CN114495395A - Human shape detection method, monitoring and early warning method, device and system - Google Patents
Human shape detection method, monitoring and early warning method, device and system Download PDFInfo
- Publication number
- CN114495395A CN114495395A CN202111599336.0A CN202111599336A CN114495395A CN 114495395 A CN114495395 A CN 114495395A CN 202111599336 A CN202111599336 A CN 202111599336A CN 114495395 A CN114495395 A CN 114495395A
- Authority
- CN
- China
- Prior art keywords
- infrared
- human
- preset
- monitoring
- information
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 120
- 238000001514 detection method Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000035945 sensitivity Effects 0.000 claims description 12
- 230000006698 induction Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 4
- 241001465754 Metazoa Species 0.000 abstract description 10
- 230000003068 static effect Effects 0.000 abstract description 5
- 238000013527 convolutional neural network Methods 0.000 description 11
- 230000015654 memory Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 239000000243 solution Substances 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000001746 injection moulding Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 229920000098 polyolefin Polymers 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/19—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using infrared-radiation detection systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19606—Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention discloses a human shape detection method, a monitoring and early warning method, a device, a system and a storage medium. Relates to the technical field of safety protection, wherein a human shape detection method comprises the following steps: receiving infrared monitoring information fed back by a preset infrared sensor through a shooting terminal, wherein the infrared monitoring information is obtained by monitoring a preset area through the infrared sensor; acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with a preset wavelength; recognizing initial image data by using a preset recognition network model, and recognizing human-shaped key characteristic data; and outputting a human shape detection result according to the human shape key characteristic data. Through the embodiment disclosed in the application, the key characteristic data of the human figure can be identified through the mode of combining the infrared sensor and the preset identification network model, so that the false alarm rate of the human figure detection on static human figure images, animals and the like is reduced to a great extent, and the accuracy of correct monitoring and early warning is improved.
Description
Technical Field
The invention relates to the technical field of safety protection, in particular to a human shape detection method, a monitoring and early warning method, a device and a system.
Background
Intelligent video monitoring is a branch of the application of computer vision technology in the field of security protection.
The shooting terminal is generally applied to a plurality of scenes, and when monitoring and early warning are performed through the shooting terminal in some scenes, a phenomenon of false early warning may occur, for example, in some dark scenes, a situation that people recognize images, animals, plants and the like exists, so that false early warning is caused.
In the related art, there are two main human shape detection methods for solving the problem of false early warning of a shooting terminal: the first method is as follows: usually, the neural network structure is optimized, and the training model is enriched, so that the model is richer and covers various scenes. For example, the method covers a scene with a darker environment and a scene with a more complex background, so that the recognition rate can be improved to a certain extent, but the optimized model cannot cover all scenes, and the model has a larger volume and occupies a larger storage space after being enriched, so that the method is not friendly to the terminal-side equipment with a low flash capacity, such as a photographing terminal, and the computational power requirement of the optimization algorithm structure on the platform is also improved, embedded equipment such as a photographing terminal (camera) does not have higher computational power due to hardware limitation, and the method has an improved requirement on hard conditions such as hardware, so that the cost is increased.
In the related art, the second method is: the sensitivity of the recognition algorithm is reduced, so that although the false alarm rate can be reduced, the false alarm rate also can be missed. The method is equivalent to sacrificing part of recognition accuracy rate in exchange for low false alarm rate.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a human shape detection method, a monitoring and early warning method, a device and a system, which can identify key characteristic data of the human shape in a mode of combining an infrared sensor and a preset identification network model so as to determine that a target object is a human, thereby reducing the false detection rate of human shape detection on static human shape images, animals and the like to a great extent and improving the accuracy of human shape detection.
In order to achieve the above object, a first aspect of the embodiments of the present disclosure provides a human form detection method, including:
receiving infrared monitoring information fed back by a preset infrared sensor, wherein the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with a preset wavelength;
recognizing initial image data by using a preset recognition network model, and recognizing human-shaped key characteristic data;
and outputting a human shape detection result according to the human shape key characteristic data.
In some embodiments, before receiving infrared monitoring information fed back by the infrared sensor, the infrared monitoring information being obtained by monitoring a preset area by a preset infrared sensor, the human form detection method further includes:
receiving a human-shaped detection mode starting instruction;
entering a preset human shape detection mode according to a human shape detection mode starting instruction;
and according to the human shape detection mode, starting the infrared sensor to monitor the preset area.
In some embodiments, the infrared monitoring information includes at least one of: the target monitoring information receives the infrared monitoring information fed back by the preset infrared sensor, and the infrared monitoring information is obtained by the infrared sensor monitoring preset area, and comprises:
acquiring a Fresnel lens arranged outside an infrared sensor;
and monitoring a target object in a preset area according to the Fresnel lens, and receiving target monitoring information fed back by the Fresnel lens.
In some embodiments, acquiring initial image data of a preset region according to a monitoring condition that infrared monitoring information has infrared information with a preset wavelength includes:
preprocessing the received infrared monitoring information to obtain infrared information with a preset wavelength, and focusing infrared rays to an infrared induction source of an infrared sensor through a Fresnel lens by the infrared information to enable the infrared induction source to detect a target object;
and acquiring initial image data of the target object in the preset area according to the infrared information with the preset wavelength obtained by the infrared induction source.
In some embodiments, acquiring initial image data of a target object in a preset area according to infrared information with a preset wavelength obtained by an infrared sensing source includes:
acquiring video data corresponding to a target object according to infrared information with preset wavelength sensed by an infrared sensing source;
carrying out decoding operation on the video data to obtain a coded frame of the video data;
and performing bitmap operation on the key frame in the coding frame according to a preset operation function to generate initial image data.
In some embodiments, recognizing the human-shaped key feature data by using the preset recognition network model to recognize the initial image data comprises:
identifying an application scene of the initial image data by using the identification network model;
identifying the initial image data according to the application scene through the identification network model to generate target image data;
and marking the key parts of the human shape in the target image data to generate key characteristic data of the human shape.
In order to achieve the above object, a second aspect of the embodiments of the present disclosure provides a monitoring and early warning method, including:
acquiring a human shape detection result, wherein the human shape detection result is obtained by the human shape detection method provided by the first aspect disclosed by the embodiment of the disclosure;
acquiring key characteristic data of the corresponding human shape according to the human shape detection result;
if the confidence coefficient of the human-shaped key characteristic data is greater than or equal to the confidence coefficient threshold value of the preset sensitivity, generating early warning information and giving an alarm;
and if the confidence coefficient of the human-shaped key feature data is smaller than the confidence coefficient threshold value, not giving an alarm.
To achieve the above object, a third aspect of the embodiments of the present disclosure provides a human form detecting apparatus, including:
the receiving module is used for receiving infrared monitoring information fed back by a preset infrared sensor, and the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
the acquisition module is used for acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with preset wavelength;
the identification module is used for identifying initial image data by using a preset identification network model and identifying human-shaped key characteristic data;
and the output module is used for outputting the human shape detection result according to the human shape key characteristic data.
To achieve the above object, a fourth aspect of the embodiments of the present disclosure provides a human form detection system, including:
a human-shaped detection device;
shooting a terminal; the shooting terminal comprises an infrared sensor;
the human shape detection device performs:
a human form detection method as described in the first aspect above.
To achieve the above object, a fifth aspect of the embodiments of the present disclosure proposes a storage medium which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute:
a human form detection method as described in the first aspect above.
According to the human shape detection method, the monitoring and early warning method, the device and the system provided by the embodiment of the invention, at least the following beneficial effects are achieved:
according to the humanoid detection method, the monitoring early warning method, the device and the system provided by the embodiment of the disclosure, firstly, infrared monitoring information fed back by a preset infrared sensor is received through a shooting terminal, and the infrared monitoring information is obtained by monitoring a preset area through the infrared sensor; acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with a preset wavelength; recognizing initial image data by using a preset recognition network model, and recognizing human-shaped key characteristic data; outputting a human shape detection result according to the human shape key characteristic data; according to the human shape detection result, if the confidence of the human shape key characteristic data is greater than or equal to the confidence threshold of the preset sensitivity, generating early warning information and giving an alarm; and if the confidence coefficient of the human-shaped key feature data is smaller than the confidence coefficient threshold value, not giving an alarm. Through the embodiment of the disclosure, the key characteristic data of the human figure can be identified through the combination of the infrared sensor and the preset identification network model, so that the target object is determined to be a human, the false alarm rate of human figure detection on static human figure images, animals and the like is reduced to a great extent, and the accuracy of correct monitoring and early warning is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further described with reference to the following figures and examples, in which:
FIG. 1 is a first flowchart illustrating a human form detection method according to the present invention;
fig. 2 is a second flowchart illustrating a human form detection method added before step S100 in fig. 1;
FIG. 3 is a flowchart illustrating the step S100 in FIG. 1;
FIG. 4 is a flowchart illustrating a specific process of step S200 in FIG. 1;
FIG. 5 is a flowchart illustrating a specific process of step S220 in FIG. 4;
fig. 6 is a specific flowchart of step S300 in fig. 1.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and larger, smaller, larger, etc. are understood as excluding the present numbers, and larger, smaller, inner, etc. are understood as including the present numbers. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
In the description of the present invention, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
First, several terms referred to in the present application are resolved:
shooting a terminal: also called as a CAMERA (CAMERA or WEBCAM), also called as a computer CAMERA, a computer eye, an electronic eye, etc., is a video input device, and is widely used in video conferences, telemedicine, infrared monitoring, etc. Common people can also have image and voice conversations and communications with each other through the camera in the network. In addition, people can also use the method for various popular digital images, video and audio processing and the like.
An infrared sensor: also called PIR, which is a type of sensor that performs data processing using infrared rays, has the advantage of high sensitivity, etc., and the infrared ray sensor can control the operation of the driving device. The infrared sensor is used for detecting a human body, particularly, by using sensitivity in the far infrared range, and the wavelength of infrared is longer than that of visible light and shorter than that of radio waves.
A mobile terminal device: in the embodiments of the present application, the terminal device is a computer, a smart phone, a tablet, or the like that can perform communication.
Fresnel lens: the screw lens is usually a thin sheet made of polyolefin material through injection molding and is also made of glass, one surface of the lens is a smooth surface, the other surface of the lens is inscribed with concentric circles from small to large, and the texture of the lens is designed according to the requirements of light interference and interference, relative sensitivity and receiving angle so as to monitor a target object in a preset area.
CNN: convolutional Neural Networks, CNN for short, are a kind of feedforward Neural network.
RNN: recurrent Neural Networks, RNN for short, i.e. the current output of a sequence is also related to the previous output. The concrete expression is that the network will memorize the previous information and apply it to the calculation of the current output, i.e. the input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the last moment.
R-CNN network: the Region-based probabilistic Neural Networks or Regions with CNN features, R-CNN for short, is an algorithm combining a candidate Region algorithm SelectSearch and a Convolutional Neural network, and obviously improves the detection speed and precision.
FastRCNN network: the fast-forward target detection method is a two-stage target detection method, FastRCNN is an improvement on R _ CNN, and is the best method for detecting targets based on deep learning R-CNN series.
When monitoring and early warning are carried out through a shooting terminal in some scenes, a phenomenon of wrong early warning may exist, for example, in some dark scenes, a situation that people identify pictures, animals, plants and the like exists, and therefore wrong early warning is caused.
Based on this, the embodiment of the disclosure provides a human shape detection method, a monitoring and early warning device and a monitoring and early warning system, which can reduce the false alarm rate and improve the accuracy of correct monitoring and early warning.
Specifically, the following examples are provided to describe the human form detection method in the embodiments of the present disclosure.
As shown in fig. 1, which is a schematic flow chart of an implementation of a human form detection method provided in the embodiment of the present application, the human form detection method may include, but is not limited to, steps S100 to S400.
S100, receiving infrared monitoring information fed back by a preset infrared sensor, wherein the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
s200, acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with a preset wavelength;
s300, recognizing initial image data by using a preset recognition network model, and recognizing human-shaped key feature data;
and S400, outputting a human shape detection result according to the human shape key characteristic data.
In step S100 of some embodiments, infrared monitoring information fed back by a preset infrared sensor is received, and the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor. It can be understood that the shooting terminal monitors the preset area according to the infrared sensor and the lens preset in the shooting terminal, and feeds back the monitoring condition of the monitoring preset area to the shooting terminal through the infrared sensor. The infrared monitoring information may be infrared information sensed by the infrared sensor in a preset area.
It should be noted that the preset area is an area where the user needs to perform monitoring and early warning, such as a factory area doorway area, a company doorway area, and the like, and the area may be changed according to the user requirement, which is not further limited in the embodiment disclosed in the present application.
In step S200 of some embodiments, initial image data of a preset area is obtained according to a monitoring condition that infrared monitoring information has infrared information with a preset wavelength. It can be understood that the shooting terminal records the monitoring condition when infrared information exists in the infrared monitoring information according to the infrared monitoring information fed back by the infrared sensor, and collects initial image data of the infrared information existing in the preset area when the preset area is monitored according to the monitoring condition.
Furthermore, the method can be used for preprocessing received target monitoring information to obtain infrared information, focusing the infrared information to an infrared induction source of an infrared sensor through a Fresnel lens, and collecting initial image data according to the induction information of the infrared induction source.
It should be noted that, the wavelength of the infrared ray is a preset wavelength, and the preset wavelength is: 8-14 μm, it can be understood that, under normal conditions, a human body has a constant body temperature, generally about 37 ℃, and at this time, the human body can emit infrared rays with a wavelength in a range of 8-14 μm, and when the shooting terminal monitors a preset area through the infrared sensor, when the infrared rays with the preset wavelength are monitored, the corresponding image is recorded at this time, and corresponding initial image data is acquired.
In some practical scenes, animals, plants, and the like can emit infrared rays with preset wavelengths under certain specific conditions, so people in a monitoring picture cannot be distinguished in detail, and based on this, in step S300 of some embodiments, the embodiment of the present application further discloses that initial image data is identified by using a preset identification network model, and key feature data of human forms is identified. It is understood that the specific implementation steps can be as follows: firstly, inputting initial image data into a recognition network model for recognition and learning to generate target image data, and then labeling key parts of human shapes in the target image data to generate key characteristic data of human shapes. Therefore, the human shape data in the initial image data can be distinguished for early warning according to the generated human shape key characteristic data.
It should be noted that the recognition network model may be a FastRCNN network, which is a two-stage target detection method, and FastRCNN is an improvement on R _ CNN, which is the best method for target detection based on deep learning R-CNN series.
Further, the human shape key feature data refers to human face data, height data, waist data and the like which are identified through the anchor frame, and human shape key part data of the human shape can be judged.
In step S400 of some embodiments, a human form detection result is output according to the human form key feature data. It is understood that the processor of the photographing terminal outputs detection information of a human form detection result according to the human form key feature data generated in step S300, that is, a target object in the preset area is detected as a human being, not a plant, an animal, or the like.
In some embodiments, as shown with reference to fig. 2, a human form detection method may further include, but is not limited to, steps S101 to S103 before performing step S100.
S101, receiving a human-shaped detection mode starting instruction;
s102, entering a preset humanoid detection mode according to a humanoid detection mode starting instruction;
and S103, starting the infrared sensor for monitoring a preset area according to the human shape detection mode.
In step S101 of some embodiments, a human form detection mode initiation instruction is received. It can be understood that, when the shooting terminal receives an operation from a user, a processor of the shooting terminal sends a human shape detection mode starting instruction, and then the shooting terminal enters the human shape detection mode according to the human shape detection mode starting instruction.
It should be noted that the shooting terminal has multiple modes, each mode has different functions, and each mode can open the corresponding demand mode and close the demand mode at any time according to the operation command required by the user.
In step S102 of some embodiments, a preset human shape detection mode is entered according to a human shape detection mode start instruction. It can be understood that the shooting terminal enters the human shape detection mode according to the human shape detection mode start instruction obtained in step S101, so as to monitor the preset area in the human shape detection mode, and recognize the detected initial image data according to the preset recognition network model in the human shape detection mode, so as to recognize the human shape key feature data, and output the human shape detection result according to the human shape key feature data.
In step S103 of some embodiments, the infrared sensor is activated to monitor the predetermined area according to the human shape detection mode. It can be understood that, after the photographing terminal enters the human shape detection mode according to step S102, the infrared sensor is started, wherein the mode of starting the infrared sensor may be automatic program starting, that is, after the photographing terminal enters the human shape detection mode, the infrared sensor is directly started, so as to monitor the preset area according to the infrared sensor.
It should be noted that, when the shooting terminal receives a user request, the shooting terminal exits the human shape detection mode, and along with an instruction for closing the shooting terminal exiting the human shape detection mode, the shooting terminal also stops the operation of the infrared sensor, and does not perform infrared monitoring any more.
In some embodiments, as shown with reference to fig. 3, step S100 may also include, but is not limited to, steps S110 to S120.
S110, acquiring a Fresnel lens arranged outside the infrared sensor;
and S120, monitoring a target object in a preset area according to the Fresnel lens, and receiving target monitoring information fed back by the Fresnel lens.
In step S110 of some embodiments, a fresnel lens disposed outside the infrared sensor is acquired. It is understood that the photographing terminal acquires a fresnel lens provided outside the infrared ray sensor, which is typically packaged outside the infrared ray sensor.
It should be noted that, the fresnel lens is also called a screw lens, and is usually a sheet made of polyolefin material by injection molding, and is also made of glass, one surface of the lens is a smooth surface, and the other surface is inscribed with concentric circles from small to large, and the texture of the fresnel lens is designed according to the requirements of light interference and interference, relative sensitivity and receiving angle, so as to monitor the target object in the preset area.
In step S120 of some embodiments, a target object in a preset area is monitored according to the fresnel lens, and target monitoring information fed back by the fresnel lens is received. It can be understood that the photographing terminal monitors a target object in a preset area according to the fresnel lens, wherein the target object is all living beings, including people, animals, plants, and the like, in the preset area, and the photographing terminal receives information of the target object monitored by the fresnel lens, that is, target detection information.
In some embodiments, as shown with reference to fig. 4, step S200 may also include, but is not limited to, steps S210-S220.
S210, preprocessing the received infrared monitoring information to obtain infrared information with a preset wavelength, and focusing infrared rays on an infrared induction source of an infrared sensor through a Fresnel lens to enable the infrared induction source to detect a target object;
and S220, acquiring initial image data corresponding to the target object according to the infrared information with the preset wavelength sensed by the infrared sensing source.
In step S210 of some embodiments, the received infrared monitoring information is preprocessed to obtain infrared information with a preset wavelength, and the infrared information focuses infrared rays to an infrared sensing source of an infrared sensor through a fresnel lens, so that the infrared sensing source detects a target object. It can be understood that, the shooting terminal preprocesses the target monitoring information obtained in step S120 to obtain infrared information, and the specific implementation steps may be: firstly, analyzing and processing target monitoring information to generate target analysis data, and screening infrared information from the target monitoring information according to the target analysis data; the target object emits infrared rays with a preset wavelength in a preset area, and the photographing terminal focuses the infrared rays to the infrared sensing source of the infrared sensor through the fresnel lens obtained in step S110.
Carry out the preliminary treatment to the infrared monitoring information that receives, obtain the infrared ray information of predetermineeing the wavelength, still include: and analyzing and processing the target monitoring information to generate target analysis data. It can be understood that, the processor of the shooting terminal analyzes and processes the target monitoring information to generate target analysis data, that is, the target monitoring information also includes data information of other monitored wavelengths, and analyzes the target analysis data to make the wavelength information correspond to the data information mapped by the wavelengths. Therefore, target analysis data is generated, and infrared information is screened from target monitoring information according to the target analysis data.
It should be noted that, from the numerous target monitoring information, according to the wavelength information of the preset wavelength, the infrared ray information is screened out, and only the infrared ray with the wavelength ranging from 8 μm to 14 μm is screened out.
In step S220 of some embodiments, initial image data corresponding to the target object is collected according to the infrared information of the preset wavelength sensed by the infrared sensing source. It is understood that the specific implementation steps can be as follows: the method comprises the steps that firstly, a shooting terminal collects video data corresponding to infrared information according to sensing information of an infrared sensing source, decoding operation is conducted on the video data to obtain a coding frame of the video data, bitmap operation is conducted on a key frame in the coding frame according to a preset operation function to generate initial image data, and the sensing information is the infrared information with preset wavelength sensed by the infrared sensing source.
It should be noted that video data includes three types of encoded frames: key frames (I-frames), predicted frames (P-frames) and interpolated bi-directional frames (B-frames).
Further, the key frame is encoded according to the JPEG standard, independently of other encoded frames, which is the only accessible frame in the video data of the capture terminal, typically occurring once every 12 frames.
In some embodiments, as shown with reference to fig. 5, step S220 may also include, but is not limited to, steps S221 through S223.
S221, acquiring video data corresponding to a target object according to infrared information with preset wavelength sensed by an infrared sensing source;
s222, decoding the video data to obtain a coding frame of the video data;
and S223, performing bitmap operation on the key frame in the coding frame according to a preset operation function, and generating initial image data.
In step S221 of some embodiments, video data corresponding to the infrared information is collected according to sensing information of the infrared sensing source, where the sensing information is infrared information of a preset wavelength sensed by the infrared sensing source. It can be understood that the processor of the shooting terminal receives the sensing information of the infrared sensing source first, and then collects video data corresponding to the infrared information according to the sensing information of the infrared sensing source, that is, collects video data of the monitored target monitoring information with the infrared information.
It should be noted that, the infrared sensing source usually employs a pyroelectric element, and when the radiation temperature of the target object in the preset area changes, the pyroelectric element loses charge balance and releases charges outwards, and a subsequent circuit can generate an alarm signal after detection processing, so as to generate sensing information.
In step S222 of some embodiments, a decoding operation is performed on the video data to obtain an encoded frame of the video data. It can be understood that the processor of the shooting terminal performs a decoding operation on the video data collected in step S221 to obtain a plurality of encoded frames of the video data. And continuously storing the continuous key frames in a buffer area of a memory of the shooting terminal by taking the frames as units by intercepting the continuous key frames.
It should be noted that video data includes three types of encoded frames: key frames, predicted frames and interpolated bi-directional frames.
In step S223 of some embodiments, a bitmap operation is performed on the key frame in the encoded frame according to a preset operation function, so as to generate initial image data. It can be understood that, according to a preset operation function, the key frame in step S222 is operated, and then two consecutive frames in the buffer are converted into bitmap data and stored in another memory space, so as to generate initial image data.
It should be noted that the buffer may be a flash memory for temporarily accessing data, and the other memory space may be a hardware device with a storage function, such as a hard disk, for storing data for a long time.
In some embodiments, as shown with reference to fig. 6, step S300 may also include, but is not limited to, steps S310 to S330.
S310, identifying an application scene of the initial image data by using an identification network model;
s320, identifying the initial image data according to the application scene through the identification network model to generate target image data;
and S330, marking the human-shaped key part in the target image data to generate human-shaped key characteristic data.
In step S310 of some embodiments, an application scene corresponding to the initial image data is identified by using a preset identification network model. It can be understood that the application scenes may include a scene with sufficient light, a scene with dark light, a scene at about 37 degrees celsius, a scene with a preset temperature, a normal life scene, and the like, and the application scenes corresponding to the initial image data are identified through the identification network model.
It should be noted that the recognition network model may be a preset deep learning model, and the implementation of the algorithm may use a Fa ster-RCNN to develop an algorithm library for a third party, which is not further limited in the embodiment of the present application.
In step S320 of some embodiments, the initial image data is identified according to the application scenario by identifying the network model to generate the target image data. It can be understood that the initial image data includes image data including a target object, where the target object is capable of emitting infrared information with a wavelength in a range of 8 μm to 14 μm, the initial image data is converted into a corresponding image format according to an application scene, image features of a preset candidate region in the initial image data are obtained, and the image features are input into a classifier for feature matching, so as to obtain the target image data.
Further, the recognition network model is a neural network model having a human shape detection algorithm, and is capable of processing the initial image data, recognizing the target image data, and extracting the target image data, which is the image data of only the target object, by operations such as convolution and pooling.
In step S330 of some embodiments, human-shaped key parts in the target image data are labeled, and human-shaped key feature data is generated. It can be understood that after the target image data is generated, the human-shaped key parts in the target image data are labeled, a plurality of anchor frames can be used for labeling, the origin is set to establish a coordinate system, so that the coordinates corresponding to each key part in the human-shaped key parts are determined, and the coordinate data corresponding to each key part, namely the human-shaped key feature data, is recorded. The target object can be judged to be a person according to the human shape key characteristic data, and therefore early warning can be carried out according to the human shape key characteristic data.
According to the technical scheme, the human shape key characteristic data can be recognized in a mode of combining the infrared sensor with the preset recognition network model, so that the target object is determined to be a human, the error detection rate of human shape detection on static human shape portrait, animals and the like is reduced to a great extent, and the accuracy of human shape detection is improved.
In addition, the embodiment of the present disclosure further provides a monitoring and early warning method, including:
acquiring a human shape detection result, wherein the human shape detection result is obtained by the human shape detection method provided by the first aspect disclosed by the embodiment of the disclosure;
acquiring key characteristic data of the corresponding human shape according to the human shape detection result;
if the confidence coefficient of the human-shaped key characteristic data is greater than or equal to the confidence coefficient threshold value of the preset sensitivity, generating early warning information and giving an alarm;
and if the confidence coefficient of the human-shaped key feature data is smaller than the confidence coefficient threshold value, not giving an alarm.
According to the human shape detection result, if the confidence of the human shape key feature data is greater than or equal to the confidence threshold of the preset sensitivity, generating early warning information and giving an alarm, wherein the method can be understood as firstly utilizing a preset identification network model to identify initial image data, identifying the human shape key feature data, then outputting the confidence value of the human shape key feature data through the identification network model, comparing the confidence value corresponding to the human shape key feature data with the confidence threshold of the preset sensitivity, and if the confidence of the human shape key feature data is greater than or equal to the confidence threshold of the preset sensitivity, generating the early warning information and giving an alarm.
It should be noted that the warning may be sending the generated warning information to a preset mobile terminal device, an email box, or the like, and an alarm sound of an alarm signal may be sent through the shooting terminal in some scene settings.
Further, if the confidence of the human-shaped key feature data is smaller than the confidence threshold, no alarm is given.
According to the technical scheme of the embodiment of the disclosure, the alarm can be given in time when the preset condition is met according to the human shape detection result obtained by the human shape detection method, so that the accuracy of the accurate human shape detection, monitoring and early warning is improved.
In addition, the embodiment of the present disclosure further provides a human shape detection apparatus, which can implement the human shape detection method, and the apparatus includes:
the receiving module is used for receiving infrared monitoring information fed back by a preset infrared sensor, and the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
the acquisition module is used for acquiring initial image data of a preset area according to the monitoring condition that infrared monitoring information has infrared information with preset wavelength;
the identification module is used for identifying initial image data by using a preset identification network model and identifying human-shaped key characteristic data;
and the output module is used for outputting the human shape detection result according to the human shape key characteristic data.
According to the human shape detection device provided by the embodiment of the disclosure, by implementing the human shape detection method, the key characteristic data of the human shape can be identified in a mode of combining the infrared sensor and a preset identification network model, so that the target object is determined to be a human, the false alarm rate of human shape detection on static human shape images, animals and the like is reduced to a great extent, and the accuracy of correct monitoring and early warning is improved.
In addition, the embodiment of the present disclosure further provides a human shape detection system, which includes:
a human-shaped detection device;
shooting a terminal; the shooting terminal comprises an infrared sensor;
the human shape detection device performs:
a human form detection method as provided in the first aspect of the embodiments of the present disclosure.
In addition, the storage medium stores executable instructions, and the executable instructions can be executed by a computer, so that the computer executes the human form detection method provided by the first aspect of the invention and the monitoring and early warning method provided by the second aspect of the invention.
The memory, as a non-transitory storage medium, may be used to store non-transitory software programs as well as non-transitory computer-executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The embodiments described in the embodiments of the present disclosure are for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation to the technical solutions provided in the embodiments of the present disclosure, and it is obvious to those skilled in the art that the technical solutions provided in the embodiments of the present disclosure are also applicable to similar technical problems with the evolution of technology and the emergence of new application scenarios.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing programs, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The preferred embodiments of the present disclosure have been described above with reference to the accompanying drawings, and therefore do not limit the scope of the claims of the embodiments of the present disclosure. Any modifications, equivalents and improvements within the scope and spirit of the embodiments of the present disclosure should be considered within the scope of the claims of the embodiments of the present disclosure by those skilled in the art.
Claims (10)
1. A human shape detection method is characterized by being applied to a shooting terminal, and comprises the following steps:
receiving infrared monitoring information fed back by a preset infrared sensor, wherein the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
acquiring initial image data of the preset area according to the monitoring condition that the infrared monitoring information has infrared information with preset wavelength;
recognizing the initial image data by using a preset recognition network model, and recognizing human-shaped key feature data;
and outputting a human shape detection result according to the human shape key characteristic data.
2. The method for detecting human forms as claimed in claim 1, wherein before the receiving of the infrared monitoring information fed back by the infrared sensor, the infrared monitoring information is obtained by monitoring a predetermined area by a predetermined infrared sensor, the method further comprises:
receiving a human-shaped detection mode starting instruction;
entering a preset humanoid detection mode according to the humanoid detection mode starting instruction;
and according to the human-shaped detection mode, starting the infrared sensor to monitor the preset area.
3. The human form detection method of claim 2, wherein the infrared monitoring information comprises at least one of: target monitoring information, receive the infrared monitoring information of predetermineeing the infrared ray sensor feedback, infrared monitoring information by the infrared ray sensor monitoring is predetermine the region and is obtained, includes:
acquiring a Fresnel lens arranged outside the infrared sensor;
and monitoring a target object in the preset area according to the Fresnel lens, and receiving the target monitoring information fed back by the Fresnel lens.
4. The human form detection method according to claim 3, wherein the acquiring initial image data of the preset area according to the monitoring condition that the infrared monitoring information has infrared information with a preset wavelength comprises:
preprocessing the received infrared monitoring information to obtain infrared information with preset wavelength, and focusing infrared rays to an infrared induction source of the infrared sensor through the Fresnel lens to enable the infrared induction source to detect a target object;
and acquiring the initial image data of the target object in the preset area according to the infrared information of the preset wavelength obtained by the infrared induction source.
5. The human form detection method of claim 4, wherein the obtaining of the initial image data of the target object in the preset area according to the infrared information of the preset wavelength obtained by the infrared sensing source comprises:
acquiring video data corresponding to the target object according to the infrared information with the preset wavelength sensed by the infrared sensing source;
performing decoding operation on the video data to obtain a coding frame of the video data;
and performing bitmap operation on the key frame in the coding frame according to a preset operation function to generate the initial image data.
6. The human form detection method according to any one of claims 1 to 5, wherein the recognizing the initial image data by using a preset recognition network model to recognize human form key feature data comprises:
identifying an application scene of the initial image data by using the identification network model;
identifying the initial image data according to the application scene through the identification network model to generate target image data;
and marking the key parts of the human shape in the target image data to generate the key characteristic data of the human shape.
7. A monitoring and early warning method is characterized by comprising the following steps:
obtaining a human shape detection result obtained by a human shape detection method according to any one of claims 1 to 6;
acquiring corresponding human shape key characteristic data according to the human shape detection result;
if the confidence coefficient of the human-shaped key characteristic data is greater than or equal to the confidence coefficient threshold value of the preset sensitivity, generating early warning information and giving an alarm;
and if the confidence coefficient of the human-shaped key feature data is smaller than the confidence coefficient threshold value, not giving an alarm.
8. A human form detection apparatus, characterized in that the apparatus comprises:
the receiving module is used for receiving infrared monitoring information fed back by a preset infrared sensor, and the infrared monitoring information is obtained by monitoring a preset area by the infrared sensor;
the acquisition module is used for acquiring initial image data of the preset area according to the monitoring condition that the infrared monitoring information has infrared information with preset wavelength;
the identification module is used for identifying the initial image data by utilizing a preset identification network model and identifying human shape key characteristic data;
and the output module is used for outputting a human shape detection result according to the human shape key characteristic data.
9. A human form detection system, the system comprising:
a human-shaped detection device;
the shooting terminal comprises an infrared sensor;
the human-shaped detection device performs:
a human form detection method as claimed in any one of claims 1 to 6.
10. A storage medium storing executable instructions executable by a computer to cause the computer to perform:
a human form detection method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111599336.0A CN114495395A (en) | 2021-12-24 | 2021-12-24 | Human shape detection method, monitoring and early warning method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111599336.0A CN114495395A (en) | 2021-12-24 | 2021-12-24 | Human shape detection method, monitoring and early warning method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114495395A true CN114495395A (en) | 2022-05-13 |
Family
ID=81496242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111599336.0A Pending CN114495395A (en) | 2021-12-24 | 2021-12-24 | Human shape detection method, monitoring and early warning method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114495395A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876969A (en) * | 2024-03-11 | 2024-04-12 | 贵州省公路建设养护集团有限公司 | Safety monitoring method and system for bridge construction |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000331252A (en) * | 1999-05-24 | 2000-11-30 | Secom Co Ltd | Composite type monitoring device |
| CN108734162A (en) * | 2018-04-12 | 2018-11-02 | 上海扩博智能技术有限公司 | Target identification method, system, equipment and storage medium in commodity image |
| CN108810622A (en) * | 2018-07-09 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Extracting method, device, computer-readable medium and the electronic equipment of video frame |
| CN108830145A (en) * | 2018-05-04 | 2018-11-16 | 深圳技术大学（筹） | A kind of demographic method and storage medium based on deep neural network |
| CN209911986U (en) * | 2019-04-09 | 2020-01-07 | 武汉领普科技有限公司 | Embedded real-time human shape detection control device |
| CN111429681A (en) * | 2020-04-30 | 2020-07-17 | 沈阳天眼智云信息科技有限公司 | Comprehensive perimeter security system with infrared thermal image verification and method |
-
2021
- 2021-12-24 CN CN202111599336.0A patent/CN114495395A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000331252A (en) * | 1999-05-24 | 2000-11-30 | Secom Co Ltd | Composite type monitoring device |
| CN108734162A (en) * | 2018-04-12 | 2018-11-02 | 上海扩博智能技术有限公司 | Target identification method, system, equipment and storage medium in commodity image |
| CN108830145A (en) * | 2018-05-04 | 2018-11-16 | 深圳技术大学（筹） | A kind of demographic method and storage medium based on deep neural network |
| CN108810622A (en) * | 2018-07-09 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Extracting method, device, computer-readable medium and the electronic equipment of video frame |
| CN209911986U (en) * | 2019-04-09 | 2020-01-07 | 武汉领普科技有限公司 | Embedded real-time human shape detection control device |
| CN111429681A (en) * | 2020-04-30 | 2020-07-17 | 沈阳天眼智云信息科技有限公司 | Comprehensive perimeter security system with infrared thermal image verification and method |
Non-Patent Citations (1)
| Title |
|---|
| 刘修文: "《物联网应用技术——智能家居》", 机械工业出版社, pages: 93 - 94 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876969A (en) * | 2024-03-11 | 2024-04-12 | 贵州省公路建设养护集团有限公司 | Safety monitoring method and system for bridge construction |
| CN117876969B (en) * | 2024-03-11 | 2024-06-04 | 贵州省公路建设养护集团有限公司 | Safety monitoring method and system for bridge construction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190278976A1 (en) | Security system with face recognition | |
| US11321575B2 (en) | Method, apparatus and system for liveness detection, electronic device, and storage medium | |
| US20170039455A1 (en) | Computer-vision based security system using a depth camera | |
| JP6134825B2 (en) | How to automatically determine the probability of image capture by the terminal using context data | |
| CN109327626B (en) | Image acquisition method and device, electronic equipment and computer readable storage medium | |
| CN109815787B (en) | Target identification method and device, storage medium and electronic equipment | |
| GB2343945A (en) | Photographing or recognising a face | |
| CN110647797B (en) | Visitor detection method and device | |
| KR101104656B1 (en) | Pet image detection system and method for controlling operation thereof | |
| KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
| KR20180086048A (en) | Camera and imgae processing method thereof | |
| CN108093170B (en) | User photographing method, device and equipment | |
| CN114495270A (en) | Real-time monitoring and early warning method, device and system and storage medium | |
| KR102233679B1 (en) | Apparatus and method for detecting invader and fire for energy storage system | |
| CN114495395A (en) | Human shape detection method, monitoring and early warning method, device and system | |
| JP5758165B2 (en) | Article detection device and stationary person detection device | |
| CN111917967A (en) | Door monitoring system and control method thereof | |
| WO2022044369A1 (en) | Machine learning device and image processing device | |
| US9684828B2 (en) | Electronic device and eye region detection method in electronic device | |
| TWI631480B (en) | Entry access system having facil recognition | |
| CN112132110A (en) | Method for intelligently judging human body posture and nursing equipment | |
| US10990859B2 (en) | Method and system to allow object detection in visual images by trainable classifiers utilizing a computer-readable storage medium and processing unit | |
| CN109982051B (en) | Monitoring camera shooting method with animal identification function, monitoring camera and storage medium | |
| US10154196B2 (en) | Adjusting length of living images | |
| US20190228532A1 (en) | Motion detection in digital images and a communication method of the results thereof |
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 |