Thermal imaging monitoring video data wireless transmission communication method and system
By constructing a dynamic saliency index for thermal radiation and a routing stability index, and combining the ant colony algorithm to optimize the path and perform data packet shaping, the routing oscillation problem of the thermal imaging monitoring system during emergencies was solved, and stable transmission of key frames and efficient rescue were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN DIAMANTE TECH CO LTD
- Filing Date
- 2026-05-21
- Publication Date
- 2026-06-19
AI Technical Summary
In the event of an emergency, the routing protocol of the existing thermal imaging monitoring system is prone to oscillation, which can lead to the loss of key frames and weaken the early warning and emergency rescue capabilities for such events.
By constructing a dynamic saliency of thermal radiation, a routing stability index, and an adaptive volatile factor, and combining this with ant colony optimization, the optimal path is established, and physical data packet shaping is performed to ensure stable transmission of key frames.
It effectively distinguishes between thermal background and human dynamic features, ensures stable transmission of key frames, reduces protocol overhead, increases transmission throughput, and buys time for emergency rescue.
Smart Images
Figure CN122247916A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image communication control. More specifically, this invention relates to a wireless transmission communication method and system for thermal imaging surveillance video data. Background Technology
[0002] Against the backdrop of an aging population, thermal imaging technology has been widely applied in monitoring nursing homes, elderly people living at home, and hospitalized patients. These systems utilize thermal imaging technology to monitor the behavior of respondents around the clock while protecting personal privacy. Due to limitations in indoor layout or the need for temporary monitoring, these systems typically rely on wireless ad hoc networks or mesh networks to transmit the collected thermal imaging video back to the medical center in real time. Currently, existing technologies mainly use on-demand distance vector or standard ant colony optimization routing protocols to establish data transmission paths. Their core logic is to find the smoothest path simply based on physical parameters such as node hop count and received signal strength.
[0003] However, this traditional routing mechanism completely severs the connection between the transmission network and the monitoring content, and cannot adapt to the characteristics of the thermal imaging data stream value fluctuating drastically over time in medical monitoring scenarios. Under normal monitoring conditions, the interviewee's body temperature is stable and their activity is slow, and the video stream contains a lot of redundant background information; but when a sudden situation occurs in the field of view, such as an elderly person accidentally falling, a patient experiencing a sudden high fever causing an abnormal increase in body temperature or experiencing violent limb convulsions, the keyframe size of the video stream will increase instantaneously as the feature saliency increases. At this time, the requirements for the real-time performance and integrity of the data transmission reach their extreme to ensure that medical staff can make judgments based on clear images.
[0004] If the routing protocol continues to update the path according to the established fixed evaporation rate, it is very easy for minor fluctuations in the complex indoor radio electromagnetic environment to trigger route rediscovery or switching. Such routing oscillations can cause key frames to be lost or out of order when transmitting sudden high-dynamic monitoring video streams. This can cause the monitoring screen to appear pixelated, stuttered, or even black at the most critical moment when an elderly person falls or their condition suddenly changes, thus seriously weakening the emergency warning and emergency rescue capabilities of the intelligent monitoring system. Summary of the Invention
[0005] To address the technical problem that existing routing protocols neglect the urgency of content and are prone to routing oscillations when transmitting sudden critical videos, resulting in the loss of key frames and weakening the ability to provide early warning and emergency rescue for sudden events, this invention provides solutions in the following aspects.
[0006] In a first aspect, the present invention provides a wireless transmission communication method for thermal imaging surveillance video data, comprising:
[0007] The dynamic saliency of thermal radiation is determined based on the gray-level distribution of each pixel in the local neighborhood window of the current frame thermal imaging image and the difference in gray-level values of pixels between the current frame and the previous frame.
[0008] Obtain the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period, and determine the routing stability index by combining the thermal radiation dynamic significance.
[0009] The adaptive evaporation factor of the link is calculated based on the routing stability index, and the optimal path is determined by combining the ant colony algorithm with the adaptive evaporation factor, so as to lock the optimal path when the routing stability index exceeds the critical value.
[0010] The length of the shaped data packet is determined based on the average adaptive volatile factor of the optimal path, and the thermal imaging video data stream is physically shaped and sent according to the length of the shaped data packet.
[0011] Preferably, the dynamic saliency of thermal radiation is determined based on the grayscale distribution within the local neighborhood window of each pixel in the current frame of the thermal imaging image and the difference in grayscale values between the current frame and the previous frame, including:
[0012] For each pixel in the current frame, the thermal radiation characteristic value of the pixel in the current transmission cycle is determined by multiplying the square of its normalized gray value, the texture complexity factor in its local neighborhood, and the absolute value of the gray value difference between adjacent frames. The average value of the thermal radiation characteristic values of all pixels in the current frame is then calculated to obtain the dynamic saliency of thermal radiation. The texture complexity factor is determined by the ratio of the Shannon information entropy of the gray value in the local neighborhood of the pixel to the theoretical maximum information entropy.
[0013] Preferably, obtaining the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period includes:
[0014] The received signal strength and ambient background noise intensity of neighboring nodes are read through the physical layer interface, and the difference between the two is converted into a linear numerical ratio to obtain the linear signal-to-noise ratio.
[0015] The one-way transmission delay of all probe packets received within a transmission cycle is statistically analyzed, and the standard deviation of the one-way transmission delay is calculated to obtain the jitter standard deviation.
[0016] Preferably, determining the routing stability index includes:
[0017] Logarithmic mapping is performed on the dynamic significance of thermal radiation; the linear signal-to-noise ratio is mapped using the hyperbolic tangent function; the jitter standard deviation is normalized and squared based on the benchmark jitter constant to obtain the higher-order penalty term for jitter; the routing stability index is obtained by multiplying the mapped dynamic significance of thermal radiation, the mapped linear signal-to-noise ratio, the higher-order penalty term for jitter, and the preset stability coefficient.
[0018] Preferably, the method for obtaining the stability coefficient is as follows:
[0019] A chain-like topology network is constructed and a video stream is transmitted. The stability coefficient is gradually increased until the routing protocol no longer switches paths when impulse interference is introduced. The value at this point is determined as the critical locking value, and 1.2 times the critical locking value is set as the stability coefficient.
[0020] Preferably, the adaptive evaporation factor of the link is calculated based on the routing stability index, including:
[0021] Based on the difference between the routing stability index and the set critical stability index, the step change control quantity of the adaptive volatile factor is calculated through a variant of the Sigmoid function; the step change control quantity is used to adjust the basic volatile rate to obtain the adaptive volatile factor.
[0022] Preferably, the step of using the ant colony algorithm combined with an adaptive volatile factor to determine the optimal path includes:
[0023] The pheromone concentration of each link is updated using an adaptive evaporation factor, so that the historical pheromone of the links in the path-locked state is retained. After completing the search iteration, all valid paths are traversed and the path with the highest total pheromone concentration is determined as the optimal path.
[0024] Preferably, determining the shaped data packet length based on the average adaptive evaporation factor of the optimal path includes:
[0025] The packet length transition factor is determined by a cosine function based on the ratio of the average adaptive volatile factor to the base volatile rate; the shaped data packet length is determined based on the packet length transition factor, the standard Ethernet length, and the preset shaping gain coefficient.
[0026] Preferably, the step of physically shaping the thermal imaging video data stream according to the shaped data packet length before sending includes:
[0027] The thermal imaging video data stream is written into the transmission buffer queue, and the data is truncated according to the length of the shaped data packet as the segmentation threshold. If the length of the shaped data packet is greater than the standard Ethernet length, the jumbo frame transmission interface is called to send a single frame. If the length of the shaped data packet is less than or equal to the standard Ethernet length, it is fragmented and encapsulated for transmission.
[0028] Secondly, the present invention provides a wireless transmission and communication system for thermal imaging surveillance video data, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned wireless transmission and communication method for thermal imaging surveillance video data is implemented.
[0029] By adopting the above technical solution, a computer program is generated from the above-mentioned thermal imaging surveillance video data wireless transmission communication method and stored in the memory so that it can be loaded and executed by the processor. In this way, a terminal device can be made based on the memory and the processor for convenient use.
[0030] The beneficial effects of this invention are as follows: By constructing a dynamic saliency of thermal radiation that includes thermal radiation energy and texture information entropy, this invention distinguishes the dynamic vital characteristics of the interviewee from the smooth thermal background interference indoors from a physical perspective. This not only effectively protects the personal privacy of the elderly or patients but also solves the pain point of existing technologies that cannot accurately identify sudden monitoring needs caused by falls, sudden high fever, etc., based solely on brightness. This invention introduces a routing stability index and uses nonlinear hyperbolic tangent and higher-order jitter penalty terms to simulate a deep potential well effect when important video content such as elderly people falling is detected, achieving powerful topology capture of high-quality links. Based on the routing stability index, this invention designs a threshold adaptive evaporation mechanism that puts the path into a zero-evaporation locked state at critical moments, eliminating routing oscillations and ensuring the absolute stable transmission of key frames in thermal imaging. In addition, this invention physically shapes data packets based on an adaptive evaporation factor and automatically switches to jumbo frame mode in the path-locked state, thereby significantly reducing protocol overhead and increasing transmission throughput while ensuring stability, thus buying valuable time for subsequent emergency medical rescue decisions. Attached Figure Description
[0031] Figure 1 This is a flowchart illustrating a wireless transmission communication method for thermal imaging surveillance video data according to the present invention. Detailed Implementation
[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0033] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0034] This invention discloses a wireless transmission and communication method for thermal imaging surveillance video data, referring to... Figure 1 This includes steps S1-S4:
[0035] S1. Determine the dynamic saliency of thermal radiation based on the grayscale distribution of each pixel in the local neighborhood window of the current frame thermal imaging image and the difference in grayscale values of pixels between the current frame and the previous frame.
[0036] It should be noted that existing technologies typically rely solely on the grayscale values of pixels in thermal imaging, i.e., temperature, to determine the importance of video content. However, in complex indoor monitoring environments, high temperatures can often be caused by thermal background interference such as radiators or reflected light. While these areas have high energy, their textures are relatively smooth and uniform. In contrast, real monitoring targets (such as patients or the elderly) possess unique physical properties in thermal imaging: Firstly, due to the influence of clothing, differences in exposed skin, and the distribution of blood vessels on the body surface, the human body, as a heat source, exhibits a non-uniform thermal radiation gradient, resulting in high spatial texture complexity. Secondly, when a person experiences sudden physiological or behavioral changes such as a fall or convulsions, their image sequence undergoes dramatic instantaneous dynamic changes. Judging solely by brightness would lead to a large number of invalid bright backgrounds occupying high-priority channels. Therefore, this invention extracts composite features that truly reflect sudden abnormal human behavior by combining thermal radiation energy, spatial texture information, and temporal dynamic information.
[0037] Specifically, two consecutive thermal imaging images are acquired, denoted as the current frame and the previous frame. For each pixel in the current frame, a... A local neighborhood window.
[0038] The dynamic saliency of thermal radiation is determined based on the grayscale distribution within the local neighborhood window of a pixel.
[0039]
[0040] In the formula, This represents the dynamic saliency of thermal radiation during the current transmission cycle, characterizing the combined saliency of heat source intensity and dynamic texture. The larger the value, the more important the video content is, indicating the presence of a target with high energy and complex texture, such as a feverish or active patient. This represents the total number of pixels in the image; Indicates the first The grayscale value of each pixel represents the intensity of thermal radiation. This represents the maximum grayscale value that the sensor can detect, used to normalize the grayscale values of pixels. Based on the photoelectric response characteristics of the infrared focal plane detector, the infrared radiation collected by the front-end device undergoes photoelectric conversion, non-uniformity correction, and radiometric calibration processing, and its output digital grayscale value is... It can objectively quantify the relative magnitude of the target's infrared radiation power based on the grayscale output of the infrared detector. Approximately proportional to the target surface radiance, this invention employs [a method] to enhance the weight of high-temperature monitoring targets. Weighting was used to highlight the surge in heat radiation that occurs when an elderly person experiences a sudden high fever or falls. Indicates the first The Shannon information entropy of gray values in the local neighborhood of a pixel reflects the local spatial texture complexity of a thermal image. Represents the theoretical maximum information entropy, for The window's value is the logarithm of 9; This represents the texture complexity factor, because the folds in the clothing and the contours of the limbs of patients or the elderly have richer texture details than a smooth thermal background. Used to suppress low-entropy smooth background interference; Represents the absolute value of the grayscale difference between adjacent frames, used to lock dynamically changing regions. The larger the value, the more intense the target's movement. The product of the above three factors constructs a weighted filtering mechanism specifically for filtering static heat and cold source movements, enabling the dynamic significance of thermal radiation to accurately reflect the sudden state of real vital signs.
[0041] S2. Obtain the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period, and determine the routing stability index in combination with the thermal radiation dynamic significance.
[0042] It should be noted that in data transmission within wireless ad hoc networks, data packets typically tend to flow along paths with lower overhead. Existing routing metrics are usually linear and cannot create a strong capture effect. To ensure that thermal imaging data containing critical actions such as elderly people falling does not experience path drift during transmission, this invention constructs a routing stability index as a non-linear routing stability metric. When the video content is extremely important, i.e., the dynamic saliency of thermal radiation is extremely high and the link is extremely stable, the routing stability index increases sharply, forcing the routing protocol to stay on the current path and avoid switching to a suboptimal path.
[0043] Specifically, the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period are obtained: wireless communication nodes periodically send link probe packets containing transmission timestamps to their neighboring nodes; for nodes... Send to node Links, nodes Upon receiving the probe packet, the received signal strength and the background noise level of the current environment are read through the physical layer interface of the wireless communication module. Both are in decibels (dB) and milliwatts (mW). The signal-to-noise ratio (SNR) in decibels is obtained by subtracting the background noise level from the received signal strength, and then converted into a linear numerical ratio. The linear signal-to-noise ratio is obtained, where, Represents a node and The linear signal-to-noise ratio between them Indicates the received signal strength. Indicates the noise signal strength; simultaneously, the node The one-way transmission delay of each probe packet is calculated based on the sending timestamp and the local receiving timestamp in the probe packet. The transmission delay of all probe packets received in the most recent transmission cycle is counted, and the standard deviation of these transmission delay values is calculated as the jitter standard deviation of the link transmission cycle.
[0044] Based on the dynamic saliency of thermal radiation during the current transmission cycle, the linear signal-to-noise ratio between nodes, and the jitter standard deviation of the link transmission cycle, the routing stability index is obtained:
[0045]
[0046] In the formula, Represents a node To the node The routing stability index; the larger the value, the stronger the ability of the link to attract data flow. Indicates the dynamic significance of thermal radiation. This is used to map the dynamic saliency of fluctuating thermal radiation to a smooth logarithmic domain to reflect the nonlinear characteristics of visual perception. The larger the value, the greater the routing stability index; Represents a node and The linear signal-to-noise ratio between them; This represents the minimum linear signal-to-noise ratio threshold that guarantees error-free transmission. It is a hyperbolic tangent function used to provide nonlinear saturation characteristics. When the linear signal-to-noise ratio reaches a certain level, the routing stability exponent no longer increases linearly, which conforms to the limiting characteristics of channel capacity. The standard deviation of jitter in the link transmission period; This represents the reference jitter constant, used to normalize jitter. The square operation in the middle is a high-order penalty for jitter, which means that even a very small jitter will cause the routing stability index to decrease sharply, thereby losing the ability to capture critical data; This is a stability coefficient used to control the overall magnitude of the routing stability index.
[0047] Among them, the reference jitter constant The setup method is as follows: In a constant-temperature, interference-free microwave anechoic chamber, a vector network analyzer is used to measure the inherent noise floor jitter of the wireless node under no-load conditions. 1000 consecutive samples are taken, and the average value is recorded as the hardware limit jitter. Considering the difference between the actual deployment environment and the ideal laboratory environment, to avoid the algorithm being overly sensitive to environmental noise, an engineering safety factor is introduced, setting the baseline jitter constant to 3 times the hardware limit jitter. This invention considers any on-site jitter not exceeding 3 times the inherent hardware limit as a quasi-static ideal transmission state, thus ensuring high-order penalty sensitivity to severe jitter while tolerating normal engineering environmental disturbances.
[0048] Stability coefficient The setup method is as follows: Construct a chain topology network with 10 hops, transmit a standard test card video stream, and gradually increase the stability coefficient. This continues until the routing protocol stops switching paths when pulse interference is artificially introduced at an intermediate node. The value is the critical locking value; in this embodiment, 1.2 times the critical locking value is used as the stability coefficient. .
[0049] Minimum linear signal-to-noise ratio threshold to guarantee error-free transmission The setup method is as follows: In a shielded environment built in the laboratory, configure the wireless communication nodes to operate at the lowest modulation and coding strategy used in the actual deployment. At the transmitting end, continuously play the test video stream, gradually reducing the signal-to-noise ratio of the link using a programmable attenuator. Simultaneously, monitor the packet loss rate of video decoding at the receiving end, recording the moment when the video image first shows visible pixelation or when the packet loss rate just exceeds a certain threshold. The signal-to-noise ratio (SNR) in Bb is denoted as . In order to preserve link margin to cope with sudden interference, Plus to The safety redundancy is then converted into a linear value, which serves as... For example, measured for ,Pick Redundancy, then .
[0050] S3. Calculate the adaptive evaporation factor of the link based on the routing stability index, and use the ant colony algorithm in combination with the adaptive evaporation factor to establish the optimal path, so as to lock the optimal path when the routing stability index exceeds the critical value.
[0051] It should be noted that the pheromone evaporation in traditional ant colony algorithms is a unidirectional decay process, which lacks a memory protection mechanism when handling sudden critical business. This invention introduces a threshold adaptive evaporation mechanism based on the routing stability index: when the routing stability index exceeds a critical value, the algorithm simulates condensed matter physics characteristics to instantly reduce the pheromone evaporation rate to an extremely low level, achieving strong memory locking of the path and ensuring stable transmission of emergency monitoring videos; when the routing stability index is low, the algorithm simulates gaseous characteristics to maintain a high evaporation rate to keep the system's exploration activity.
[0052] Specifically, the adaptive volatile factor of the link is calculated, and the adaptive volatile factor satisfies the expression:
[0053]
[0054] In the formula, Represents a node arrive The adaptive volatile factor of the link has a value ranging from 0 to between; This represents the basic volatility, indicating the rate at which the system is forgotten under normal conditions. Indicates the routing stability index; This represents the set critical stability index; Indicates the switching steepness coefficient; A variant of the Sigmoid function, via and The difference controls the step change in volatile rate: when Less than When the function value approaches 1, Maintain at Nearby, high volatility is observed, at which point the system tends to explore new paths; when Greater than At that time, the function value rapidly approaches 0. The rapid decrease approaches zero, indicating zero evaporation and achieving path locking.
[0055] It should be noted that, according to the convergence criterion of the ant colony algorithm, the basic volatile rate... Typically, a value between 0.5 and 0.8 is selected. In this embodiment, the base volatility is used. The value is set to 0.6. In other embodiments, implementers can set it according to the network's response speed requirements to environmental changes.
[0056] Critical stability index The configuration method is as follows: Calculate the average route stability index of the system under normal operation (i.e., without high-risk targets), and set it to twice the average route stability index. This means that locking is only triggered when the event importance or link quality reaches twice the average. In other embodiments, implementers can adjust this based on the business's tolerance for false alarm rates.
[0057] Switch steepness coefficient The setup method is as follows: Simulate the linear change of the routing stability index from low to high in the simulation environment, observe the change curve of the volatile factor, and adjust accordingly. The value caused the volatility factor to increase from 0.9 times. Decreased to 0.1 times The process occurred Within a range of 10% above and below, in this embodiment The empirical value is 4. In other embodiments, implementers can set it according to their requirements for the smoothness of the lock state transition.
[0058] Furthermore, the pheromone concentration is updated based on the adaptive volatile factor:
[0059]
[0060] In the formula, This indicates the updated pheromone concentration; Indicates the current pheromone concentration; Represents the adaptive volatility factor, when When it approaches 0 at a critical moment, Approaching 1, making historical pheromones Almost all of them are preserved, and the paths are strongly memorized by the system; This indicates the pheromone increment left after this successful transmission.
[0061] Using the ant colony algorithm, multiple virtual ants perform path search and iteration within the current transmission cycle. In each iteration, an adaptive evaporation factor is used to update the pheromone concentration of each link on the path, so that the pheromone of high-quality links in the locked state is strongly preserved. After all iterations of the current cycle are completed, all valid paths that successfully reach the sink node from the source node are traversed, the total pheromone concentration accumulated on each path is compared, and the path with the highest total pheromone concentration is established as the current optimal path.
[0062] S4. Determine the length of the shaped data packet based on the average adaptive volatile factor of the optimal path, and then send the thermal imaging video data stream after physically shaping it according to the length of the shaped data packet.
[0063] It should be noted that when the path is in a low-volatility locked state, the channel state is extremely stable, like a laminar flow pipe, suitable for large blocks of data to pass through at high speed to reduce packet header overhead; when the path is in a high-volatility exploration state, the channel may fluctuate, like turbulent flow, suitable for small blocks of data to pass through discretely to reduce retransmission costs. This invention uses an adaptive volatility factor to physically shape data packets and adaptively adjusts the physical length of the data packets to match the current channel carrying state.
[0064] Specifically, the average adaptive evaporation factor of the current optimal path is obtained, and the shaped data packet length is determined based on the average adaptive evaporation factor:
[0065]
[0066] In the formula, Indicates the length of the reshaped data packet; Indicates the standard Ethernet length; This represents the shaping gain coefficient, used to control the maximum amplification ratio of the packet length; This represents the average adaptive volatile factor of the current optimal path; Indicates the basic volatility; The function is used in From 0 to Provides a smooth non-linear transition during changes: when When the value approaches 0, it indicates that the path is in a locked state. When the value approaches 1, the data packet length reaches its maximum value. To achieve giant frame transmission to increase throughput; when Approaching This indicates that the path is in the exploratory state. When the value approaches 0, the data packet length returns to the standard length. Or smaller, to ensure basic connectivity.
[0067] Among them, standard Ethernet length The setting method is as follows: according to the IEEE 802.3 standard, it is set to 1500 bytes. In other embodiments, the implementer can set it according to the MTU limit of the network hardware.
[0068] Shaping gain coefficient The setup method is as follows: Test the network device's maximum support for jumbo frames, and calculate the maximum supported length compared to the standard Ethernet length. The ratio, minus 1, is taken as... The upper limit is set to 0.5 in this embodiment, which means that the maximum allowable packet length increase is 50%. In other embodiments, the implementer can set it according to the router's cache size.
[0069] Furthermore, based on the calculated shaped data packet length, the thermal imaging video data stream is physically encapsulated and transmitted. Specifically:
[0070] Write the thermal imaging video data stream of the current transmission cycle into the send buffer queue, according to the shaped data packet length. The data in the buffer queue is truncated using a segmentation threshold. If If the length exceeds the standard Ethernet length, the giant frame transmission interface of the wireless communication module is invoked to encapsulate the captured large blocks of data into a single physical frame for transmission, thereby reducing the proportion of frame header overhead; if If the length is less than or equal to the standard Ethernet length, then follow the... The data is fragmented and encapsulated, and finally, the encapsulated physical frame is sent to the next hop node through the optimal path established in step S3.
[0071] This invention also discloses a wireless transmission and communication system for thermal imaging surveillance video data, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a wireless transmission and communication method for thermal imaging surveillance video data according to the present invention.
[0072] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.
[0073] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise expressly and specifically defined.
[0074] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.
Claims
1. A wireless transmission communication method for thermal imaging surveillance video data, characterized in that, include: The dynamic saliency of thermal radiation is determined based on the gray-level distribution of each pixel in the local neighborhood window of the current frame thermal imaging image and the difference in gray-level values of pixels between the current frame and the previous frame. Obtain the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period, and determine the routing stability index by combining the thermal radiation dynamic significance. The adaptive evaporation factor of the link is calculated based on the routing stability index, and the optimal path is determined by combining the ant colony algorithm with the adaptive evaporation factor, so as to lock the optimal path when the routing stability index exceeds the critical value. The length of the shaped data packet is determined based on the average adaptive volatile factor of the optimal path, and the thermal imaging video data stream is physically shaped and sent according to the length of the shaped data packet.
2. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, Based on the grayscale distribution of each pixel within its local neighborhood window in the current frame of the thermal imaging image and the difference in grayscale values between the current frame and the previous frame, the dynamic saliency of thermal radiation is determined, including: For each pixel in the current frame, the thermal radiation characteristic value of the pixel in the current transmission cycle is determined by multiplying the square of its normalized gray value, the texture complexity factor in its local neighborhood, and the absolute value of the gray value difference between adjacent frames. The average value of the thermal radiation characteristic values of all pixels in the current frame is then calculated to obtain the dynamic saliency of thermal radiation. The texture complexity factor is determined by the ratio of the Shannon information entropy of the gray value in the local neighborhood of the pixel to the theoretical maximum information entropy.
3. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The acquisition of the linear signal-to-noise ratio between nodes and the jitter standard deviation of the link transmission period includes: The received signal strength and ambient background noise intensity of neighboring nodes are read through the physical layer interface, and the difference between the two is converted into a linear numerical ratio to obtain the linear signal-to-noise ratio. The one-way transmission delay of all probe packets received within a transmission cycle is statistically analyzed, and the standard deviation of the one-way transmission delay is calculated to obtain the jitter standard deviation.
4. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The determination of the routing stability index includes: Logarithmic mapping is performed on the dynamic significance of thermal radiation; the linear signal-to-noise ratio is mapped using the hyperbolic tangent function; the jitter standard deviation is normalized and squared based on the benchmark jitter constant to obtain the higher-order penalty term for jitter; the routing stability index is obtained by multiplying the mapped dynamic significance of thermal radiation, the mapped linear signal-to-noise ratio, the higher-order penalty term for jitter, and the preset stability coefficient.
5. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 4, characterized in that, The method for obtaining the stability coefficient is as follows: A chain-like topology network is constructed and a video stream is transmitted. The stability coefficient is gradually increased until the routing protocol no longer switches paths when impulse interference is introduced. The value at this point is determined as the critical locking value, and 1.2 times the critical locking value is set as the stability coefficient.
6. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The adaptive evaporation factor of the link is calculated based on the routing stability index, including: Based on the difference between the routing stability index and the set critical stability index, the step change control quantity of the adaptive volatile factor is calculated through a variant of the Sigmoid function; the step change control quantity is used to adjust the basic volatile rate to obtain the adaptive volatile factor.
7. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The method of determining the optimal path using ant colony optimization combined with an adaptive volatile factor includes: The pheromone concentration of each link is updated using an adaptive evaporation factor, so that the historical pheromone of the links in the path-locked state is retained. After completing the search iteration, all valid paths are traversed and the path with the highest total pheromone concentration is determined as the optimal path.
8. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The step of determining the shaped data packet length based on the average adaptive evaporation factor of the optimal path includes: The packet length transition factor is determined by a cosine function based on the ratio of the average adaptive volatile factor to the base volatile rate; the shaped data packet length is determined based on the packet length transition factor, the standard Ethernet length, and the preset shaping gain coefficient.
9. The method for wireless transmission and communication of thermal imaging surveillance video data according to claim 1, characterized in that, The step of physically shaping the thermal imaging video data stream according to the shaped data packet length before sending includes: The thermal imaging video data stream is written into the transmission buffer queue, and the data is truncated according to the length of the shaped data packet as the segmentation threshold. If the length of the shaped data packet is greater than the standard Ethernet length, the jumbo frame transmission interface is called to send a single frame. If the length of the shaped data packet is less than or equal to the standard Ethernet length, it is fragmented and encapsulated for transmission.
10. A wireless transmission and communication system for thermal imaging surveillance video data, characterized in that, include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement a wireless transmission communication method for thermal imaging surveillance video data according to any one of claims 1-9.