View field multi-fire-source positioning system and method based on DSP image processing

Abstract

The invention discloses a field-of-view multi-fire-source positioning system and method based on DSP image processing, and relates to the technical field of fire source image recognition. Comprising the steps of collecting continuous multi-frame image data, establishing display real-time circulation, storing and directly outputting a first frame image, checking whether a high gray value exists in a collection cache region when fire alarm information is received, sending a stop command to a water cannon immediately if the high gray value exists, solving a corresponding image feature map by utilizing an image difference method and storing the image feature map, and framing a flame frame by utilizing a greedy algorithm. Storing all flame frames greater than a threshold value in the field of view when there are multiple flames; the camera coordinate of the maximum flame block and the relative coordinates of the other flame blocks are calculated, the maximum flame block is positioned, the relative coordinates of the other flame blocks are combined, the screen coordinates of the flame blocks are calculated, and the flame block with the closer coordinate distance is selected to start the next round of scanning fire extinguishing. According to the invention, the effect of accurately positioning and extinguishing a fire source can be achieved.

Description

Technical Field

[0001] The invention relates to the technical field of fire source image recognition, and in particular to a field of view multi-fire source positioning system and method based on DSP image processing. Background Art

[0002] The large-space intelligent fire-fighting water cannon system is recognized as an efficient and fast fire-fighting technology, especially in that it can detect and deal with fires in the early stages. It can solve the fire-fighting problems of large-space buildings, realize fully automated fire-fighting, and provide strong technical support for the security of the construction industry.

[0003] Currently, intelligent fire water cannons locate fire sources based on infrared sensors, video image positioning and other methods. Document CN114187364A discloses a method for quickly locating a fire source, which uses infrared thermal imaging technology to record the current position of the center of gravity of the image in the field of view, uses a center of gravity algorithm to calculate the center of gravity coordinates of the fire source on the image, and calibrates the image in the horizontal and vertical directions so that the center of gravity of the fire source on the image is located at the center of the field of view to complete the positioning; Document CN105056455B invents a method and device for locating a fire cannon by image recognition, wherein a processing unit marks the center of the fire source area on the image through image analysis and processing, and the angle formed by the center of the flame area relative to the center of the image is the horizontal adjustment angle of the gun barrel according to the position of the center of the flame area. Thus, the positioning angle of the gun barrel is determined; Document CN104971458B discloses a method for identifying multiple fire sources based on an automatic tracking and positioning jet fire extinguishing device. Under the triggering of a fire warning signal, a video image acquisition module in the fire extinguishing device is started to identify and confirm the fire signal, and each flame target and its maximum ignition point are accurately identified by means of target fusion and segmentation.

[0004] At present, the field of view of infrared array sensors when searching for fire sources is relatively narrow. In the case of a large space, it is difficult to effectively solve the coordinates of a fire source that is far away. In addition, the dynamic processing of the fire source is relatively poor and is greatly disturbed by the static flame jitter. The existing method of using cameras to capture fire sources, for the problem of multiple flames in complex situations, will result in fire source selection without specified rules, resulting in low fire extinguishing efficiency.

[0005] Therefore, it is an urgent problem for those skilled in the art to propose a field of view multi-fire source positioning system and method based on DSP image processing to solve the problems existing in the prior art. Summary of the invention

[0006] In view of this, the present invention provides a field of view multi-fire source positioning system and method based on DSP image processing, which can achieve the effect of accurately positioning and extinguishing fire sources.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A visual field multi-fire source positioning system based on DSP image processing comprises an embedded microprocessor DSP, a CCD module, a communication module, a display module and a water monitor. The CCD module, the embedded microprocessor DSP and the display module are connected in sequence, and the embedded microprocessor DSP and the water monitor are connected with communication module signals.

[0009] Optionally, in the above system, the embedded microprocessor DSP includes an acquisition buffer, a display buffer, a previous frame temporary buffer, an accumulation temporary buffer, a display temporary buffer and a frame opening status buffer.

[0010] A method for locating multiple fire sources in a visual field based on DSP image processing comprises the following steps:

[0011] Data acquisition step: collect image data acquired by the CCD module for multiple frames continuously, obtain the initial data set, establish a real-time loop for display, store the first frame of image into the acquisition buffer and output it directly;

[0012] Flame scanning steps: after receiving the fire alarm information from the water monitor, check whether there is a high grayscale value in the acquisition buffer. If there is, send a stop command to the water monitor immediately, and store the corresponding image in the previous frame temporary buffer and the cumulative temporary buffer;

[0013] Image processing steps: using the image difference method to solve the feature map of the previous frame of the temporary buffer area image and store it in the cumulative temporary buffer area, and using the greedy algorithm to frame the position of the flame block in the display temporary buffer area;

[0014] Flame frame marking step: when there are multiple flames, if the current flame frame is small, it is discarded, and all flame frames larger than the threshold in the field of view are calculated and saved; if it is a single flame, the flame frame is saved;

[0015] Flame frame comparison step: compare all flame frames and calculate the camera coordinates of the largest flame block and the relative coordinates of the remaining flame blocks;

[0016] Positioning and fire extinguishing steps: locate the largest flame block according to the camera coordinates, take the current screen midpoint as the reference point, combine the relative coordinates of the remaining flame blocks, calculate the screen coordinates of the remaining flame blocks, and select a flame block with a closer coordinate distance to start the next round of scanning and fire extinguishing.

[0017] In the above method, optionally, the image processing step includes:

[0018] S1. Using the initial data set to obtain multiple frames of data, performing differential accumulation processing on the previous and next frame data, and storing them in a temporary accumulation buffer area;

[0019] S2: traverse the temporary display buffer area, perform the first line boundary search, find the upper boundary of the flame frame of a row of white dots, and the initial left and right boundaries;

[0020] S3: Use the greedy algorithm to frame the position of the flame block in the display temporary buffer area, start from the upper boundary, traverse the rows downward, expand the left and right boundaries, count the number of white dots, determine whether the current row is occupied by white dots, and update the lower boundary until the number of black dot rows is greater than the set value.

[0021] The above method optionally includes: S1 capturing the second frame image and performing differential processing on it with the previous frame image, dividing the differential value by a set value and rounding it to an integer, and adding it to an accumulated temporary buffer; repeating the operation until the set frame is read, storing the accumulated temporary buffer data in the display temporary buffer, and clearing the accumulated temporary buffer.

[0022] In the above method, optionally, in the flame frame marking step, when there are multiple flames, the principle of proximity is adopted, and when the world coordinate system is converted to the camera coordinate system, the small flame frame is discarded and the large flame frame is retained.

[0023] It can be seen from the above technical solution that compared with the prior art, the present invention provides a field of view multi-fire source positioning system and method based on DSP image processing, which has the following beneficial effects: 1) The present invention uses image difference method to deal with the static flame jitter problem, and can accurately solve the field of view fire source coordinates and estimate the target fire source size; 2) The present invention uses a fire source selection strategy suitable for complex fire sources in large spaces, giving priority to extinguishing nearby fires and fires with large fire source fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0025] Figure 1 A block diagram of a field of view multi-fire source positioning system based on DSP image processing disclosed by the present invention;

[0026] Figure 2 A flow chart of a method for locating multiple fire sources in a visual field based on DSP image processing disclosed by the present invention;

[0027] Figure 3 The present invention discloses a principle diagram of multi-fire source positioning in a visual field based on DSP image processing. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0030] Reference Figure 1 As shown, the present invention discloses a field of view multi-fire source positioning system based on DSP image processing, including an embedded microprocessor DSP, a CCD module, a communication module, a display module and a water monitor. The CCD module, the embedded microprocessor DSP and the display module are connected in sequence, and the embedded microprocessor DSP and the water monitor are connected to the communication module signal.

[0031] Furthermore, the embedded microprocessor DSP includes an acquisition buffer area, a display buffer area, a previous frame temporary buffer area, an accumulation temporary buffer area, a display temporary buffer area and a frame opening state buffer area.

[0032] Furthermore, the CCD module is provided with a filter and the water cannon is equipped with an ultraviolet sensor.

[0033] A method for locating multiple fire sources in the field of view based on DSP image processing, referring to Figure 2 and Figure 3 As shown, the following steps are included:

[0034] Data acquisition step: collect image data acquired by the CCD module for multiple frames continuously, obtain the initial data set, establish a real-time loop for display, store the first frame of image into the acquisition buffer and output it directly;

[0035] Flame scanning steps: after receiving the fire alarm information from the water monitor, check whether there is a high grayscale value in the acquisition buffer. If there is, send a stop command to the water monitor immediately, and store the corresponding image in the previous frame temporary buffer and the cumulative temporary buffer;

[0036] Image processing steps: using the image difference method to solve the feature map of the previous frame of the temporary buffer area image and store it in the cumulative temporary buffer area, and using the greedy algorithm to frame the position of the flame block in the display temporary buffer area;

[0037] Flame frame marking step: when there are multiple flames, if the current flame frame is small, it is discarded, and all flame frames larger than the threshold in the field of view are calculated and saved; if it is a single flame, the flame frame is saved;

[0038] Flame frame comparison step: compare all flame frames and calculate the camera coordinates of the largest flame block and the relative coordinates of the remaining flame blocks;

[0039] Positioning and fire extinguishing steps: locate the largest flame block according to the camera coordinates, take the current screen midpoint as the reference point, combine the relative coordinates of the remaining flame blocks, calculate the screen coordinates of the remaining flame blocks, and select a flame block with a closer coordinate distance to start the next round of scanning and fire extinguishing.

[0040] Furthermore, in the image data acquisition step, the image data acquired by the CCD module includes: each pixel of the CCD image with a filter installed has an 8-bit grayscale value; in order to effectively weaken the influence of radial distortion and increase the speed, the detection field of view can be reduced inward when matching different application environments.

[0041] Furthermore, in the flame scanning step, the fire alarm information of the water cannon is obtained, including: the water cannon determines whether a flame is found in a large space. If a fire occurs, it immediately communicates with the DSP through the serial port, and the water cannon performs a gradient search, while the DSP performs image processing and recognition; when a high grayscale value of the image is found, the water cannon immediately stops searching, and this frame of image is stored in the temporary buffer area of ​​the previous frame and in the cumulative temporary buffer area as the initial value.

[0042] Furthermore, the image processing steps include:

[0043] S1. Using the initial data set to obtain multiple frames of data, performing differential accumulation processing on the previous and next frame data, and storing them in a temporary accumulation buffer area;

[0044] S2: traverse the temporary display buffer area, perform the first line boundary search, find the upper boundary of the flame frame of a row of white dots, and the initial left and right boundaries;

[0045] S3: Use the greedy algorithm to frame the position of the flame block in the display temporary buffer area, start from the upper boundary, traverse the rows downward, expand the left and right boundaries, count the number of white dots, determine whether the current row is occupied by white dots, and update the lower boundary until the number of black dot rows is greater than the set value.

[0046] Furthermore, S1 includes: capturing the second frame image, and performing differential processing on it with the previous frame image, dividing the differential value by a set value and rounding it up, and adding it to an accumulated temporary buffer; repeating the operation until the set frame is read, storing the accumulated temporary buffer data in the display temporary buffer, and clearing the accumulated temporary buffer.

[0047] Furthermore, in S2, a white point is a pixel whose gray value is not less than a set threshold, and the search state has not been transferred and is still in a to-be-searched state; the definition of a white point row is that the number of white points is continuous and greater than a set value.

[0048] Specifically, the definition of continuous white dots is that the number of black dots between two white dots is not greater than the set number. Once the number of black dots is greater than the set number, the flame frame ends at the right boundary of the current row. The black dots are pixels whose grayscale values ​​are less than the set threshold.

[0049] Furthermore, the flame blocks framed by the greedy algorithm in S3 include:

[0050] S3.1, starting from the left border of the flame frame, traverse the search to the left; if a white spot is found, update the left border; otherwise, update the black spot width until the number of black spots is greater than the set value, and exit the traversal to the left;

[0051] S3.2: Start from the right border of the flame frame and search to the right; if a white dot is found, update the right border; otherwise, update the black dot width until the number of black dots is greater than the set value, and then exit the rightward traversal;

[0052] S3.3: Determine whether the current row is a white dot row. If so, update the lower boundary. Otherwise, add 1 to the height of the black dot row. When the number of black dot rows is greater than the set value, exit the traversal and find the flame box to be evaluated.

[0053] Furthermore, in the flame frame marking step, when there are multiple flames, the proximity principle is adopted. When the world coordinate system is converted to the camera coordinate system, the small flame frame is discarded and the large flame frame is retained.

[0054] Specifically, the threshold value in the selection criteria of the flame frame can be flexibly switched according to the user or application scenario.

[0055] Furthermore, in the flame frame marking step, the flame block coordinates are the center point coordinates of the flame frame.

[0056] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0057] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A visual field multi-fire source positioning system based on DSP image processing, characterized in that: The device comprises an embedded microprocessor DSP, a CCD module, a communication module, a display module and a water monitor. The CCD module, the embedded microprocessor DSP and the display module are connected in sequence, and the embedded microprocessor DSP and the water monitor are connected with communication module signals.

2. A visual field multi-fire source positioning system based on DSP image processing according to claim 1, characterized in that: The embedded microprocessor DSP comprises a collection buffer area, a display buffer area, a previous frame temporary buffer area, an accumulation temporary buffer area, a display temporary buffer area and a frame opening state buffer area.

3. A method for locating multiple fire sources in the field of view based on DSP image processing, characterized in that: The following steps are involved: Data acquisition step: collect image data acquired by the CCD module for multiple frames continuously, obtain the initial data set, establish a real-time loop for display, store the first frame of image into the acquisition buffer and output it directly; Flame scanning steps: after receiving the fire alarm information from the water monitor, check whether there is a high grayscale value in the acquisition buffer. If there is, send a stop command to the water monitor immediately, and store the corresponding image in the previous frame temporary buffer and the cumulative temporary buffer; Image processing steps: using the image difference method to solve the feature map of the previous frame of the temporary buffer area image and store it in the cumulative temporary buffer area, and using the greedy algorithm to frame the position of the flame block in the display temporary buffer area; Flame frame marking step: when there are multiple flames, if the current flame frame is small, it will be discarded, and all flame frames larger than the threshold in the field of view will be calculated and saved; If it is a single flame, save the current flame frame; Flame frame comparison step: compare all flame frames and calculate the camera coordinates of the largest flame block and the relative coordinates of the remaining flame blocks; Positioning and fire extinguishing steps: locate the largest flame block according to the camera coordinates, take the current screen midpoint as the reference point, combine the relative coordinates of the remaining flame blocks, calculate the screen coordinates of the remaining flame blocks, and select a flame block with a closer coordinate distance to start the next round of scanning and fire extinguishing.

4. A method for locating multiple fire sources in a visual field based on DSP image processing according to claim 3, characterized in that: The image processing steps include: S1. Using the initial data set to obtain multiple frames of data, performing differential accumulation processing on the previous and next frame data, and storing them in a temporary accumulation buffer area; S2: traverse the temporary display buffer area, perform the first line boundary search, find the upper boundary of the flame frame of a row of white dots, and the initial left and right boundaries; S3: Use the greedy algorithm to frame the position of the flame block in the display temporary buffer area, start from the upper boundary, traverse the rows downward, expand the left and right boundaries, count the number of white dots, determine whether the current row is occupied by white dots, and update the lower boundary until the number of black dot rows is greater than the set value.

5. A method for locating multiple fire sources in a visual field based on DSP image processing according to claim 4, characterized in that: S1 includes: capturing the second frame image, and performing differential processing on it with the previous frame image, dividing the differential value by the set value and rounding it up, and adding it to the cumulative temporary buffer area; repeating the operation until the set frame is read, storing the cumulative temporary buffer area data into the display temporary buffer area, and clearing the cumulative temporary buffer area.

6. A method for locating multiple fire sources in a visual field based on DSP image processing according to claim 3, characterized in that: In the flame frame marking step, when there are multiple flames, the principle of proximity is adopted. When the world coordinate system is converted to the camera coordinate system, the small flame frame is discarded and the large flame frame is retained.

Images