CN-122002128-A - Power consumption control method, system, equipment and medium of thermal infrared imager

CN122002128ACN 122002128 ACN122002128 ACN 122002128ACN-122002128-A

Abstract

The application provides a power consumption control method, a system, equipment and a medium of a thermal infrared imager, wherein the method comprises the following steps of acquiring infrared image data of the thermal infrared imager and power consumption data of a target imaging component of the thermal infrared imager in real time; the method comprises the steps of carrying out feature analysis on infrared image data through a preset target detection model to obtain a preset target in an image, grading the importance of a current detection scene based on the preset target to obtain a attention degree grade, converting the attention degree grade into a quantized attention degree parameter according to a preset conversion rule, determining a target performance configuration file according to the quantized attention degree parameter, obtaining a lowest target power consumption value meeting the operation parameter based on the operation parameter and a preset performance power consumption mapping relation, and generating a power consumption adjustment signal according to the lowest target power consumption value and the power consumption data, so that power consumption adjustment is carried out on a target imaging component. By implementing the technical scheme provided by the application, the dynamic accurate matching of the power consumption and the imaging performance of the thermal infrared imager is realized.

Inventors

LIU JIANDONG
FAN YUANYUAN
GAO SHAN
XIA YINHUI

Assignees

北京东宇宏达科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260202

Claims (10)

1. A method for controlling power consumption of a thermal infrared imager, the method being applied to a power consumption control platform, the method comprising: Acquiring infrared image data of an infrared thermal imager in real time and power consumption data of a target imaging component in the infrared thermal imager; Performing feature analysis on the infrared image data through a preset target detection model to acquire a preset target in the infrared image data; Classifying importance of a current detection scene corresponding to the infrared image data based on the preset target to obtain a attention level, and converting the attention level into a corresponding quantized attention parameter through a preset conversion rule; Determining a target performance configuration file according to the quantized attention parameter, wherein the target performance configuration file comprises operation parameters, and the operation parameters comprise a target frame rate and a target resolution; Based on the operation parameters, obtaining the minimum target power consumption value required by meeting the operation parameters through a preset performance power consumption mapping relation; And generating a power consumption adjusting signal based on the lowest target power consumption value and the power consumption data, and adjusting the power consumption of the target imaging component according to the power consumption adjusting signal.
2. The method according to claim 1, wherein the performing feature analysis on the infrared image data by using a preset object detection model to obtain a preset object in the infrared image data specifically includes: Carrying out multi-stage convolution processing on the infrared image data through a multi-convolution layer of a backbone network in the target detection model, wherein the convolution processing of each stage outputs a feature image with corresponding resolution, the feature image output by the current stage is input to the next adjacent stage after being subjected to downsampling operation, a group of feature images formed by all feature images output by at least two stages are obtained, the group of feature images are used as multi-scale features of the preset target, and the feature images comprise thermal contours and shape information; Upsampling a first feature map generated in a later stage of any two adjacent stages of the multiscale features through a connecting layer in the target detection model, and fusing the upsampled first feature map with a second feature map to obtain a fused feature map, wherein the second feature map is generated in a previous stage of any two adjacent stages, and the fused feature map is subjected to multi-branch convolution processing through a preset receptive field enhancement module to generate enhanced fusion features; And classifying the enhanced fusion features through a detection head in the target detection model, determining a target class, carrying out regression processing on the enhanced fusion features through a regression head in the detection head, determining a boundary frame, and combining the target class and the boundary frame to obtain the preset target.
3. The method according to claim 1, wherein the classifying the importance of the current detected scene corresponding to the infrared image data based on the preset target to obtain a attention level, and converting the attention level into a corresponding quantized attention parameter through a preset conversion rule specifically includes: acquiring environmental parameters acquired by a sensor pre-configured in the thermal infrared imager, wherein the environmental parameters comprise temperature; Determining the attention level of the current detection scene through a preset scene classification and grading system based on the target type of the preset target and the environment parameter; And converting the attention level into the quantized attention parameter through a preset mapping relation.
4. A method according to claim 3, wherein said determining said attention level of said current detected scene by a preset scene classification and hierarchy based on a target type of said preset target and said environmental parameter, comprises: If a first target exists in the preset targets, the first target belongs to a preset high importance category, or the moving speed of the first target exceeds a first speed threshold, or the thermal abnormality change rate of the first target exceeds a first change rate threshold, or the temperature exceeds a first temperature threshold, determining the attention degree grade as a first grade; Judging whether a second target exists in the preset targets or not if the first target does not exist in the preset targets, wherein the second target belongs to a preset middle importance category, or the moving speed of the second target exceeds a second speed threshold, or the thermal abnormality change rate of the second target exceeds a second change rate threshold, the second speed threshold is smaller than the first speed threshold, the second change rate threshold is smaller than the first change rate threshold, and if the second target exists, the attention rate grade is determined to be a second grade; and when the first target and the second target are not present in the preset targets, determining the attention level as a third level, wherein the first level is higher than the second level, and the second level is higher than the third level.
5. The method according to claim 1, wherein determining a target performance profile according to the quantized attention parameter comprises: Acquiring equipment state data of the thermal infrared imager, wherein the equipment state data comprises residual electric quantity and the temperature of the target imaging component; Calculating a first candidate performance configuration file according to the quantized attention parameter through a preset conservative power consumption mapping relation, wherein the first candidate performance configuration file comprises a first operation parameter and a first imaging quality threshold; calculating a second candidate performance configuration file according to the quantized attention parameter through a preset priority performance mapping relation, wherein the second candidate performance configuration file comprises a second operation parameter and a second imaging quality threshold; when the residual electric quantity is lower than a preset electric quantity threshold value and/or the temperature is higher than a preset temperature threshold value, selecting the first candidate performance configuration file as the target performance configuration file; and when the residual electric quantity is higher than the electric quantity threshold value and the temperature is lower than the temperature threshold value, selecting the second candidate performance configuration file as the target performance configuration file, wherein the total pixel processing amount per unit time corresponding to the operation parameter in the first candidate performance configuration file is lower than the total pixel processing amount per unit time corresponding to the operation parameter in the second candidate performance configuration file, and the total pixel processing amount per unit time is the product of the target frame rate and the target resolution.
6. The method according to claim 1, wherein the generating a power consumption adjustment signal based on the lowest target power consumption value and the power consumption data and performing power consumption adjustment on the target imaging component according to the power consumption adjustment signal, specifically comprises: determining an imaging quality index of the target imaging assembly according to the signal-to-noise ratio of the infrared image data; Acquiring a target imaging quality threshold in the target performance configuration file; When the imaging quality index is lower than the target imaging quality threshold, calculating a quality difference value between the imaging quality index and the target imaging quality threshold, and converting the quality difference value into a power consumption enhancement signal through a preset mapping relation; when the imaging quality index is not lower than the target imaging quality threshold, calculating a power consumption error based on the lowest target power consumption value and the power consumption data, and generating a power consumption weakening signal based on the power consumption error; And adjusting the power consumption of the target imaging component according to the power consumption enhancing signal or the power consumption weakening signal.
7. The method according to claim 6, wherein said determining an imaging quality indicator of the target imaging assembly from a signal-to-noise ratio of the infrared image data, in particular comprises: identifying and dividing a signal area and a noise area in the infrared image data, wherein the signal area is an image area containing the preset target, and the noise area is an image area not containing the preset target; calculating the arithmetic average value of the pixel values of all pixels in the signal area to obtain a signal average value; calculating standard deviation of pixel values of all pixels in the noise area to obtain noise standard deviation; Dividing the signal average value by the noise standard deviation to obtain a signal-to-noise ratio, and taking the signal-to-noise ratio as the imaging quality index.
8. The power consumption control system of the thermal infrared imager is characterized by comprising a data acquisition module, a target detection module, a scene conversion module, a performance decision module, a power consumption calculation module and a power consumption adjustment module, wherein: The data acquisition module is configured to acquire infrared image data of the thermal infrared imager in real time and power consumption data of a target imaging component in the thermal infrared imager; The target detection module is configured to perform feature analysis on the infrared image data through a preset target detection model to obtain a preset target in the infrared image data; The scene conversion module is configured to classify the importance of the current detection scene corresponding to the infrared image data based on the preset target to obtain a attention level, and convert the attention level into a corresponding quantized attention parameter through a preset conversion rule; The performance decision module is configured to determine a target performance configuration file according to the quantized attention parameter, wherein the target performance configuration file comprises operation parameters, and the operation parameters comprise a target frame rate and a target resolution; The power consumption calculation module is configured to obtain a minimum target power consumption value required by meeting the operation parameters through a preset performance power consumption mapping relation based on the operation parameters; The power consumption adjusting module is configured to generate a power consumption adjusting signal based on the lowest target power consumption value and the power consumption data, and adjust the power consumption of the target imaging component according to the power consumption adjusting signal.
9. An electronic device comprising a processor, a memory, a user interface, and a network interface, the memory for storing instructions, the user interface and the network interface each for communicating with other devices, the processor for executing instructions stored in the memory to cause the electronic device to perform the method of any of claims 1-7.
10. A computer readable storage medium storing instructions which, when executed, perform the method of any one of claims 1-7.

Description

Power consumption control method, system, equipment and medium of thermal infrared imager Technical Field The invention relates to the technical field of thermal infrared imager control, in particular to a method, a system, equipment and a medium for controlling power consumption of a thermal infrared imager. Background The infrared thermal imager has wide application in the fields of security protection, industry, portable monitoring and the like due to the unique imaging capability. Particularly, in a battery-powered scenario, the device needs to operate for a long time, so that the power consumption is reduced as much as possible and the endurance is prolonged while the detection performance is ensured, which is an important technical target in the field. The working modes in the prior art are mostly fixed preset mechanisms. Such as a timed sleep or manual low power mode, the power consumption adjustment mechanism of which operates independently of the real-time image data stream. In particular, the timed dormancy is based on a preset time sequence, which means that the operational status of the device is not directly related to whether a critical event occurs within the scene. The conversion of the working mode depends on manual instructions, and the applicability of the interaction mode is limited by the operation condition in the application requiring the system to run for a long time and fully autonomously. This mode of power consumption adjustment mechanism, separate from real-time image content, limits the ability of the device to autonomously and intelligently adjust power consumption according to scene changes. Disclosure of Invention In view of the above, the present application provides a method, a system, a device and a medium for controlling power consumption of a thermal infrared imager, so as to solve the above-mentioned problems. In a first aspect, a power consumption control method of a thermal infrared imager is provided, and the method is applied to a power consumption control platform, and includes: Acquiring infrared image data of the thermal infrared imager in real time, and acquiring power consumption data of a target imaging component in the thermal infrared imager; Performing feature analysis on the infrared image data through a preset target detection model to obtain a preset target in the infrared image data; Classifying the importance of the current detection scene corresponding to the infrared image data based on a preset target to obtain a attention level, and converting the attention level into a corresponding quantized attention parameter through a preset conversion rule; determining a target performance configuration file according to the quantized attention parameter, wherein the target performance configuration file comprises operation parameters, and the operation parameters comprise a target frame rate and a target resolution; based on the operation parameters, obtaining the minimum target power consumption value required by the operation parameters through a preset performance power consumption mapping relation; And generating a power consumption adjusting signal based on the lowest target power consumption value and the power consumption data, and adjusting the power consumption of the target imaging component according to the power consumption adjusting signal. According to the technical scheme, the real-time infrared image data is analyzed by utilizing the preset target detection model to obtain the preset target, a direct perception link between the power consumption control system and the image content stream is fundamentally established, a barrier that an adjusting mechanism in the prior art works independently of the data stream is broken, the importance of a scene is quantized based on the obtained preset target, a required target performance configuration file is determined according to the importance of the scene, abstract scene content is successfully converted into a specific performance decision, intelligent association is realized, an optimal power consumption value is calculated according to the determined performance configuration, and closed-loop adjustment is performed. A complete power consumption control closed loop driven by image content in real time is constructed, so that power consumption adjustment is not a timing or manual instruction irrelevant to scene events, but is dynamically dominant by the image content, thereby endowing the device with the capability of autonomously and intelligently adjusting power consumption according to scene changes. Optionally, performing feature analysis on the infrared image data through a preset target detection model to obtain a preset target in the infrared image data, which specifically includes: Carrying out multi-stage convolution processing on the infrared image data through multi-convolution layers of a backbone network in a target detection model, wherein the convolution processing of each stage outp