of the truck compartment to further determine whether there is a living body in the truck compartment through the image algorithm, while ensuring the efficiency of the live body detection, the accuracy of the live body detection is guaranteed.

[0069] In one embodiment, controlling the infrared sensor to collect infrared signals in the truck compartment in real time may specifically include:

[0070] When the truck is detected to be started, the infrared sensor is controlled to rotate along a preset angle, and after each rotation of one unit angle, the infrared sensor is controlled to collect infrared signals in the truck compartment in real time to obtain infrared signals of multiple angles of the infrared sensor.

[0071] In this embodiment, the infrared sensor can be set to a rotating mode: this method can use only one infrared sensor, but set it to a rotating structure with two degrees of freedom, which can cover a conical area. Figure 4 shown.

[0072] This embodiment can scan a certain conical area by rotating the infrared sensor, extract infrared signals at different angles, and can continue to rotate for detection after the vehicle is started.

[0073] Specifically, when the truck is detected to be started, the terminal device can control the infrared sensor to rotate along a preset angle, such as within an angle range of 120 degrees, and after each rotation of a unit angle, control the infrared sensor to collect infrared signals in the truck compartment in real time to obtain infrared signals of multiple angles of the infrared sensor. Among them, a unit angle can be 1 degree, or it can be 10 degrees or 20 degrees as a basis, which is not specifically limited in this application.

[0074] In one embodiment, determining the presence of a living body in the truck compartment according to the in-vehicle video may specifically include:

[0075] Extracting all video frames of the in-car video to obtain multiple video frames;

[0076] Performing grayscale processing on each of the video frames to obtain multiple first video frames;

[0077] For every two adjacent first video frames, subtract the pixel value of the first video frame with the later shooting time node from the pixel value of the first video frame with the earlier shooting time node to obtain the pixel difference between the two first video frames;

[0078] Calculate the average of the pixel differences between every two first video frames to obtain an average pixel difference;

[0079] Determining whether the average pixel difference is greater than a preset average pixel difference;

[0080] If so, it is determined that there is a living body in the truck compartment.

[0081] In this embodiment, since the infrared sensor can sense objects with a temperature higher than a set value, when there is a living body in the car, the body temperature will generate infrared radiation, notifying the infrared sensor to generate an alarm signal. However, due to possible interference in the space and the limited accuracy of the device itself, false alarms may occur. Therefore, the infrared sensor alone cannot be used to determine whether a living body is present.

[0082] In this application, when the infrared sensor does not sense infrared rays, the monitoring device does not generate an alarm signal and the camera does not process data. When the infrared sensor generates a large area of ​​living body signals, the terminal device controls the camera to start, shoot the image inside the car, shoot to obtain a segment of N frames of in-car video, extract all video frames of the in-car video, obtain multiple video frames, perform grayscale processing on the multiple video frames, and convert them into the first video frame with a value of 0-255.

[0083] For every two adjacent first video frames, the pixel value of the first video frame with a later shooting time node is subtracted from the pixel value of the first video frame with a previous shooting time node to obtain the pixel difference between every two first video frames, that is, the pixel value of the first video frame of the second frame is subtracted from the pixel value of the first video frame of the first frame, the pixel value of the first video frame of the third frame is subtracted from the pixel value of the first video frame of the second frame, and so on, until the pixel value of the first video frame of the Nth frame is subtracted from the pixel value of the first video frame of the N-1 frame, and finally the pixel difference map of the N-1 frame is obtained.

[0084] Then, the average pixel difference between every two first video frames is calculated to obtain the average pixel difference. The average pixel difference can be obtained by taking the average value of these pixel difference images. When there is no living body in the car, the situation in the car is basically still, and the image changes between frames are small, so the average pixel difference will be very small. When there is a living body, it is likely that the living body will move, resulting in an increase in the average pixel difference. Therefore, a pixel difference threshold can be set as the preset average pixel difference based on the experiment. When it is greater than the threshold, it is determined that there is a living body in the truck compartment. Otherwise, it is determined that there is no living body in the truck compartment and the infrared sensor is falsely reported.

[0085] Reference Figure 5 In an embodiment of the present application, a liveness detection device for a truck compartment is provided, which is applied to a terminal device, wherein the terminal device is communicatively connected to a monitoring device, wherein the monitoring device includes an infrared sensor and a camera, and the device includes:

[0086] A control module 11 is used to control the infrared sensor to collect infrared signals in the truck compartment in real time;

[0087] An analysis module 12 is used to analyze the infrared signal to obtain an analysis result;

[0088] A determination module 13, configured to control the camera to shoot the interior of the truck compartment to obtain an interior video when it is determined that the analysis result meets a condition;

[0089] The alarm module 14 is used to output an alarm signal when it is determined that there is a living body in the truck compartment based on the in-vehicle video.

[0090] When it is necessary to detect a living body in a truck compartment, the terminal device responds to the start instruction, controls the infrared sensor installed in the truck compartment to detect the truck compartment, and collects the infrared signal in the truck compartment in real time. When the infrared sensor collects the infrared signal from the truck compartment, it sends the infrared signal to the terminal device, and the terminal device receives the infrared signal and pre-processes the infrared signal. The pre-processing method includes analog-to-digital conversion, noise reduction processing, etc. Among them, the start instruction includes the start signal of the truck, the opening signal that reaches the predetermined time, or the closing signal of the switch, etc.; the infrared sensor is used to receive part of the infrared radiation of the living body in the truck compartment, and can sense whether an object with a temperature higher than the set value exists in the effective range of the infrared sensor monitoring. When there is a living body in the truck compartment, the body temperature of the living body will generate infrared radiation, and the infrared sensor will receive the infrared radiation generated by the living body and generate an alarm signal. Among them, the living body includes a human or an animal.

[0091] After receiving the infrared signal, the terminal device analyzes the infrared signal to determine the approximate location of the living body by analyzing which infrared sensor the infrared signal comes from; or analyzes the number of infrared sensors that have collected the infrared signal; or analyzes the intensity of the infrared signal. Accordingly, the analysis results include the source of the infrared signal, the specific number of infrared sensors that have collected the infrared signal, and the specific intensity of the infrared signal.

[0092] When the number of infrared sensors that have collected infrared signals is greater than a preset threshold or the intensity of the infrared signals is greater than a preset intensity, it indicates that there is a high probability of a living body in the truck compartment. The preset threshold can be customized, such as 3.

[0093] When the terminal device determines that the analysis result meets the condition, it can be that the number of infrared sensors that collect infrared signals is greater than a preset threshold or the intensity of the infrared signal is greater than a preset intensity, then the analysis result is determined to meet the condition, and at this time the camera installed in the truck compartment is controlled to shoot the inside of the truck compartment to obtain a section of in-car video, and the camera sends the section of in-car video to the terminal device. The section of in-car video can be a continuous, uninterrupted video, or it can be a video obtained by splicing multiple videos taken at preset intervals and obtained by splicing the multiple videos.

[0094] Among them, the shooting duration of the in-vehicle video can be customized, such as set to 5 minutes. The camera can be installed on the four sides of the interior of the truck compartment, or on the top of the interior of the truck compartment, and the present invention does not make specific limitations.

[0095] After receiving the in-vehicle video, the terminal device pre-processes the in-vehicle video, including noise reduction processing, resolution adjustment, etc., and then analyzes the pre-processed in-vehicle video to further determine whether there is a living body in the truck compartment. When it is determined that there is a living body in the truck compartment based on the in-vehicle video, the terminal device outputs an alarm signal.

[0096] Specifically, the terminal device can extract feature points from the video frames of the in-vehicle video, and compare the extracted feature points with the pre-collected image features of animals or human bodies. When it is determined that there are video frames in the in-vehicle video that match the image features of animals or human bodies, it is determined that there is a living body in the truck compartment, and the terminal device outputs an alarm signal. Among them, the image features of animals or human bodies can be pre-stored in the database, including feature points such as hands, heads or feet.

[0097] In one embodiment, if a living body is detected in the truck compartment, the terminal device processes the data obtained by the camera to generate a corresponding alarm message and sends the alarm message to the traffic police central control platform to remind the traffic police personnel that there is a truck illegally transporting living bodies; at the same time, the terminal device activates other sensors to detect the environmental parameters of the vehicle, including temperature, oxygen concentration, etc. Different temperature thresholds can be set in advance, and the terminal device analyzes and processes the current temperature obtained by the temperature sensor within each threshold range and generates corresponding alarm messages of different levels, and also sends the alarm message to the traffic police central control platform through the communication module. For example, the first temperature threshold is set to 30°, and the second temperature threshold is set to 40°. When the current temperature in the truck compartment is greater than 30°, a first-level alarm message is generated accordingly, and when the current temperature in the truck compartment is greater than 40°, a second-level alarm message is generated accordingly; or, when the current temperature in the truck compartment is greater than 30° and the current air quality in the truck compartment meets the third threshold, in a specific implementation, the current air quality meeting the third threshold may include the current oxygen concentration in the truck compartment being lower than 19.5%, the CO2 concentration reaching 1000PPM and / or the CO concentration reaching 50ppm, and a third-level alarm message is generated accordingly, so that the traffic police central control platform can make corresponding response strategies according to different levels of alarm information. In addition, for example, the second-level alarm message includes the contents such as the temperature in the car is too high and the life of the living body will be endangered if not handled in time, and the third-level alarm message includes the contents such as the temperature in the car is extremely high and the living body target in the truck compartment is in a life-threatening state. In addition, the terminal device sends the corresponding alarm information to the traffic police central control platform and can set the number of alarm sending times and sending methods according to the level of the alarm information. The sending methods include voice broadcast and / or vibration, which are not specifically limited in the present invention.

[0098] The present application provides a truck compartment living body detection device, which controls an infrared sensor to collect infrared signals in the truck compartment in real time, analyzes the infrared signals to obtain analysis results, and when it is determined that the analysis results meet the conditions, controls a camera to shoot the inside of the truck compartment to obtain a video inside the compartment, and when it is determined that there is a living body in the truck compartment based on the video inside the compartment, outputs an alarm signal, thereby performing a preliminary judgment and analysis of the truck compartment through the infrared sensor, and when it is determined that the analysis results meet the conditions, further combining the camera and image algorithm to perform refined analysis, thereby realizing automatic detection of living bodies in the truck compartment while improving detection accuracy and efficiency, and at a low cost.

[0099] As described above, it can be understood that the various components of the truck compartment living body detection device proposed in the present application can realize the functions of any one of the truck compartment living body detection methods described above, and the specific structure will not be described in detail.

[0100] Reference Figure 6 In the embodiment of the present application, a computer device is also provided, whose internal structure can be as follows Figure 6 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a storage medium and an internal memory. The storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the storage medium. The database of the computer device is used to store relevant data of the truck compartment liveness detection method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a truck compartment liveness detection method is implemented.

[0101] The processor executes the truck compartment living body detection method, which includes:

[0102] Controlling the infrared sensor to collect infrared signals in the truck compartment in real time;

[0103] Analyzing the infrared signal to obtain an analysis result;

[0104] When it is determined that the analysis result meets the condition, controlling the camera to shoot the interior of the truck to obtain an interior video;

[0105] When it is determined based on the in-vehicle video that there is a living body in the truck compartment, an alarm signal is output.

[0106] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a method for detecting living bodies in a truck compartment is implemented. The method includes:

[0107] Controlling the infrared sensor to collect infrared signals in the truck compartment in real time;

[0108] Analyzing the infrared signal to obtain an analysis result;

[0109] When it is determined that the analysis result meets the condition, controlling the camera to shoot the interior of the truck to obtain an interior video;

[0110] When it is determined based on the in-vehicle video that there is a living body in the truck compartment, an alarm signal is output.

[0111] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in the present application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0112] In summary, the greatest beneficial effects of this application are:

[0113] The present application provides a method, device, equipment and storage medium for detecting living things in a truck compartment. By controlling an infrared sensor to collect infrared signals in the truck compartment in real time, the infrared signals are analyzed to obtain analysis results. When it is determined that the analysis results meet the conditions, a camera is controlled to shoot the inside of the truck compartment to obtain a video inside the compartment. When it is determined that there is a living thing in the truck compartment based on the video inside the compartment, an alarm signal is output, thereby performing a preliminary judgment and analysis of the truck compartment through the infrared sensor. When it is determined that the analysis results meet the conditions, a camera and an image algorithm are further combined to perform a refined analysis. While realizing automatic detection of living things in the truck compartment, the detection accuracy and efficiency are improved, and the cost is low.

[0114] 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, device, article or method 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, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0115] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting living things in a truck compartment, applied to a terminal device, wherein the terminal device is connected to a monitoring device for communication, and the monitoring device includes an infrared sensor and a camera, and is characterized in that: The method comprises: Controlling the infrared sensor to collect infrared signals in the truck compartment in real time; Analyzing the infrared signal to obtain an analysis result; When it is determined that the analysis result meets the condition, controlling the camera to shoot the interior of the truck to obtain an interior video; When it is determined according to the in-vehicle video that there is a living body in the truck compartment, an alarm signal is output; The determining that the analysis result meets a condition includes: When it is determined according to the analysis result that the coverage area of ​​the collected infrared signal is greater than a preset area, it is determined that the analysis result meets the condition; The controlling the infrared sensor to collect infrared signals in the truck compartment in real time includes: When the truck is detected to be started, the infrared sensor is controlled to rotate along a preset angle, and after each rotation of one unit angle, the infrared sensor is controlled to collect infrared signals in the truck compartment in real time to obtain infrared signals of multiple angles of the infrared sensor; or, The infrared sensor includes a plurality of sub-infrared sensors, and the plurality of sub-infrared sensors are horizontally distributed in a matrix or at equal intervals. The infrared sensor is controlled to collect infrared signals in the truck compartment in real time, including: Controlling each of the sub-infrared sensors to collect infrared signals in the truck compartment in real time to obtain multiple infrared signals; The determining, based on the in-vehicle video, that there is a living body in the truck compartment comprises: Extracting all video frames of the in-car video to obtain multiple video frames; Performing grayscale processing on each of the video frames to obtain multiple first video frames; For every two adjacent first video frames, subtract the pixel value of the first video frame with the later shooting time node from the pixel value of the first video frame with the earlier shooting time node to obtain the pixel difference between the two first video frames; Calculate the average of the pixel differences between every two first video frames to obtain an average pixel difference; Determining whether the average pixel difference is greater than a preset average pixel difference; If so, it is determined that there is a living body in the truck compartment.

2. The method according to claim 1, characterized in that The analysis result includes whether the number of infrared signals is greater than a preset threshold, and determining, according to the analysis result, that the coverage area of ​​the collected infrared signals is greater than a preset area includes: When it is determined according to the analysis result that the number of the infrared signals is greater than a preset threshold, it is determined that the coverage area of ​​the collected infrared signals is greater than a preset area.

3. The method according to claim 1, characterized in that The infrared sensor and the camera are arranged on the top of the truck compartment, and the infrared sensor and the camera are arranged opposite to each other.

4. A liveness detection device for a truck compartment, applied to a terminal device, wherein the terminal device is connected to a monitoring device for communication, and the monitoring device includes an infrared sensor and a camera, and is characterized in that: The device comprises: A control module, used to control the infrared sensor to collect infrared signals in the truck compartment in real time; An analysis module, used for analyzing the infrared signal to obtain an analysis result; A determination module, configured to control the camera to shoot the interior of the truck compartment to obtain an interior video when it is determined that the analysis result meets a condition; An alarm module, configured to output an alarm signal when it is determined based on the in-vehicle video that there is a living body in the truck compartment; The determining that the analysis result meets a condition includes: When it is determined according to the analysis result that the coverage area of ​​the collected infrared signal is greater than a preset area, it is determined that the analysis result meets the condition; The controlling the infrared sensor to collect infrared signals in the truck compartment in real time includes: When the truck is detected to be started, the infrared sensor is controlled to rotate along a preset angle, and after each rotation of one unit angle, the infrared sensor is controlled to collect infrared signals in the truck compartment in real time to obtain infrared signals of multiple angles of the infrared sensor; or, The infrared sensor includes a plurality of sub-infrared sensors, and the plurality of sub-infrared sensors are horizontally distributed in a matrix or at equal intervals. The infrared sensor is controlled to collect infrared signals in the truck compartment in real time, including: Controlling each of the sub-infrared sensors to collect infrared signals in the truck compartment in real time to obtain multiple infrared signals; The determining, based on the in-vehicle video, that there is a living body in the truck compartment comprises: Extracting all video frames of the in-car video to obtain multiple video frames; Performing grayscale processing on each of the video frames to obtain multiple first video frames; For every two adjacent first video frames, subtract the pixel value of the first video frame with the later shooting time node from the pixel value of the first video frame with the earlier shooting time node to obtain the pixel difference between the two first video frames; Calculate the average of the pixel differences between every two first video frames to obtain an average pixel difference; Determining whether the average pixel difference is greater than a preset average pixel difference; If so, it is determined that there is a living body in the truck compartment.

5. A computer device, characterized in that: include: processor; Memory; The memory stores a computer program, and the processor implements the truck compartment living body detection method according to any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for detecting living things in a truck compartment according to any one of claims 1 to 3.

Images