CN111488772B - Method and device for detecting smoke - Google Patents
Method and device for detecting smoke Download PDFInfo
- Publication number
- CN111488772B CN111488772B CN201910087220.5A CN201910087220A CN111488772B CN 111488772 B CN111488772 B CN 111488772B CN 201910087220 A CN201910087220 A CN 201910087220A CN 111488772 B CN111488772 B CN 111488772B
- Authority
- CN
- China
- Prior art keywords
- video frame
- smoke
- camera
- frame images
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/10—Actuation by presence of smoke or gases, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means
Abstract
The disclosure provides a method and a device for detecting smoke, and belongs to the technical field of video monitoring. The method comprises the following steps: when smoke detection is performed, a suspected smoke area in a target video frame image can be determined according to the target video frame image, then a first preset number of video frame images continuously shot at a target position after the target video frame image is shot are acquired, wherein the target position is the position where a camera shooting the target video frame image is positioned, then the first preset number of video frame images are detected, and if the smoke area exists in a camera coverage area, a preset smoke prompt signal is controlled to be sent to a remote terminal device. By adopting the method and the device, the accuracy of smoke detection can be improved.
Description
Technical Field
The disclosure relates to the technical field of video monitoring, and in particular relates to a method and a device for detecting smoke.
Background
Smoke is an early manifestation of fire, so people often judge whether there is fire through smoke, and video-based smoke detection is attracting attention because video monitoring is not limited by spatial distance and scene, and video monitoring technology is continuously developed and video monitoring points are widely distributed.
In the related art, when detecting smoke, a video frame image is acquired from video monitoring, smoke characteristics are extracted from the video frame image, whether the smoke is real smoke is judged based on a preset experience threshold value, and whether prompt is needed is further determined.
Because the video frame images are easily affected by factors such as illumination, scenes, camera mounting modes and the like, whether the video frame images are real smoke is judged only based on a preset experience threshold value, and the false detection rate is possibly high.
Disclosure of Invention
In order to solve the problems of the prior art, embodiments of the present disclosure provide a method and apparatus for smoke detection. The technical scheme is as follows:
in a first aspect, there is provided a method of smoke detection, the method comprising:
determining a suspected smoke area in a target video frame image according to the target video frame image;
acquiring a first preset number of video frame images continuously shot at the target position after the target video frame images are shot, wherein the target position is the position of a camera when the target video frame images are shot;
detecting the first preset number of video frame images, and if a smoke area exists in the coverage area of the camera, controlling to send a preset smoke prompt signal to the remote terminal equipment.
Optionally, the camera is a rotary camera;
the acquiring, after capturing the target video frame image, before a first preset number of video frame images captured continuously at the target position, further includes:
and controlling the rotary camera to rotate to the target position.
Optionally, the method further comprises:
and if the coverage area of the camera does not exist in the smoke area, controlling the rotary camera to continue rotating.
Optionally, the detecting the first preset number of video frame images includes:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke area exists in a camera coverage area and a second probability that the smoke area does not exist in the camera coverage area;
and if the first probability is greater than or equal to the second probability, determining that a smoke area exists in the camera coverage area, and if the first probability is less than the second probability, determining that no smoke area exists in the camera coverage area.
Optionally, the method further comprises:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
In this way, a worker can be made to more quickly determine the smoke area.
Optionally, the determining, according to the target video frame image, that the suspected smoke area exists in the target video frame image includes:
inputting the data of the RGB channel of the target video frame image into a second preset classification model to obtain the probability of existence of a suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image;
and determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the non-existence of the suspected smoke area.
In this way, false positives can be prevented.
Optionally, the determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the non-existence of the suspected smoke area includes:
if the probability of the existence of the suspected smoke area is greater than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at the target position, wherein the second preset number of video frame images refer to video frame images on the left side and video frame images on the right side which are adjacent to the target video frame image in time;
and if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics and color characteristics.
In this way, false positives can be prevented.
In a second aspect, there is provided an apparatus for smoke detection, the apparatus comprising:
the determining module is used for determining a suspected smoke area in the target video frame image according to the target video frame image;
the acquisition module is used for acquiring a first preset number of video frame images continuously shot at the target position after the target video frame images are shot, wherein the target position is the position where a camera shooting the target video frame images is positioned;
and the control module is used for detecting the first preset number of video frame images, and if the smoke area exists in the coverage area of the camera, the control module is used for controlling the remote terminal equipment to send a preset smoke prompt signal.
Optionally, the camera is a rotary camera;
the control module is further configured to:
and controlling the rotary camera to rotate to the target position before a first preset number of video frame images continuously shot at the target position after the target video frame images are shot.
Optionally, the control module is further configured to:
and if the coverage area of the camera does not exist in the smoke area, controlling the rotary camera to continue rotating.
Optionally, the control module is configured to:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke area exists in a camera coverage area and a second probability that the smoke area does not exist in the camera coverage area;
and if the first probability is greater than or equal to the second probability, determining that a smoke area exists in the camera coverage area, and if the first probability is less than the second probability, determining that no smoke area exists in the camera coverage area.
Optionally, the control module is further configured to:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
Optionally, the determining module is configured to:
inputting the data of the RGB channel of the target video frame image into a second preset classification model to obtain the probability of existence of a suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image;
and determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the non-existence of the suspected smoke area.
Optionally, the determining module is configured to:
if the probability of the existence of the suspected smoke area is greater than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at the target position, wherein the second preset number of video frame images refer to video frame images on the left side and video frame images on the right side which are adjacent to the target video frame image in time;
and if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics and color characteristics.
In a third aspect, there is provided an apparatus for smoke detection, the apparatus comprising: a processor and a memory; the memory is used for storing at least one instruction; the processor is configured to execute at least one instruction stored in the memory, to implement the method steps of the first aspect.
In a fourth aspect, a computer readable storage medium is provided, having stored therein at least one instruction, which when executed by a processor, implements the method steps of the first aspect described above.
The technical scheme provided by the embodiment of the disclosure has the beneficial effects that at least:
in the embodiment of the disclosure, when smoke detection is performed, a suspected smoke area in a target video frame image can be determined according to the target video frame image, then a first preset number of video frame images continuously shot at a target position after the target video frame image is shot are acquired, wherein the target position is the position where a camera shooting the target video frame image is positioned, then the first preset number of video frame images are detected, and if the smoke area exists in a camera coverage area, a preset smoke prompt signal is controlled to be sent to a remote terminal device. In this way, since the secondary judgment is performed after determining that the suspected smoke region exists, instead of the judgment based on only the empirical threshold, the accuracy of smoke detection can be improved.
Drawings
FIG. 1 is a schematic diagram of a camera provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of smoke detection provided by an embodiment of the present disclosure;
FIG. 3 is a flow chart of a method of smoke detection provided by an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a preset classification model provided by an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a smoke detection structure provided by an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a camera according to an embodiment of the present disclosure.
Detailed Description
For the purposes of clarity, technical solutions and advantages of the present disclosure, the following further details the embodiments of the present disclosure with reference to the accompanying drawings.
Embodiments of the present disclosure provide a method of smoke detection, the subject of which may be a camera or a detection device. The camera can be any camera which can be used for shooting video frame images, such as a heavy-duty tripod head type camera, a ball camera, a gun camera and other cameras. The detection device may be a computer, a server, etc.
The camera may be provided with a processor, a memory and a transceiver, the processor may be used for performing smoke detection processing and controlling the processing of capturing video frame images, the memory may be used for storing data required in the smoke detection process and generated data, and the transceiver may be used for receiving and transmitting data.
The detection device may be provided with a processor, which may be used for the processing of the smoke detection, a memory, which may be used for storing data required in the smoke detection process and the resulting data, and a transceiver, which may be used for receiving and transmitting data.
When the execution subject is the detection device, the detection device may establish a data connection with the camera, and the camera may send the captured video frame image to the detection device for smoke detection by the detection device.
In this embodiment, the camera is taken as an execution body to perform detailed description of the scheme, and other cases are similar to the detailed description, so that the description of this embodiment is not repeated.
Before implementation, first, application scenarios and related concepts of the embodiments of the present disclosure will be described:
smoke is an early manifestation of fire, so that whether a fire is present or not can be judged by smoke, and further, the occurrence of the fire can be avoided. The method can be mainly applied to forest fire prevention monitoring, straw combustion monitoring and pollutant emission monitoring.
Ball machine: as shown in figure 1, the camera is fully called a dome camera, is representative of the development of modern television monitoring, integrates the functions of a color integrated camera, a cradle head, a decoder, a protective cover and the like, is convenient to install and use, has simple and powerful functions, and is widely applied to monitoring of open areas. The ball machine can automatically rotate, and the shooting range is wider.
Gun machine: is one of the monitoring type CCD (charge coupled device ) cameras. As shown in fig. 1, the exterior of the bolt is generally rectangular parallelepiped, with a C/CS lens interface in front, and the bolt does not include a lens. The so-called bolt is mainly distinguished from the exterior, lens mounting interface. After the gun bolt is installed, the gun bolt can not automatically rotate.
Fixing the camera: a camera that cannot be rotated.
A rotary camera: in contrast to a fixed camera, a camera can be rotated about an axis.
As shown in fig. 2, the embodiment of the disclosure provides a method for detecting smoke, and taking a camera as a fixed camera as an example, the execution flow of the method may be as follows:
step 201, determining that a suspected smoke area exists in the target video frame image according to the target video frame image.
The target video frame image is any video frame image shot by the camera. A suspected smoke area refers to an area where smoke is likely to be present.
In implementation, a worker may install a camera in an area to be monitored, after the camera is installed successfully, may capture a video frame image, may store each time one video frame image is captured, may determine whether a suspected smoke area exists in the target video frame image according to the one video frame image (which may be referred to as a target video frame image later), and if it is determined that a suspected smoke area exists in the target video frame image, perform the processing of subsequent steps 202 to 203.
The captured video frame image may be captured periodically (e.g., 1 second) or continuously, and the video frame image may be obtained from a video obtained by capturing an image.
Alternatively, the process of determining the suspected smoke region may be as follows:
inputting the data of the RGB channels of the target video frame image into a second preset classification model to obtain the probability of existence of the suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image. And determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the suspected smoke area not existing.
In implementation, a second preset classification model may be trained in advance, where the second preset classification model includes a convolution layer, a pooling layer, and a full-connection layer, where the convolution layer may be used to extract image depth features, the pooling layer may be used to perform dimension reduction processing, and the full-connection layer is used to output a position, a category, and a confidence level of the category of the target frame. The input of the second preset classification model is the data of three RGB channels of the target video frame image, the image features are extracted through the convolution layer, the pooling layer performs dimension reduction treatment on the image features, the position, the confidence and the category of the target frame are output by the full-connection layer, and the category comprises a suspected smoke area and a non-suspected smoke area.
The second preset classification model can be obtained, the data of the RGB channel of the target video frame image is input into the second preset classification model, the output is the position of the suspected smoke area, the confidence of the suspected smoke area and the confidence of the non-suspected smoke area (the sum of the confidence of the suspected smoke area and the confidence of the non-suspected smoke area is equal to 1), and the confidence is the same as the probability, so that the probability of the existence of the suspected smoke area and the probability of the non-existence of the suspected smoke area can be obtained. And then determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the non-existence of the suspected smoke area.
Optionally, in order to filter false alarms occurring in a short time, a suspected smoke area in a target video frame image may be determined based on a video frame image temporally adjacent to the target video frame image, and the corresponding processing may be as follows:
and if the probability of the existence of the suspected smoke area is greater than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at the target position, wherein the second preset number of video frame images refer to the left video frame image and the right video frame image which are adjacent to the target video frame image in time. And if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics, color characteristics and motion characteristics.
Wherein the second preset number may be preset and stored in the camera, e.g. the second preset number may be 4 or the like. The position feature refers to the position of the suspected smoke area in the video frame image, the shape feature refers to the shape of the suspected smoke area, and the color feature refers to the color of the suspected smoke area.
In implementation, the camera may determine the probability of the existence of the suspected smoke region and the probability of the absence of the suspected smoke region, and if the probability of the existence of the suspected smoke region is greater than or equal to the probability of the absence of the suspected smoke region, may acquire a second preset number of video frame images captured at the target position, where the second preset number of video frame images refers to a left video frame image and a right video frame image that are temporally adjacent to the target video frame image, and the number of video frame images on the left side is generally the same as the number of frame images on the right side.
The camera may then extract features of the suspected smoke region in the second preset number of video frame images and extract features of the suspected smoke region in the target video frame image that are one or more of location features, shape features, and color features.
And judging whether the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, and if so, determining that the suspected smoke areas exist in the target video frame images.
In addition, if the probability of the existence of the suspected smoke area is smaller than the probability of the nonexistence of the suspected smoke area, the fact that the suspected smoke area does not exist generally is indicated, and subsequent processing, namely, the second preset number of video frame images shot at the target position are not acquired.
The left video frame image refers to a video frame image captured before the target video frame image, and the right video frame image refers to a video frame image captured after the target video frame image. In addition, when the above-mentioned judging features are associated, if the position information of the suspected smoke areas in the target video frame images is the same as the position information of the suspected smoke areas in the second preset number of video frame images (the distance may also be less than the first preset value (such as 5cm, etc.), it is determined that the features of the suspected smoke areas in the second preset number of video frame images are associated with the features of the suspected smoke areas in the target video frame images. If the color information of the suspected smoke areas in the target video frame images is the same as the color information of the suspected smoke areas in the second preset number of video frame images (or the similarity is higher than a second preset value (such as 90%), the feature of the suspected smoke areas in the second preset number of video frame images is determined to be associated with the feature of the suspected smoke areas in the target video frame images. If the shape information of the suspected smoke areas in the target video frame images is the same as the shape information of the suspected smoke areas in the second preset number of video frame images (or the similarity is higher than a third preset value (such as 90%), the feature of the suspected smoke areas in the second preset number of video frame images is determined to be associated with the feature of the suspected smoke areas in the target video frame images. If the plurality of features are included and all the plurality of features satisfy the association, it may be determined that the features of the suspected smoke areas in the second preset number of video frame images are associated with the features of the suspected smoke areas in the target video frame image.
For example, the feature includes position information and shape information, and if the position information of the suspected smoke region in the target video frame image is the same as the position information of the suspected smoke region in the second preset number of video frame images, and the position information of the suspected smoke region in the target video frame image is the same as the shape information of the suspected smoke region in the second preset number of video frame images, it may be determined that the feature of the suspected smoke region in the second preset number of video frame images is associated with the feature of the suspected smoke region in the target video frame image.
Therefore, as the video frame images adjacent to the target video frame image are also used for judging whether the suspected smoke area really exists, the determination of the suspected smoke area can be more accurate.
Step 202, acquiring a first preset number of video frame images continuously shot at a target position after shooting a target video frame image.
The target position is the position of a camera when the target video frame image is shot. The first preset number may be preset and stored at the camera, such as 16.
In an implementation, the camera may acquire a first preset number of video frame images taken consecutively at the target location after the target video frame images are taken.
Step 203, detecting a first preset number of video frame images, and if a smoke area exists in the coverage area of the camera, controlling to send a preset smoke prompt signal to the remote terminal equipment.
The remote terminal equipment refers to terminal equipment of monitoring staff.
In an implementation, the camera may detect a first preset number of video frame images, determine whether a smoke area exists in a coverage area of the camera, and if it is determined that the smoke area exists, send a preset smoke prompt signal to the remote terminal device. Thus, after receiving the smoke prompt signal sent by the camera, the remote terminal can play the smoke prompt signal so that a worker can see that smoke exists in the monitoring area of the camera.
Alternatively, the process of detecting the video frame image may be as follows:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke region exists in a camera coverage area and a second probability that the smoke region does not exist in the camera coverage area, determining that the smoke region exists in the camera coverage area if the first probability is greater than or equal to the second probability, and determining that the smoke region does not exist in the camera coverage area if the first probability is less than the second probability.
In implementation, a first preset classification model can be trained in advance, the first classification model comprises a convolution layer, a pooling layer and a full-connection layer, the convolution layer can be used for extracting image depth features, the pooling layer can be used for performing dimension reduction processing, and the full-connection layer can be used for outputting target confidence and categories. The input of the first classification model is data of three channels RGB of a video frame image, image features are extracted through a convolution layer, a pooling layer performs dimension reduction processing on the image features, a full connection layer outputs category and confidence level of the category, and the category comprises a smoke area and a non-smoke area.
The first preset classification model can be obtained, the data of RGB channels of the video frame images with the first preset number are input into the first preset classification model, the output is the confidence coefficient of the smoke area and the confidence coefficient of the smoke area which does not exist, the confidence coefficient of the smoke area is identical to the probability of the smoke area which does not exist, the confidence coefficient of the smoke area which does not exist is identical to the probability of the smoke area which does not exist, and therefore the first probability of the smoke area which exists and the second probability of the smoke area which does not exist can be obtained. And then judging the magnitude of the first probability and the second probability, if the first probability is larger than or equal to the second probability, determining that the smoke area exists in the coverage area of the camera, and if the first probability is smaller than the second area, determining that the smoke area does not exist in the coverage area of the camera.
Alternatively, in order to make it possible for the staff to know what area has smoke, position information or the like may be sent to the terminal, and the corresponding processing may be as follows:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
In an implementation, if it is determined that there is a smoke area, the location information of itself may be acquired, the location information may be determined as the location information of the smoke area, and a first preset number of video frame images photographed at the target location may be acquired, and then the location information of the smoke area and the first preset number of video frame images will be transmitted to the remote terminal device. In this way, the staff can be made aware of what areas are smoke, and can determine whether smoke is actually present or not based on the video frame images.
In addition, when the position information of the smoke area is sent to the remote terminal equipment, the video image shot when the position information is sent can be carried.
In addition, when the position information is not carried, the identification of the camera can be carried, so that the position of the smoke area can be determined based on the identification of the camera.
Another embodiment of the present disclosure provides that the camera is a rotating camera, as shown in fig. 3, a flow chart of a method of smoke detection may be as follows:
step 301, determining that a suspected smoke area exists in the target video frame image according to the target video frame image.
In implementation, the processing procedure of step 301 is identical to the processing procedure of step 201, and will not be described here again.
Alternatively, the process of detecting the video frame image may be as follows:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability of a smoke region and a second probability of a non-smoke region, determining that the smoke region exists if the first probability is greater than or equal to the second probability, and determining that the smoke region does not exist if the first probability is less than the second probability.
In implementation, the processing procedure is identical to the processing procedure in fig. 2, and will not be described here again.
Optionally, in order to filter false alarms occurring in a short time, a suspected smoke area in a target video frame image may be determined based on a video frame image adjacent to the target video frame image, and the corresponding processing may be as follows:
and if the probability of the existence of the suspected smoke area is greater than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at the target position, wherein the second preset number of video frame images refer to the left video frame image and the right video frame image which are adjacent to the target video frame image in time. And if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics, color characteristics and motion characteristics.
In implementation, the processing procedure is identical to the processing procedure in fig. 2, and will not be described here again.
Step 302, controlling the rotation camera to rotate to a target position.
In an implementation, if the camera is rotated, the rotation can be stopped every time the camera is rotated by a certain angle, the video frame image is shot, the shot video frame image is stored corresponding to the current position information, and the position information can be information such as the rotation angle. For example, the camera rotates clockwise, the camera has an initial position point, the initial position point is 0 degrees each time the camera passes through the initial position point, the initial position point of the camera is 0 degrees, the camera rotates 60 degrees, the target video frame image is shot, the target position is a position point of 60 degrees, the 60 degrees can be stored corresponding to the target video frame image, and the shooting time point is stored.
In this way, when the suspected smoke area exists in the target video frame image, the angle corresponding to the target video frame image can be acquired, and then the camera is controlled to rotate to the target position based on the angle. For example, a target video frame image is captured at 60 degrees, and the camera may be controlled to rotate to 60 degrees with respect to the initial position point.
Step 303, acquiring a first preset number of video frame images continuously shot at a target position after shooting a target video frame image.
In implementation, the processing procedure of step 303 is identical to the processing procedure of step 202, and will not be described here again.
Step 304, detecting a first preset number of video frame images, and if a smoke area exists in the coverage area of the camera, controlling to send a preset smoke prompt signal to the remote terminal equipment.
In implementation, the processing procedure of step 304 is identical to the processing procedure of step 203, and will not be described here again.
Alternatively, the process of detecting the video frame image may be as follows:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke region exists in a camera coverage area and a second probability that the smoke region does not exist in the camera coverage area, determining that the smoke region exists in the camera coverage area if the first probability is greater than or equal to the second probability, and determining that the smoke region does not exist in the camera coverage area if the first probability is less than the second probability.
In implementation, a first preset classification model can be trained in advance, the first classification model comprises a convolution layer, a pooling layer and a full-connection layer, the convolution layer can be used for extracting image depth features, the pooling layer can be used for performing dimension reduction processing, and the full-connection layer is used for outputting target confidence and categories. The input of the first classification model is data of three channels RGB of a video frame image, image features are extracted through a convolution layer, a pooling layer performs dimension reduction processing on the image features, and a full-connection layer outputs target confidence and categories, wherein the categories comprise a smoke region and a non-smoke region.
The first preset classification model may be obtained, the data of RGB channels of the first preset number of video frame images may be input to the first preset classification model, and the output is a first probability of a smoke area and a second probability of a non-smoke area. And then judging the magnitude of the first probability and the second probability, if the first probability is larger than or equal to the second probability, determining that the smoke area exists in the coverage area of the camera, and if the first probability is smaller than the second area, determining that the smoke area does not exist in the coverage area of the camera.
In addition, if there is no smoke area, the camera may be controlled to continue rotating, and the corresponding process may be as follows:
if the smoke area does not exist in the coverage area of the camera, the rotary camera is controlled to continue to rotate.
In practice, if there is no smoke area in the camera coverage area, the rotating camera may be controlled to continue to rotate.
Alternatively, in order to make it possible for the staff to know what area has smoke, position information or the like may be sent to the terminal, and the corresponding processing may be as follows:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
In implementation, the processing procedure is identical to the processing procedure in fig. 2, and will not be described here again.
The above description is made taking the camera as the execution subject, and if the detection device is taken as the execution subject, the difference is only that the detection device acquires the photographed image from the camera and that the detection device controls the camera to rotate.
In addition, it should be noted that, the first preset classification model and the second preset classification model are convolutional neural network algorithms obtained by training in advance, as shown in fig. 4, for the first preset classification model, the first preset classification model may include a convolutional layer, a pooling layer and a full-connection layer, the convolutional layer may be used to extract depth features of an image, the pooling layer may be used to perform dimension reduction processing, the full-connection layer may be used to output confidence degrees and categories of the categories, and when training is performed, an initial classification model may be constructed, then data of RGB three channels of a plurality of video frame images is used as input, parameter values of each parameter to be trained included in the initial classification model are trained, and parameter values of the parameter to be trained are substituted into the initial classification model to obtain the first preset classification model. In addition, the second preset classification model also includes a convolution layer, a pooling layer and a full connection layer, and the training manner is the same as that of the first preset classification model, which is not described herein.
In the embodiment of the disclosure, when smoke detection is performed, a suspected smoke area in a target video frame image can be determined according to the target video frame image, then a first preset number of video frame images continuously shot at a target position after the target video frame image is shot are acquired, wherein the target position is the position where a camera shooting the target video frame image is positioned, then the first preset number of video frame images are detected, and if the smoke area exists in a camera coverage area, a preset smoke prompt signal is controlled to be sent to a remote terminal device. In this way, since the secondary judgment is performed after determining that the suspected smoke region exists, instead of the judgment based on only the empirical threshold, the accuracy of smoke detection can be improved.
Based on the same technical concept, the embodiment of the present disclosure further provides a device for detecting smoke, as shown in fig. 5, including:
a determining module 510, configured to determine, according to a target video frame image, that a suspected smoke area exists in the target video frame image;
an obtaining module 520, configured to obtain a first preset number of video frame images continuously captured at the target position after capturing the target video frame image, where the target position is a position where a camera capturing the target video frame image is located;
and the control module 530 is configured to detect the first preset number of video frame images, and if a smoke area exists in the coverage area of the camera, control to send a preset smoke prompt signal to a remote terminal device.
Optionally, the camera is a rotary camera;
the control module 530 is further configured to:
and controlling the rotary camera to rotate to the target position before a first preset number of video frame images continuously shot at the target position after the target video frame images are shot.
Optionally, the control module 530 is further configured to:
and if the coverage area of the camera does not exist in the smoke area, controlling the rotary camera to continue rotating.
Optionally, the control module 530 is configured to:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke area exists in a camera coverage area and a second probability that the smoke area does not exist in the camera coverage area;
and if the first probability is greater than or equal to the second probability, determining that a smoke area exists in the camera coverage area, and if the first probability is less than the second probability, determining that no smoke area exists in the camera coverage area.
Optionally, the control module 530 is further configured to:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
Optionally, the determining module 510 is configured to:
inputting the data of the RGB channel of the target video frame image into a second preset classification model to obtain the probability of existence of a suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image;
and determining that the suspected smoke area exists in the target video frame image according to the probability of the suspected smoke area and the probability of the non-existence of the suspected smoke area.
Optionally, the determining module 510 is configured to:
if the probability of the existence of the suspected smoke area is greater than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at the target position, wherein the second preset number of video frame images refer to video frame images on the left side and video frame images on the right side which are adjacent to the target video frame image in time;
and if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics and color characteristics.
In the embodiment of the disclosure, when smoke detection is performed, a suspected smoke area in a target video frame image can be determined according to the target video frame image, then a first preset number of video frame images continuously shot at a target position after the target video frame image is shot are acquired, wherein the target position is the position where a camera shooting the target video frame image is positioned, then the first preset number of video frame images are detected, and if the smoke area exists in a camera coverage area, a preset smoke prompt signal is controlled to be sent to a remote terminal device. In this way, since the secondary judgment is performed after determining that the suspected smoke region exists, instead of the judgment based on only the empirical threshold, the accuracy of smoke detection can be improved.
It should be noted that: in the smoke detection device provided in the above embodiment, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the smoke detection device is divided into different functional modules, so as to perform all or part of the functions described above. In addition, the apparatus for detecting smoke and the method embodiment for detecting smoke provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the apparatus for detecting smoke and the method embodiment are detailed in the method embodiment, and are not repeated here.
Fig. 6 is a schematic structural diagram of a camera according to an embodiment of the present invention, where the camera 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 601 and one or more memories 602, where at least one instruction is stored in the memories 602, and the at least one instruction is loaded and executed by the processors 601 to implement the above-mentioned method steps of smoke detection.
The present disclosure also provides a smoke detection apparatus comprising a processor and a memory; the memory is used for storing at least one instruction; the processor is configured to execute at least one instruction stored in the memory, and implement the method steps of smoke detection described above.
The present disclosure also provides a computer readable storage medium having at least one instruction stored therein, which when executed by a processor, performs method steps for smoke detection.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The foregoing description of the preferred embodiments of the present disclosure is not intended to limit the disclosure, but rather to enable any modification, equivalent replacement, improvement or the like, which fall within the spirit and principles of the present disclosure.
Claims (12)
1. A method of smoke detection, the method comprising:
inputting the data of the red, green and blue RGB channels of the target video frame image into a second preset classification model to obtain the probability of existence of a suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image;
if the probability of the existence of the suspected smoke area is larger than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at a target position, wherein the second preset number of video frame images refer to a left video frame image and a right video frame image which are adjacent to the target video frame image in time, and the target position is the position where a camera shooting the target video frame image is located;
if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics and color characteristics;
acquiring a first preset number of video frame images continuously shot at the target position after shooting the target video frame image;
detecting the first preset number of video frame images, and if a smoke area exists in the coverage area of the camera, controlling to send a preset smoke prompt signal to the remote terminal equipment.
2. The method of claim 1, wherein the camera is a rotating camera;
the acquiring, after capturing the target video frame image, before a first preset number of video frame images captured continuously at the target position, further includes:
and controlling the rotary camera to rotate to the target position.
3. The method according to claim 2, wherein the method further comprises:
and if the coverage area of the camera does not exist in the smoke area, controlling the rotary camera to continue rotating.
4. A method according to any one of claims 1 to 3, wherein said detecting said first predetermined number of video frame images comprises:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke area exists in a camera coverage area and a second probability that the smoke area does not exist in the camera coverage area;
and if the first probability is greater than or equal to the second probability, determining that a smoke area exists in the coverage area of the camera, and if the first probability is less than the second probability, determining that no smoke area exists in the coverage area of the camera.
5. A method according to any one of claims 1 to 3, wherein the method further comprises:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
6. An apparatus for smoke detection, the apparatus comprising:
the determining module is used for inputting the data of the RGB channel of the target video frame image into a second preset classification model to obtain the probability of existence of the suspected smoke area and the probability of absence of the suspected smoke area in the target video frame image;
if the probability of the existence of the suspected smoke area is larger than or equal to the probability of the absence of the suspected smoke area, acquiring a second preset number of video frame images shot at a target position, wherein the second preset number of video frame images refer to a left video frame image and a right video frame image which are adjacent to the target video frame image in time, and the target position is the position where a camera shooting the target video frame image is located;
if the characteristics of the suspected smoke areas in the second preset number of video frame images are associated with the characteristics of the suspected smoke areas in the target video frame images, determining that the suspected smoke areas exist in the target video frame images, wherein the characteristics are one or more of position characteristics, shape characteristics and color characteristics, and determining that the suspected smoke areas exist in the target video frame images according to the target video frame images;
the acquisition module is used for acquiring a first preset number of video frame images continuously shot at the target position after the target video frame images are shot, wherein the target position is the position where a camera shooting the target video frame images is positioned;
and the control module is used for detecting the first preset number of video frame images, and if the smoke area exists in the coverage area of the camera, the control module is used for controlling the remote terminal equipment to send a preset smoke prompt signal.
7. The apparatus of claim 6, wherein the camera is a rotating camera;
the control module is further configured to:
and controlling the rotary camera to rotate to the target position before a first preset number of video frame images continuously shot at the target position after the target video frame images are shot.
8. The apparatus of claim 7, wherein the control module is further configured to:
and if the coverage area of the camera does not exist in the smoke area, controlling the rotary camera to continue rotating.
9. The apparatus of any one of claims 6 to 8, wherein the control module is configured to:
inputting the data of RGB channels of the first preset number of video frame images into a first preset classification model to obtain a first probability that a smoke area exists in a camera coverage area and a second probability that the smoke area does not exist in the camera coverage area;
and if the first probability is greater than or equal to the second probability, determining that a smoke area exists in the coverage area of the camera, and if the first probability is less than the second probability, determining that no smoke area exists in the coverage area of the camera.
10. The apparatus of any one of claims 6 to 8, wherein the control module is further configured to:
and controlling to send the position information of the smoke area and the first preset number of video frame images to the remote terminal equipment.
11. An apparatus for smoke detection comprising a processor and a memory; the memory is used for storing at least one instruction; the processor being configured to execute at least one instruction stored on the memory to perform the method steps of any one of claims 1-5.
12. A computer readable storage medium, characterized in that at least one instruction is stored in the computer readable storage medium, which at least one instruction, when executed by a processor, implements the method steps of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087220.5A CN111488772B (en) | 2019-01-29 | 2019-01-29 | Method and device for detecting smoke |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910087220.5A CN111488772B (en) | 2019-01-29 | 2019-01-29 | Method and device for detecting smoke |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111488772A CN111488772A (en) | 2020-08-04 |
| CN111488772B true CN111488772B (en) | 2023-09-22 |
Family
ID=71812325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910087220.5A Active CN111488772B (en) | 2019-01-29 | 2019-01-29 | Method and device for detecting smoke |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111488772B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2006202296A1 (en) * | 2006-05-30 | 2007-12-20 | Canon Kabushiki Kaisha | Digital video storage |
| CN101587622A (en) * | 2009-06-18 | 2009-11-25 | 任芳 | Forest rocket detection and recognition methods and equipment based on video image intelligent analysis |
| CN101738394A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting indoor smog |
| CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
| CN101916380A (en) * | 2010-09-08 | 2010-12-15 | 大连古野软件有限公司 | Video-based device and method for detecting smog |
| CN102136059A (en) * | 2011-03-03 | 2011-07-27 | 苏州市慧视通讯科技有限公司 | Video- analysis-base smoke detecting method |
| CN102567722A (en) * | 2012-01-17 | 2012-07-11 | 大连民族学院 | Early-stage smoke detection method based on codebook model and multiple features |
| CN103049460A (en) * | 2011-10-17 | 2013-04-17 | 天津市亚安科技股份有限公司 | Video surveillance scene information classifying and storing method and search method |
| CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
| CN104794486A (en) * | 2015-04-10 | 2015-07-22 | 电子科技大学 | Video smoke detecting method based on multi-feature fusion |
| KR20160048240A (en) * | 2014-10-23 | 2016-05-04 | 공주대학교 산학협력단 | Smoke detection method using density distribution characteristics of smoke |
| KR101620989B1 (en) * | 2015-02-12 | 2016-05-16 | 계명대학교 산학협력단 | Method of detecting fire automatically from video including night images and system for performing the same |
| JP2016110258A (en) * | 2014-12-03 | 2016-06-20 | 能美防災株式会社 | Smoke detection device and smoke detection method |
| CN105809120A (en) * | 2016-03-03 | 2016-07-27 | 魏晓峰 | Video image analyzing method and system |
| CN106228150A (en) * | 2016-08-05 | 2016-12-14 | 南京工程学院 | Smog detection method based on video image |
| CN106339664A (en) * | 2016-08-10 | 2017-01-18 | 杭州电子科技大学 | Color mixing model and multi-feature combination-based video smoke detection method |
| CN107749067A (en) * | 2017-09-13 | 2018-03-02 | 华侨大学 | Fire hazard smoke detecting method based on kinetic characteristic and convolutional neural networks |
| CN108537726A (en) * | 2017-03-03 | 2018-09-14 | 杭州海康威视数字技术股份有限公司 | A kind of method of track up, equipment and unmanned plane |
| CN108985192A (en) * | 2018-06-29 | 2018-12-11 | 东南大学 | A kind of video smoke recognition methods based on multitask depth convolutional neural networks |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971082A (en) * | 2013-01-31 | 2014-08-06 | 威联通科技股份有限公司 | Video object detecting system and method based on area conversion |
| CN110322659A (en) * | 2019-06-21 | 2019-10-11 | 江西洪都航空工业集团有限责任公司 | A kind of smog detection method |
-
2019
- 2019-01-29 CN CN201910087220.5A patent/CN111488772B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2006202296A1 (en) * | 2006-05-30 | 2007-12-20 | Canon Kabushiki Kaisha | Digital video storage |
| CN101738394A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for detecting indoor smog |
| CN101587622A (en) * | 2009-06-18 | 2009-11-25 | 任芳 | Forest rocket detection and recognition methods and equipment based on video image intelligent analysis |
| CN101872526A (en) * | 2010-06-01 | 2010-10-27 | 重庆市海普软件产业有限公司 | Smoke and fire intelligent identification method based on programmable photographing technology |
| CN101916380A (en) * | 2010-09-08 | 2010-12-15 | 大连古野软件有限公司 | Video-based device and method for detecting smog |
| CN102136059A (en) * | 2011-03-03 | 2011-07-27 | 苏州市慧视通讯科技有限公司 | Video- analysis-base smoke detecting method |
| CN103049460A (en) * | 2011-10-17 | 2013-04-17 | 天津市亚安科技股份有限公司 | Video surveillance scene information classifying and storing method and search method |
| CN102567722A (en) * | 2012-01-17 | 2012-07-11 | 大连民族学院 | Early-stage smoke detection method based on codebook model and multiple features |
| CN103116746A (en) * | 2013-03-08 | 2013-05-22 | 中国科学技术大学 | Video flame detecting method based on multi-feature fusion technology |
| KR20160048240A (en) * | 2014-10-23 | 2016-05-04 | 공주대학교 산학협력단 | Smoke detection method using density distribution characteristics of smoke |
| JP2016110258A (en) * | 2014-12-03 | 2016-06-20 | 能美防災株式会社 | Smoke detection device and smoke detection method |
| KR101620989B1 (en) * | 2015-02-12 | 2016-05-16 | 계명대학교 산학협력단 | Method of detecting fire automatically from video including night images and system for performing the same |
| CN104794486A (en) * | 2015-04-10 | 2015-07-22 | 电子科技大学 | Video smoke detecting method based on multi-feature fusion |
| CN105809120A (en) * | 2016-03-03 | 2016-07-27 | 魏晓峰 | Video image analyzing method and system |
| CN106228150A (en) * | 2016-08-05 | 2016-12-14 | 南京工程学院 | Smog detection method based on video image |
| CN106339664A (en) * | 2016-08-10 | 2017-01-18 | 杭州电子科技大学 | Color mixing model and multi-feature combination-based video smoke detection method |
| CN108537726A (en) * | 2017-03-03 | 2018-09-14 | 杭州海康威视数字技术股份有限公司 | A kind of method of track up, equipment and unmanned plane |
| CN107749067A (en) * | 2017-09-13 | 2018-03-02 | 华侨大学 | Fire hazard smoke detecting method based on kinetic characteristic and convolutional neural networks |
| CN108985192A (en) * | 2018-06-29 | 2018-12-11 | 东南大学 | A kind of video smoke recognition methods based on multitask depth convolutional neural networks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111488772A (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040709B (en) | Video monitoring method and device, monitoring server and video monitoring system | |
| US11410415B2 (en) | Processing method for augmented reality scene, terminal device, system, and computer storage medium | |
| WO2020057355A1 (en) | Three-dimensional modeling method and device | |
| JP6127152B2 (en) | Security monitoring system and corresponding alarm triggering method | |
| CN102833478B (en) | Fault-tolerant background model | |
| WO2019196009A1 (en) | Method for detecting defective pixel of image sensor, and photography apparatus, unmanned aerial vehicle and storage medium | |
| CN110402456B (en) | Abnormality detection system, abnormality detection method, and storage medium | |
| KR101038650B1 (en) | Adaptive modeling method for background image, detecting method and system for illegal-stopping and parking vehicle using it | |
| CN112257554B (en) | Forest fire recognition method, system, program and storage medium based on multiple spectra | |
| KR101442669B1 (en) | Method and apparatus for criminal acts distinction using intelligent object sensing | |
| CN111354024A (en) | Behavior prediction method for key target, AI server and storage medium | |
| CN112036242B (en) | Face picture acquisition method and device, computer equipment and storage medium | |
| CN111488772B (en) | Method and device for detecting smoke | |
| CN106303232A (en) | Terminal anti-theft method and device | |
| JP2011087214A (en) | Photographing system, method and program | |
| US20130083963A1 (en) | Electronic camera | |
| CN112738387B (en) | Target snapshot method, device and storage medium | |
| CN114495395A (en) | Human shape detection method, monitoring and early warning method, device and system | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device | |
| TWI448976B (en) | Ultra-wide-angle imaging method and system using the same | |
| CN108881860A (en) | A kind of artificial intelligence TERMINAL DEFENSE system and method | |
| JP7480841B2 (en) | Event management method, event management device, system and program | |
| CN108989757A (en) | A kind of artificial intelligence server-side system of defense and method | |
| JP2020136855A (en) | Monitoring system, monitor support device, monitoring method, monitor support method, and program | |
| CN111225178A (en) | Video monitoring method and system based on object detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |