Smoke cloud detection method, device, equipment, medium and product

Abstract

The invention discloses a smoke cloud detection method, device and equipment, a medium and a product. The invention relates to the technical field of target detection. The method comprises the following steps: acquiring three continuous frames of images, wherein the three continuous frames of images comprise a first image, a second image and a third image; performing feature matching on the three continuous frames of images to obtain feature matching points of the first image, feature matching points of the second image and feature matching points of the third image; determining motion track information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image and the feature matching points of the third image; and if the movement track information of the feature matching point meets a preset movement track feature condition of the cigarette, determining that the detection result is cigarette, and if the movement track information of the feature matching point meets a preset movement track feature condition of cloud, determining that the detection result is cloud. According to the technical scheme, accurate distinguishing and detection of smoke and cloud are achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of target detection technology, and in particular to a smoke cloud detection method, device, equipment, medium and product. Background Art

[0002] With the rapid development of artificial intelligence technology, its application in target detection research is becoming more and more extensive and has become an important means of target detection.

[0003] In current target detection technology, since the characteristics of smoke and clouds are similar, it is difficult to distinguish and detect clouds and smoke through existing artificial intelligence methods. Summary of the invention

[0004] The present invention provides a smoke and cloud detection method, device, equipment, medium and product, which realize accurate distinction and detection of smoke and cloud.

[0005] According to one aspect of the present disclosure, a smoke cloud detection method is provided, comprising:

[0006] Acquire three consecutive image frames, wherein the three consecutive image frames include a first image, a second image, and a third image;

[0007] Performing feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image;

[0008] Determine motion trajectory information of feature matching points based on feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image;

[0009] If the motion trajectory information of the feature matching point meets the preset motion trajectory characteristic condition of smoke, the detection result is determined to be smoke; if the motion trajectory information of the feature matching point meets the preset motion trajectory characteristic condition of cloud, the detection result is determined to be cloud.

[0010] According to another aspect of the present disclosure, there is provided a smoke cloud detection device, comprising:

[0011] A continuous image acquisition module, used to acquire three continuous image frames, wherein the three continuous image frames include a first image, a second image and a third image;

[0012] An image feature matching module, used to perform feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image;

[0013] A motion trajectory information determination module, configured to determine the motion trajectory information of feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image;

[0014] A smoke and cloud detection result determination module, configured to determine that the detection result is smoke if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, and determine that the detection result is cloud if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, which includes:

[0016] At least one processor;

[0017] And a memory communicatively connected to the at least one processor;

[0018] Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the smoke and cloud detection method according to any embodiment of the present disclosure.

[0019] According to another aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions for implementing the smoke and cloud detection method according to any embodiment of the present disclosure when executed by a processor.

[0020] According to another aspect of the present disclosure, there is provided a computer program product including a computer program, which implements the smoke and cloud detection method according to any one of the embodiments of the present disclosure when executed by a processor.

[0021] The technical solution of the embodiment of the present disclosure obtains three consecutive frames of images, which include a first image, a second image, and a third image. Then, feature matching is performed on the three consecutive frames of images to obtain the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image. The motion trajectory information of the feature matching points is determined based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, the detection result is determined to be smoke; if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, the detection result is determined to be cloud. In the above technical solution, accurate distinction and detection of smoke and cloud are achieved.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a flowchart of a smoke plume detection method provided according to an embodiment of the present disclosure;

[0025] Figure 2 is a flowchart of another smoke plume detection method provided according to an embodiment of the present disclosure;

[0026] Figure 3 is a flowchart of another smoke plume detection method provided according to an embodiment of the present disclosure;

[0027] Figure 4A is a schematic diagram of a smoke plume detection result provided according to an embodiment of the present disclosure;

[0028] Figure 4B is a schematic diagram of another smoke plume detection result provided according to an embodiment of the present disclosure;

[0029] Figure 5 is a flowchart of another smoke plume detection method provided according to an embodiment of the present disclosure;

[0030] Figure 6 is a schematic structural diagram of a smoke plume detection device provided according to an embodiment of the present disclosure;

[0031] Figure 7 is a schematic structural diagram of an electronic device for implementing the smoke plume detection method of the embodiments of the present disclosure. Detailed Embodiments

[0032] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present disclosure.

[0033] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present disclosure are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of the present disclosure all comply with the relevant regulations of national laws and regulations.

[0034] Figure 1 FIG. is a flowchart of a smoke detection method provided by an embodiment of the present disclosure. This embodiment is applicable to the situation of automatically detecting smoke in a video. This method can be executed by a smoke detection device, which can be implemented in the form of hardware and / or software, and the smoke detection device can be configured in electronic devices such as terminals and servers. As Figure 1 shown, the method includes:

[0035] S110. Obtain three consecutive frames of images, where the three consecutive frames of images include a first image, a second image, and a third image.

[0036] Among them, the three consecutive frames of images are three images consecutive in time, which can be images in a video.

[0037] Exemplarily, an image can be extracted from the video at every preset time interval, so that the first image, the second image, and the third image can be obtained.

[0038] S120. Perform feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image.

[0039] Among them, the feature matching can be Scale-invariant feature transform (SIFT) or other feature matching methods, which are not specifically limited here. The feature matching point refers to the feature point obtained by performing feature matching on the image. The feature matching points between different frames can correspond to the same physical point. In other words, the feature matching point is the representation of the same physical point in different frames.

[0040] Exemplarily, feature point matching can be performed on three consecutive frames of images through SIFT feature changes, so as to obtain feature matching points between the three images. The number of feature matching points can be one or more. Specifically, SIFT key point detection is performed on each frame of image to obtain the key points of each frame of image, the common key points belonging to the three frames of images are extracted, and the common key points belonging to the three frames of images are used as the feature matching points of each image.

[0041] S130. Determine the motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image.

[0042] Among them, the motion trajectory information refers to the motion trajectory of the feature matching points, and may include, but is not limited to, information such as motion distance and motion angle.

[0043] Exemplarily, the A feature matching point of the first image, the B feature matching point of the second image, and the C feature matching point of the third image are the same physical point, and the formed matching chain A - B - C is the motion trajectory of the feature matching points, and this motion trajectory can be used as the motion trajectory information.

[0044] S140. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, determine that the detection result is smoke; if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, determine that the detection result is cloud.

[0045] It should be noted that smoke and cloud are in the sky, and smoke is closer in the video than cloud. Therefore, the motion speed of smoke is faster than that of cloud, that is, the motion distance of smoke is longer than that of cloud in the same time, and the motion direction of smoke is upward or inclined upward, while the motion state of cloud is in any direction.

[0046] In the embodiments of the present disclosure, the preset motion trajectory feature conditions of smoke can be that the motion speed or motion distance of the feature matching points is greater than a preset value, and the motion direction of the feature matching points is upward or inclined upward. The preset motion trajectory feature conditions of cloud can be that the motion speed or motion distance of the feature matching points is less than a preset value, and / or the motion direction of the feature matching points is downward or inclined downward.

[0047] The technical solution of the embodiment of the present disclosure obtains three consecutive frames of images, which include a first image, a second image, and a third image. Then, feature matching is performed on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image. Based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image, the motion trajectory information of the feature matching points is determined. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, the detection result is determined to be smoke. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, the detection result is determined to be cloud. In the above technical solution, accurate distinction and detection of smoke and cloud are achieved.

[0048] Figure 2 FIG. 4 is a flowchart of another method for detecting smoke and cloud provided by an embodiment of the present disclosure. The method of this embodiment can be combined with each optional solution in the method for detecting smoke and cloud provided in the above embodiment. On the basis of the above embodiments, this embodiment further refines the step of determining the motion trajectory information of the feature matching points.

[0049] As Figure 2 shown, the method includes:

[0050] S210. Obtain three consecutive frames of images, where the three consecutive frames of images include a first image, a second image, and a third image.

[0051] S220. Perform feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image.

[0052] S230. Determine the motion angle of the feature matching points based on the feature matching points of the first image and the feature matching points of the third image.

[0053] Specifically, a point-to-point vector can be determined based on the feature matching points of the first image and the feature matching points of the third image; determine the included angle between the point-to-point vector and the horizontal direction, and use the included angle between the point-to-point vector and the horizontal direction as the motion angle of the feature matching points, where the point-to-point vector is a vector with the feature matching point of the first image as the starting point and the feature matching point of the third image as the ending point, and the vertex of the included angle is the feature matching point of the first image.

[0054] S240. Determine the motion distance of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image.

[0055] Specifically, determine the distance between the feature matching points of the first image and the feature matching points of the second image, determine the distance between the feature matching points of the second image and the feature matching points of the third image, and add the distance between the feature matching points of the first image and the feature matching points of the second image to the distance between the feature matching points of the second image and the feature matching points of the third image to obtain the movement distance of the feature matching points.

[0056] S250. Construct the movement trajectory information of the feature matching points based on the movement angle and the movement distance of the feature matching points.

[0057] S260. If the movement trajectory information of the feature matching points meets the preset movement trajectory feature conditions of smoke, determine that the detection result is smoke; if the movement trajectory information of the feature matching points meets the preset movement trajectory feature conditions of cloud, determine that the detection result is cloud.

[0058] Based on the above embodiments, optionally, if the movement trajectory information of the feature matching points meets the preset movement trajectory feature conditions of smoke, determining that the detection result is smoke includes: if the movement angle of the feature matching points is greater than zero degrees and less than one hundred and eighty degrees, and the movement distance of the feature matching points is greater than the preset distance threshold, determine that the detection result is smoke.

[0059] Exemplarily, the preset movement trajectory feature conditions of smoke can be: 0 < angle < 180 and dis >= 10, where angle represents the movement angle, dis represents the movement distance, and the unit of 10 can be meters or other distance measurement units. If the movement angle of the feature matching points is 90 degrees and the movement distance of the feature matching points is 50, determine that the detection result is smoke.

[0060] Based on the above embodiments, optionally, if the movement trajectory information of the feature matching points meets the preset movement trajectory feature conditions of cloud, determining that the detection result is cloud includes: if the movement angle of the feature matching points is greater than minus one hundred and eighty degrees and less than zero degrees, and the movement distance of the feature matching points is less than the preset distance threshold, determine that the detection result is cloud.

[0061] Exemplarily, the preset movement trajectory feature conditions of cloud can be: -180 < angle < 0 and dis < 10, where angle represents the movement angle, dis represents the movement distance, and the unit of 10 can be meters or other distance measurement units. If the movement angle of the feature matching points is -10 degrees and the movement distance of the feature matching points is 2, determine that the detection result is cloud.

[0062] The technical solution of the disclosed embodiment determines the movement angle of the feature matching point based on the feature matching points of the first image and the feature matching points of the third image; determines the movement distance of the feature matching point based on the feature matching points of the first image, the feature matching points of the second image and the feature matching points of the third image; and constructs the movement trajectory information of the feature matching point based on the movement angle of the feature matching point and the movement distance of the feature matching point, thereby realizing the accurate measurement of the motion trajectory information and providing a reliable data basis for the subsequent smoke cloud judgment.

[0063] Figure 3 A flowchart of another smoke cloud detection method provided for an embodiment of the present disclosure, the method of this embodiment can be combined with each optional scheme in the smoke cloud detection method provided in the above embodiments. Based on the above embodiments, this embodiment optionally, after acquiring three consecutive frames of images, further includes: performing moving target detection on the three consecutive frames of images, and drawing a bounding box of the moving target in the image when there is a moving target in the image; correspondingly, the number of the feature matching points is multiple, and if the motion trajectory information of the feature matching point meets the preset motion trajectory feature condition of the smoke, then the detection result is determined to be smoke, and if the motion trajectory information of the feature matching point meets the preset motion trajectory feature condition of the cloud, then the detection result is determined to be cloud, it also includes: if the number of feature matching points in the bounding box of the moving target with the detection result of smoke is greater than the number of feature matching points with the detection result of cloud, then the moving target is determined to be smoke; if the number of feature matching points in the bounding box of the moving target with the detection result of smoke is not greater than the number of feature matching points with the detection result of cloud, then the moving target is determined to be cloud.

[0064] like Figure 3 As shown, the method includes:

[0065] S310: Acquire three consecutive image frames, where the three consecutive image frames include a first image, a second image, and a third image.

[0066] S320: Perform moving target detection on the three consecutive frames of images, and if a moving target exists in the image, draw a boundary box of the moving target in the image.

[0067] Specifically, it is possible to determine whether there is a moving target detection in the image by using a multi-frame difference detection technology. If there is a moving target in the image, a bounding box of the moving target is drawn in the image to highlight the moving target. If there is no moving target in the image, the smoke cloud detection process is terminated.

[0068] S330 , performing feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image.

[0069] S340. Determine the motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image.

[0070] S350. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, determine that the detection result is smoke; if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, determine that the detection result is cloud.

[0071] S360. If the number of feature matching points with a detection result of smoke in the bounding box of the moving target is greater than the number of feature matching points with a detection result of cloud, determine that the moving target is smoke; if the number of feature matching points with a detection result of smoke in the bounding box of the moving target is not greater than the number of feature matching points with a detection result of cloud, determine that the moving target is cloud.

[0072] Exemplarily, Figure 4A and Figure 4B is a schematic diagram of a smoke and cloud detection result provided by an embodiment of the present disclosure. As Figure 4A shown, the red dots represent the feature matching points with a detection result of smoke. If only red dots are included within the bounding box of the moving target, it can be determined that the moving target is smoke. As Figure 4B shown, the yellow dots represent the feature matching points with a detection result of cloud. If only yellow dots are included within the bounding box of the moving target, it can be determined that the moving target is cloud.

[0073] Figure 5 is a flowchart of another smoke and cloud detection method provided by an embodiment of the present disclosure. The method of this embodiment is a preferred example of the above embodiment. As Figure 5 shown, the method includes:

[0074] Obtain three consecutive frames of images, where the three consecutive frames of images include a first image, a second image, and a third image. Perform moving target detection on the three consecutive frames of images. In the case where there is a moving target in the image, draw a bounding box of the moving target in the image. In the case where there is no moving target in the image, end the smoke and cloud detection process. Perform SIFT feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image. Determine the motion angle and motion distance of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image. If the motion angle of the feature matching points is greater than zero degrees and less than one hundred and eighty degrees, and the motion distance of the feature matching points is greater than 10, then determine that the detection result is smoke. If the motion angle of the feature matching points is greater than negative one hundred and eighty degrees and less than zero degrees, and the motion distance of the feature matching points is less than 10, then determine that the detection result is cloud. If the number of feature matching points with a detection result of smoke in the bounding box of the moving target is greater than the number of feature matching points with a detection result of cloud, then determine that the moving target is smoke; if the number of feature matching points with a detection result of smoke in the bounding box of the moving target is not greater than the number of feature matching points with a detection result of cloud, then determine that the moving target is cloud. The above technical solution realizes the accurate distinction and detection of smoke and cloud.

[0075] Figure 6 The following is a schematic structural diagram of a smoke and cloud detection device provided by an embodiment of the present disclosure. As Figure 6 shown, the device includes:

[0076] A continuous image acquisition module 510, configured to obtain three consecutive frames of images, where the three consecutive frames of images include a first image, a second image, and a third image;

[0077] An image feature matching module 520, configured to perform feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image;

[0078] A motion trajectory information determination module 530, configured to determine motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image;

[0079] A smoke and cloud detection result determination module 540, configured to determine that the detection result is smoke if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, and determine that the detection result is cloud if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud.

[0080] The technical solution of the embodiment of the present disclosure obtains three consecutive images, which include a first image, a second image, and a third image, and then performs feature matching on the three consecutive images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image. Based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image, the motion trajectory information of the feature matching points is determined. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, the detection result is determined to be smoke. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, the detection result is determined to be cloud. In the above technical solution, accurate distinction and detection of smoke and cloud are achieved.

[0081] Based on any optional technical solution in the embodiment of the present disclosure, optionally, the motion trajectory information determination module 530 includes:

[0082] A motion angle determination unit, configured to determine the motion angle of the feature matching points based on the feature matching points of the first image and the feature matching points of the third image;

[0083] A motion distance determination unit, configured to determine the motion distance of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image;

[0084] A motion trajectory information construction unit, configured to construct the motion trajectory information of the feature matching points based on the motion angle of the feature matching points and the motion distance of the feature matching points.

[0085] Based on any optional technical solution in the embodiment of the present disclosure, optionally, the motion angle determination unit may specifically be used for:

[0086] Determine a point-to-point vector based on the feature matching points of the first image and the feature matching points of the third image;

[0087] Determine the included angle between the point-to-point vector and the horizontal direction, and use the included angle between the point-to-point vector and the horizontal direction as the motion angle of the feature matching points.

[0088] Based on any optional technical solution in the embodiment of the present disclosure, optionally, the smoke and cloud detection result determination module 540 may further specifically be used for:

[0089] If the motion angle of the feature matching points is greater than zero degrees and less than one hundred and eighty degrees, and the motion distance of the feature matching points is greater than a preset distance threshold, determine the detection result to be smoke.

[0090] Based on any optional technical solution in the embodiment of the present disclosure, optionally, the smoke and cloud detection result determination module 540 may further specifically be used for:

[0091] If the movement angle of the feature matching point is greater than negative one hundred and eighty degrees and less than zero degrees, and the movement distance of the feature matching point is less than a preset distance threshold, the detection result is determined to be a cloud.

[0092] Based on any optional technical solution in the embodiments of the present disclosure, optionally, the smoke cloud detection device further includes:

[0093] A moving target detection module, used to perform moving target detection on the three consecutive frames of images, and if there is a moving target in the image, draw a boundary box of the moving target in the image;

[0094] Accordingly, the number of the feature matching points is multiple, and the smoke cloud detection device further includes:

[0095] A mobile target smoke and cloud detection module is used to determine that the mobile target is smoke if the number of feature matching points in the bounding box of the mobile target whose detection result is smoke is greater than the number of feature matching points whose detection result is cloud; and to determine that the mobile target is cloud if the number of feature matching points in the bounding box of the mobile target whose detection result is smoke is not greater than the number of feature matching points whose detection result is cloud.

[0096] The smoke cloud detection device provided in the embodiments of the present disclosure can execute the smoke cloud detection method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0097] Figure 7 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0098] like Figure 7As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0099] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0100] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the smoke detection method, which includes:

[0101] Obtaining three consecutive frames of images, the three consecutive frames of images including a first image, a second image, and a third image;

[0102] Performing feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image;

[0103] Determining motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image;

[0104] If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, determining the detection result as smoke; if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, determining the detection result as cloud.

[0105] In some embodiments, the smoke detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the smoke detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the smoke detection method by any other suitable means (e.g., by means of firmware).

[0106] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0107] The computer programs for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on a remote machine or server.

[0108] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0109] For purposes of providing an interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0110] The systems and techniques described herein can be implemented in a computing system that includes a back-end component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0111] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0113] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the smoke cloud detection method provided in any embodiment of the present disclosure.

[0114] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A smoke cloud detection method, characterized in that: Including: Obtain three consecutive frames of images, where the three consecutive frames of images include a first image, a second image, and a third image; Perform feature matching on the three consecutive frames of images to obtain feature matching points of the first image, feature matching points of the second image, and feature matching points of the third image; Determine the motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image; If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, determine the detection result as smoke. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, determine the detection result as cloud.

2. The method according to claim 1, characterized in that The determining the motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image includes: Determine the motion angle of the feature matching points based on the feature matching points of the first image and the feature matching points of the third image; Determine the motion distance of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image; Construct the motion trajectory information of the feature matching points based on the motion angle and the motion distance of the feature matching points.

3. The method according to claim 2, characterized in that, The determining the motion angle of the feature matching points based on the feature matching points of the first image and the feature matching points of the third image includes: Determine the point-to-point vector based on the feature matching points of the first image and the feature matching points of the third image; Determine the angle between the point-to-point vector and the horizontal direction, and use the angle between the point-to-point vector and the horizontal direction as the motion angle of the feature matching points.

4. The method according to claim 2, wherein The if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, then determine the detection result as smoke includes: If the motion angle of the feature matching points is greater than zero degrees and less than one hundred and eighty degrees, and the motion distance of the feature matching points is greater than the preset distance threshold, then determine the detection result as smoke.

5. The method according to claim 2, characterized in that The if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, then determine the detection result as cloud includes: If the motion angle of the feature matching points is greater than negative one hundred and eighty degrees and less than zero degrees, and the motion distance of the feature matching points is less than the preset distance threshold, then determine the detection result as cloud.

6. The method according to any one of claims 1-5, characterized in that, After obtaining the three consecutive frames of images, it further includes: Perform moving target detection on the three consecutive frames of images. When there is a moving target in the image, draw a bounding box of the moving target in the image; Correspondingly, the number of feature matching points is multiple. After the if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, then determine the detection result as smoke. If the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud, then determine the detection result as cloud, it further includes: If the number of feature matching points detected as smoke in the bounding box of the moving target is greater than the number of feature matching points detected as cloud, determine that the moving target is smoke; if the number of feature matching points detected as smoke in the bounding box of the moving target is not greater than the number of feature matching points detected as cloud, determine that the moving target is cloud.

7. A smoke cloud detection device, characterized in that: Including: A continuous image acquisition module for acquiring three consecutive images, the three consecutive images including a first image, a second image, and a third image; An image feature matching module for performing feature matching on the three consecutive images to obtain the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image; A motion trajectory information determination module for determining the motion trajectory information of the feature matching points based on the feature matching points of the first image, the feature matching points of the second image, and the feature matching points of the third image; A smoke and cloud detection result determination module for determining that the detection result is smoke if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of smoke, and determining that the detection result is cloud if the motion trajectory information of the feature matching points meets the preset motion trajectory feature conditions of cloud.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the smoke and cloud detection method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the smoke and cloud detection method according to any one of claims 1-6 when executed.

10. A computer program product, characterized in that, The computer program product includes a computer program that implements the smoke and cloud detection method according to any one of claims 1-6 when executed by a processor.

Images