Pulse signal-based target detection method, detection system, equipment and medium

Abstract

The invention provides a target detection method based on pulse signals, a detection system, equipment and a medium, and the detection method comprises the steps: obtaining n * m image resolution and collection frequency, setting the number of sampling frames, obtaining a collection data set through collection of pulse data, obtaining a pulse data stream set through the collection data set, taking pixels as a unit, and obtaining a pulse data stream set through the collection data set; the pulse data stream set is recombined according to the frame header information to obtain a recombined image, the image comprises n * m pixels, the pulse signal length of each pixel is the same as the sampling frame number, a recombined atlas set is generated according to the recombined image, and the recombined atlas set comprises a pulse height atlas, used for reflecting the process that a target passes through the pixel, of each pixel; and finally, obtaining target position information according to the recombination map set. According to the invention, target detection is directly carried out in the pulse domain, and through pulse domain image detection, the calculation amount of the image domain can be greatly reduced, the data operation pressure is reduced, the target detection speed is improved, and the target detection capability of the system is enhanced.

Description

Technical Field

[0001] The present application relates to the technical field of target detection, and in particular to a target detection method based on pulse signals. Background Art

[0002] In a pulse camera, each pixel works independently, using a continuous binary pulse matrix to continuously record the light intensity in external dynamic scenes. There is no concept of exposure time window, which breaks through the limitations of traditional cameras. It can better capture and record high-speed motion, and also demonstrates good ability to accumulate photons in scenes with extremely low light intensity.

[0003] In the existing technology, due to the powerful scene characterization ability of pulse signals, the amount of data has increased dramatically. The traditional method of image reconstruction and target detection in the image domain has put forward great computing power requirements for embedded systems. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, the present application aims to provide a target detection method, detection system, device and medium based on pulse signals.

[0005] In a first aspect, the present application proposes a target detection method based on a pulse signal, comprising the following steps:

[0006] S100. Obtaining image resolution and acquisition frequency, wherein the image resolution is set to n*m;

[0007] S200. Set the sampling frame number;

[0008] S300. Periodically collect pulse data at the collection frequency to obtain a collection data set, wherein the collection data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals;

[0009] S400. According to the collected data set, a pulse data stream set is obtained, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals;

[0010] S500. Taking pixels as units, reorganize the pulse data stream set according to the frame header information to obtain a reorganized image, wherein the reorganized image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number;

[0011] S600. Generate a recombined atlas set according to the recombined image, wherein the recombined atlas set includes a pulse height map of each pixel in the recombined image, and each pulse height map is used to reflect a process of a target passing through the pixel;

[0012] S700. Obtain target position information according to the recombination map set.

[0013] According to the technical solution provided in the embodiment of the present application, step S600 includes the following steps:

[0014] S610. Acquire the signal strength of each pixel in the recombined image at different acquisition times, wherein the signal strength is used to reflect the target state, and the target state includes the target not entering, the target entering, the target staying, the target leaving, and the target leaving completely;

[0015] S620. Obtain the pulse height spectrum of each pixel according to the acquisition time and the signal intensity corresponding to the acquisition time.

[0016] According to the technical solution provided in the embodiment of the present application, step S610 includes the following steps:

[0017] S611. Obtaining a time interval according to the acquisition frequency;

[0018] S612. Acquire a plurality of high-level sequences each including two high-level pulse signals according to the pulse data stream set;

[0019] S613. The number of time intervals between two high-level pulse signals is obtained according to each of the high-level sequences, which is the number of time intervals;

[0020] S614. Obtain the signal strengths corresponding to the collection moments of the first high-level pulse signal and all the low-level pulse signals in each of the high-level sequences according to the number of time intervals.

[0021] According to the technical solution provided in the embodiment of the present application, the reciprocal of the time intervals in each of the high-level sequences is the signal strength corresponding to the collection moments corresponding to the first high-level pulse signal and all the low-level pulse signals in the high-level sequence.

[0022] According to the technical solution provided in an embodiment of the present application, the method for obtaining the target position information based on the recombinant map set is: searching for similar signal strengths at one or several acquisition moments based on the recombinant map set, and obtaining the target position information based on the similar signal strengths, wherein the similar signal strengths include multiple signal strengths, and the difference between any two of the signal strengths is less than a preset threshold.

[0023] According to the technical solution provided in the embodiment of the present application, step S700 further includes the following steps:

[0024] S800. Reconstruct an image according to the pulse data stream set to obtain a reconstructed image;

[0025] S900. Input the reconstructed image into a neural network to obtain a target type.

[0026] According to the technical solution provided in the embodiment of the present application, step S800 further includes the following steps:

[0027] S810. Set the frame selection window;

[0028] S820. Frame the reconstructed image according to the target position information and the frame selection window to obtain a framed image;

[0029] S830. Input the framed image into the neural network to obtain the target type.

[0030] In a second aspect, the present application proposes a detection system, comprising:

[0031] An acquisition module, wherein the acquisition module is configured to acquire image resolution and acquisition frequency, wherein the image resolution is set to n*m;

[0032] A setting module, wherein the setting module is configured to set the number of sampling frames;

[0033] An acquisition module, wherein the acquisition module is configured to periodically acquire pulse data at the acquisition frequency to obtain an acquisition data set, wherein the acquisition data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals;

[0034] A data conversion module, wherein the data conversion module is configured to obtain a pulse data stream set according to the collected data set, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals;

[0035] A recombining module, wherein the recombining module is configured to recombine the pulse data stream set in units of pixels according to the frame header information to obtain a recombined image, wherein the recombined image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number;

[0036] A generating module, wherein the generating module is configured to generate a recombined atlas set according to the recombined image, wherein the recombined atlas set includes a pulse height atlas of each pixel in the recombined image, wherein each pulse height atlas is used to reflect a process in which a target passes through the pixel point;

[0037] An execution module is configured to obtain target position information according to the recombination map set.

[0038] In a third aspect, the present application proposes a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the pulse signal-based target detection method as described above when executing the computer program.

[0039] In a fourth aspect, the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the target detection method based on pulse signals as described above are implemented.

[0040] In summary, the present application proposes a target detection method based on pulse signals, by obtaining an image resolution of n*m and an acquisition frequency and setting the number of sampling frames, pulse data is periodically acquired through the acquisition frequency to obtain an acquisition data set, the acquisition data set includes multiple frame header information and voltage information corresponding to each frame header information, and then a pulse data stream set is obtained through the acquisition data set, and the pulse data stream set is reorganized according to the frame header information in units of pixels to obtain a reorganized image, which includes n*m pixels, and the pulse signal length of each pixel is the same as the number of sampling frames, and then a reorganized spectrum set is generated based on the reorganized image, and the reorganized spectrum set includes a pulse height spectrum of each pixel for reflecting the process of the target passing through the pixel; finally, the target position information is obtained based on the reorganized spectrum set; the present application is based on directly performing target detection in the pulse domain, and through pulse domain image detection, the image domain calculation amount can be greatly reduced, the data calculation pressure is reduced, the target detection speed is improved, and the target detection capability of the system is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a target detection method based on pulse signals provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a reconstructed image provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of a pulse height spectrum provided in an embodiment of the present application;

[0044] Figure 4A schematic diagram of a process of reconstructing an image by selecting a frame through a selection window provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of the structure of the terminal device provided for this application.

[0046] The text annotations in the figure represent:

[0047] 700, computer system; 701, CPU; 702, ROM; 703, RAM; 704, bus; 705, I / O interface; 706, input part; 707, output part; 708, storage part; 709, communication part; 710, drive; 711, removable media DETAILED DESCRIPTION

[0048] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0049] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0050] Example 1

[0051] As mentioned in the background technology, this application proposes a target detection method based on pulse signals, such as Figure 1 As shown, the following steps are included:

[0052] S100. Obtaining image resolution and acquisition frequency, wherein the image resolution is set to n*m;

[0053] The image resolution and the acquisition frequency are properties of the image acquisition device. Optionally, the image resolution is 640*512; the acquisition frequency is 10,000 frames per second;

[0054] S200. Set the sampling frame number; wherein the sampling frame number is set to 100;

[0055] S300. Periodically collect pulse data at the collection frequency to obtain a collection data set, wherein the collection data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals;

[0056] First, the host computer control system is started and stopped to complete the collection of infrared or visible light data, wherein the reset voltage, reset signal and the sampling frame number can be adjusted online to meet the image collection requirements in different complex scenes; optionally, the image acquisition device is a camera, and the infrared or visible light data is collected by the camera, wherein the pulse data has an integral mark.

[0057] S400. According to the collected data set, a pulse data stream set is obtained, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals;

[0058] Wherein, obtaining a pulse data stream set according to the collected data set comprises the following steps:

[0059] Set the voltage threshold; the voltage threshold can be set on the host computer;

[0060] Convert each of the pulse voltage signals into a digital pulse signal;

[0061] According to the voltage threshold, the digital pulse signal is converted into the single-bit pulse signal, thereby obtaining the collected data set.

[0062] This application uses a high-performance AD ​​analog-to-digital conversion chip to complete signal quantization, converting the pulse voltage signal into a digital signal that can be processed by a computer, and then comparing the digital pulse signal with the voltage threshold. When it is greater than the voltage threshold, it is quantized into a single-bit pulse signal of 0 or 1.

[0063] The image acquisition device has a photoelectric sensor, which includes a capacitor. When light hits the chip of the photoelectric sensor, it is converted into electrons through the photoelectric conversion chip, and the electrons are accumulated in the capacitor. The voltage information is obtained by measuring the voltage across the capacitor. For example, if the capacitor is full when 6000 electrons are accumulated, the corresponding single-bit pulse signal is 1. If the background accumulates 600 electrons in the capacitor each time, and the target accumulates 3000 electrons in the capacitor each time, if the background has accumulated 5 times and the target suddenly enters the field of view, the capacitor is full and the output single-bit pulse signal is 1. Therefore, the external light intensity is inversely proportional to the time it takes for the capacitor to be full. The stronger the light intensity, the shorter the time it takes for the capacitor to be full.

[0064] S500. Taking pixels as units, reorganize the pulse data stream set according to the frame header information to obtain a reorganized image, wherein the reorganized image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number;

[0065] Among them, take the image resolution of 640*512 as an example, Figure 2 As shown, the x-axis represents rows, the y-axis represents columns, and the t-axis represents time; Figure 2 The image includes 100 pulse frames, with black as the background and bright as the target. As the timeline goes on, the target completes the action within a fixed time. Finally, 640*512 groups of pulse streams with a length of 100 are generated; 640*512 is the array size, and 100 is the number of sampling frames. Both need to be analyzed and set according to the actual application scenario.

[0066] S600. Generate a recombined map set according to the recombined image, wherein the recombined map set includes a pulse height map of each pixel in the recombined image, and each pulse height map is used to reflect the process of a target passing through the pixel; the process is performed in a pulse flow detector, and includes the following steps:

[0067] S610. Acquire the signal strength of each pixel in the recombined image at different acquisition times, wherein the signal strength is used to reflect the target state, wherein the target state includes the target not entering, the target entering, the target staying, the target leaving, and the target leaving completely; comprising the following steps:

[0068] S611. Obtaining a time interval according to the acquisition frequency; taking the acquisition frequency as 1s10000 times as an example, the time interval is 1s / 10000=0.1ms;

[0069] S612. Acquire a plurality of high-level sequences each including two high-level pulse signals according to the pulse data stream set;

[0070] S613. The number of time intervals between two high-level pulse signals is obtained according to each of the high-level sequences, which is the number of time intervals;

[0071] S614. Obtain the signal strength corresponding to the collection moment of the first high-level pulse signal and all the low-level pulse signals in each of the high-level sequences according to the number of time intervals; wherein, taking the inverse of the number of time intervals in each of the high-level sequences is the signal strength corresponding to the collection moment of the first high-level pulse signal and all the low-level pulse signals in the high-level sequence.

[0072] If the pulse data stream set is as follows:

[0073]

[0074] The single-bit pulse signal corresponding to a certain pixel is [1,0,1,1,…,0], the time interval between the two "1" pulse signals in [1,0,1] is N=2, then the signal strength corresponding to the first acquisition moment and the second acquisition moment is 1 / 2, the time interval between the two "1" pulse signals in [1,1] is N=1, then the signal strength corresponding to the third acquisition moment is 1; at the start and end of the acquisition, it cannot be guaranteed that the entire integration process can be completed, and the single-bit pulse signal data will have only "0" at the beginning and end, for example, [1,0,1,1,…,1,0,0,0], in this scenario, the last 1,0,0,0 cannot calculate the time interval, and this part of the data is discarded.

[0075] S620. Obtain the pulse height spectrum of each pixel according to the acquisition time and the signal intensity corresponding to the acquisition time.

[0076] Method for determining target status according to the signal strength:

[0077] Set the minimum signal strength A;

[0078] Compare the signal strengths of each pixel at different acquisition times to obtain a maximum signal strength B, where the target state corresponding to the maximum signal strength is target stay;

[0079] Before the maximum signal strength, the target state corresponding to the signal strength greater than the minimum signal strength and less than the maximum signal strength is target entry;

[0080] The target state is before the target enters the corresponding signal strength, and the target state corresponding to the signal strength less than the minimum signal strength is that the target has not entered

[0081] After the maximum signal strength, the target state corresponding to the signal strength less than the maximum signal strength and greater than the minimum signal strength is the target leaving;

[0082] After the target state is that the target leaves the corresponding signal strength, the target state corresponding to the signal strength less than the minimum signal strength is that the target has completely left.

[0083] Figure 3 Three pixels with coordinates (20,400), (260,400) and (500,400) are selected for data analysis and processing. It can be seen from the figure that the signal strength can directly reflect the movement of the target entering and leaving the field of view. When the target enters the field of view, its signal strength can be seen to gradually increase. By counting the storage time of its strongest signal, the target's moving speed can also be measured. When the target leaves the field of view, its signal strength gradually weakens. After leaving completely, its signal strength remains in a relatively weak state.

[0084] S700. Obtain target location information according to the recombinant spectrum set. The method for obtaining target location information according to the recombinant spectrum set is: find similar signal strengths at one or several acquisition moments according to the recombinant spectrum set, and obtain target location information according to the similar signal strengths, wherein the similar signal strengths include multiple signal strengths, and the difference between the two signal strengths is less than a preset threshold.

[0085] The target size is mainly determined by analyzing the pulse intensity at one or several specific acquisition moments. If similar signal strengths are found in certain areas, the target position can be roughly determined. The target's motion trajectory requires an overall characterization of the pulse signal during the entire motion process, and the target position is described frame by frame or frame by frame based on the time interval, thereby restoring the target's motion trajectory. The target's moving speed is calculated by calculating the relative time and relative speed based on the acquisition frequency and the distance it moves in the field of view, thereby performing speed calculation.

[0086] In a preferred embodiment, step S700 further includes the following steps:

[0087] S800. Reconstruct an image according to the pulse data stream set to obtain a reconstructed image;

[0088] Optionally, image reconstruction is performed by TFI (Texture from Interval, based on pulse interval reconstruction method), and the number of frames between two high-level pulse signals in the high-level sequence is the trigger interval, which directly reflects the change in scene light intensity. Obviously, the signal intensity of each pixel at a certain stage is inversely proportional to its trigger interval at this stage. The larger the trigger interval, the longer the integration time is required to fill the capacitor, and the darker the scene; conversely, the smaller the trigger interval, the shorter the capacitor can be filled in a short time, and the brighter the scene. Pulse data is quantified by this method.

[0089] S900. Input the reconstructed image into a neural network to obtain a target type.

[0090] Optionally, the neural network is a network that is conducive to embedded system deployment, such as Yolo, Faster-Rcnn, etc. Identifying the target through the neural network and obtaining the target type is a prior art and will not be described in detail here.

[0091] In a preferred embodiment, image generation is completed through the TFI reconstruction method. Since the original image has a large resolution, searching and identifying targets in a global range places high demands on the computing power of hardware resources. Therefore, the target position information box detected in the pulse domain is used to select the detection range, and the image domain signal is used to perform small-range target recognition.

[0092] like Figure 4 As shown, after step S800, the following steps are also included:

[0093] S810. Set a selection window; optionally, the size of the selection window is defined as 30 pixels, that is, the outside of the target is filled with a rectangular frame of 30 pixels, and the aspect ratio is kept unchanged;

[0094] S820. Frame the reconstructed image according to the target position information and the frame selection window to obtain a framed image; the framed target is the target position information calculated by the pulse stream;

[0095] S830. Input the framed image into the neural network to obtain the target type. After frame selection, since the image domain resolution is greatly reduced, the computing power requirement of the embedded system is reduced, so it plays a greater role in systems that have certain requirements for recognition speed.

[0096] Example 2

[0097] Based on Example 1, the present application proposes a detection system for implementing the above-mentioned target detection method based on pulse signals, including:

[0098] An acquisition module, wherein the acquisition module is configured to acquire image resolution and acquisition frequency, wherein the image resolution is set to n*m;

[0099] A setting module, wherein the setting module is configured to set the number of sampling frames;

[0100] An acquisition module, wherein the acquisition module is configured to periodically acquire pulse data at the acquisition frequency to obtain an acquisition data set, wherein the acquisition data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals;

[0101] A data conversion module, wherein the data conversion module is configured to obtain a pulse data stream set according to the collected data set, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals;

[0102] A recombining module, wherein the recombining module is configured to recombine the pulse data stream set in units of pixels according to the frame header information to obtain a recombined image, wherein the recombined image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number;

[0103] A generating module, wherein the generating module is configured to generate a recombined atlas set according to the recombined image, wherein the recombined atlas set includes a pulse height atlas of each pixel in the recombined image, wherein each pulse height atlas is used to reflect a process in which a target passes through the pixel point;

[0104] An execution module is configured to obtain target position information according to the recombination map set.

[0105] Example 3

[0106] like Figure 5 As shown, the computer system 700 of the terminal device includes a CPU 701, which can perform various appropriate actions and processes according to the program stored in the ROM 702 or the program loaded from the storage part 708 to the RAM 703. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702 and the RAM 703 are connected to each other through the bus 704. The I / O interface 705 is also connected to the bus 704. The following components are connected to the I / O interface 705: an input part 706 including a keyboard, a mouse, etc.; an output part 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part 708 including a hard disk, etc.; and a communication part 709 including a network interface card such as a LAN card, a modem, etc. The communication part 709 performs communication processing via a network such as the Internet. The drive is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is mounted on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0107] In particular, according to the embodiments of the present application, the above reference process Figure 1 The described process can be implemented as a computer software program. For example, embodiment 3 of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by CPU 701, the above-mentioned functions defined in the present computer system 700 are executed.

[0108] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0109] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments 3 of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0110] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the target detection method based on pulse signals as described in the above embodiment.

[0111] For example, the electronic device may implement Figure 1 As shown in: S100. Obtain image resolution and acquisition frequency, the image resolution is set to n*m; S200. Set the number of sampling frames; S300. Periodically acquire pulse data at the acquisition frequency to obtain an acquisition data set, the acquisition data set includes multiple frame header information and voltage information corresponding to each frame header information, the voltage information includes n*m pulse voltage signals; S400. According to the acquisition data set, a pulse data stream set is obtained, the pulse data stream set includes multiple groups of pulse data stream information, each of the pulse data stream information includes frame header information and single-bit pulse data corresponding thereto, the pulse number The number of data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals; S500. In units of pixels, the pulse data stream set is reorganized according to the frame header information to obtain a reorganized image, and the reorganized image includes n*m pixels, and the pulse signal length of each pixel is the same as the number of sampling frames; S600. A reorganized map set is generated according to the reorganized image, and the reorganized map set includes a pulse height map of each pixel in the reorganized image, and each pulse height map is used to reflect the process of the target passing through the pixel; S700. According to the reorganized map set, the target position information is obtained.

[0112] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments disclosed in the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0113] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0114] Through the description of the above implementations, those skilled in the art can easily understand that the example implementations described here can be implemented by software, or by combining software with necessary hardware.

[0115] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

Claims

1. A target detection method based on pulse signals, characterized in that: The steps include: S100. Obtaining image resolution and acquisition frequency, wherein the image resolution is set to n*m; S200. Set the sampling frame number; S300. Periodically collect pulse data at the collection frequency to obtain a collection data set, wherein the collection data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals; S400. According to the collected data set, a pulse data stream set is obtained, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals; S500. Taking pixels as units, reorganize the pulse data stream set according to the frame header information to obtain a reorganized image, wherein the reorganized image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number; S600. Generate a recombined atlas set according to the recombined image, wherein the recombined atlas set includes a pulse height map of each pixel in the recombined image, and each pulse height map is used to reflect a process of a target passing through the pixel; S700. Obtain target position information according to the recombination map set.

2. The target detection method based on pulse signal according to claim 1, characterized in that: Step S600 includes the following steps: S610. Acquire the signal strength of each pixel in the recombined image at different acquisition times, wherein the signal strength is used to reflect the target state, and the target state includes the target not entering, the target entering, the target staying, the target leaving, and the target leaving completely; S620. Obtain the pulse height spectrum of each pixel according to the acquisition time and the signal intensity corresponding to the acquisition time.

3. The target detection method based on pulse signal according to claim 2, characterized in that: Step S610 includes the following steps: S611. Obtaining a time interval according to the acquisition frequency; S612. Acquire a plurality of high-level sequences each including two high-level pulse signals according to the pulse data stream set; S613. The number of time intervals between two high-level pulse signals is obtained according to each of the high-level sequences, which is the number of time intervals; S614. Obtain the signal strengths corresponding to the collection moments of the first high-level pulse signal and all the low-level pulse signals in each of the high-level sequences according to the number of time intervals.

4. The target detection method based on pulse signal according to claim 3 is characterized in that: The reciprocal of the time intervals in each of the high-level sequences is the signal strength corresponding to the collection moments corresponding to the first high-level pulse signal and all the low-level pulse signals in the high-level sequence.

5. The target detection method based on pulse signal according to claim 2, characterized in that: The method for obtaining the target location information according to the recombinant spectrum set is: searching for similar signal strengths at one or several acquisition moments according to the recombinant spectrum set, and obtaining the target location information according to the similar signal strengths, wherein the similar signal strengths include multiple signal strengths, and the difference between any two of the signal strengths is less than a preset threshold.

6. The target detection method based on pulse signal according to claim 1, characterized in that: After step S700, the following steps are also included: S800. Reconstruct an image according to the pulse data stream set to obtain a reconstructed image; S900. Input the reconstructed image into a neural network to obtain a target type.

7. The target detection method based on pulse signal according to claim 2, characterized in that: After step S800, the following steps are also included: S810. Set the frame selection window; S820. Frame the reconstructed image according to the target position information and the frame selection window to obtain a framed image; S830. Input the framed image into the neural network to obtain the target type.

8. A detection system for implementing the target detection method based on pulse signals according to any one of claims 1 to 7, characterized in that: include: An acquisition module, wherein the acquisition module is configured to acquire image resolution and acquisition frequency, wherein the image resolution is set to n*m; A setting module, wherein the setting module is configured to set the number of sampling frames; An acquisition module, wherein the acquisition module is configured to periodically acquire pulse data at the acquisition frequency to obtain an acquisition data set, wherein the acquisition data set includes a plurality of frame header information and voltage information corresponding to each of the frame header information, wherein the voltage information includes n*m pulse voltage signals; A data conversion module, wherein the data conversion module is configured to obtain a pulse data stream set according to the collected data set, wherein the pulse data stream set includes multiple groups of pulse data stream information, each of which includes frame header information and single-bit pulse data corresponding thereto, the number of the pulse data stream information is the same as the number of sampling frames, and the single-bit pulse data includes n*m single-bit pulse signals; A recombining module, wherein the recombining module is configured to recombine the pulse data stream set in units of pixels according to the frame header information to obtain a recombined image, wherein the recombined image includes n*m pixels, and the pulse signal length of each pixel is the same as the sampling frame number; A generating module, wherein the generating module is configured to generate a recombined atlas set according to the recombined image, wherein the recombined atlas set includes a pulse height atlas of each pixel in the recombined image, wherein each pulse height atlas is used to reflect a process in which a target passes through the pixel point; An execution module is configured to obtain target position information according to the recombination map set.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the target detection method based on pulse signals as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the target detection method based on pulse signals as described in any one of claims 1 to 7 are implemented.

Images