A video monitoring system and method based on Internet of Things

Abstract

The present invention relates to the field of community video surveillance technology, and discloses a video surveillance system and method based on the Internet of Things, including a video surveillance module, a sensor data acquisition module, a data analysis module and a data early warning module, wherein the video surveillance module includes a video surveillance data identification unit, a video surveillance area overlap annotation unit and a fire image data identification unit, and the data analysis module includes a video identification storage unit and a comprehensive data analysis unit. After detecting a fight or a traffic accident, the system records the current detection time, reads the shooting time and the distance from the place where the fight or traffic accident occurred of all cameras that simultaneously shot the fight or traffic accident, retains a group of videos with the highest weight coefficient, and repeats the above steps at intervals until the fight or traffic accident is handled, and all videos are spliced ​​and stored, so that both parties in the accident can quickly find the accident video.

Description

Technical Field

[0001] The present invention relates to the technical field of community video monitoring, and in particular to a video monitoring system and method based on the Internet of Things. Background Art

[0002] The Internet of Things is an important part of the new generation of information technology and an important development stage in the information age. It uses communication technologies such as local networks or the Internet to connect sensors, controllers, machines, people and objects in new ways, forming a network that connects people and objects, objects and objects, and realizes informatization, remote management and control, and intelligence. The Internet of Things is an extension of the Internet. It includes the Internet and all its resources, and is compatible with all Internet applications, but all elements in the Internet of Things are personalized and privatized.

[0003] Video surveillance equipment based on the Internet of Things is an application of the Internet of Things technology, but the existing video surveillance equipment only has a single recording and recognition function. Moreover, when there are multiple surveillance cameras at the scene of the accident, searching for surveillance images one by one along the timeline will result in a lot of time being wasted in searching for surveillance images at the scene of the accident. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a video monitoring system and method based on the Internet of Things, which has the advantages of quickly finding the monitoring footage where an accident occurred, and solves the above-mentioned technical problems.

[0006] (II) Technical solution

[0007] To achieve the above object, the present invention provides the following technical solutions: a video monitoring system based on the Internet of Things, comprising a video monitoring module, a sensor data acquisition module, a data analysis module and a data early warning module;

[0008] The video surveillance module includes a video surveillance data recognition unit, a video surveillance area overlap marking unit and a fire image data recognition unit. The video surveillance data recognition unit is used to recognize residences, vehicles and pedestrians in each road section in the current video. The video surveillance area overlap marking unit is used to mark the area where the surveillance picture of the current camera overlaps with the other surveillance pictures. The fire image data recognition unit is used to identify whether a fire occurs in the current residence in combination with the video surveillance data recognition unit. If a fire is identified, the sensor data acquisition module is called, and if a fire is not identified, the sensor data acquisition module is not called;

[0009] The sensor data acquisition module includes an ambient temperature data acquisition unit and an ambient smoke data acquisition unit. The ambient temperature data acquisition unit is used to collect ambient temperature data, and the ambient smoke data acquisition unit is used to collect ambient smoke data. The sensor data acquisition module sends the collected ambient temperature data and ambient smoke data to the data analysis module.

[0010] The data analysis module includes a video identification storage unit and a comprehensive data analysis unit. The video identification storage unit stores fights or accidents in the community based on the video surveillance data recognition unit and the video surveillance area overlap labeling unit in the video surveillance module. The comprehensive data analysis unit determines whether a fire occurs based on the ambient temperature data and ambient smoke data collected by the fire image data recognition unit and the sensor data acquisition module. If a fire occurs, the data warning module is called, and if no fire occurs, the data warning module is not called;

[0011] The data early warning module issues early warnings to residents and properties after receiving data from the comprehensive data analysis unit.

[0012] As a preferred technical solution of the present invention, the specific steps of the video surveillance data identification unit are as follows:

[0013] Step A1, selecting a moving object in the current video image with a minimum rectangular frame, and obtaining a vertical height and a horizontal length of the minimum rectangular frame;

[0014] Step A2: Calculate the vertical height and horizontal length of the identified minimum rectangular frame to obtain a determination ratio, and identify the type of the moving object based on the determination ratio, wherein the types of the identified objects include vehicles and pedestrians.

[0015] As a preferred technical solution of the present invention, the expression for calculating the vertical height and horizontal length of the identified minimum rectangular frame in step A2 is as follows:

[0016]

[0017] in, Indicates the judgment ratio, Indicates the vertical height of the minimum rectangular box. Indicates the horizontal length of the minimum rectangular frame. When the target is judged to be a pedestrian, The identified target is judged to be a vehicle.

[0018] As a preferred technical solution of the present invention, the specific steps of fire recognition by the fire image data recognition unit are as follows:

[0019] Step B1, identifying the color change area identified in the video surveillance data identification unit;

[0020] Step B2: When the identified residential color is consistent with the stored fire color, it is determined that a fire has occurred and the sensor data acquisition module is called.

[0021] As a preferred technical solution of the present invention, the ambient temperature data collected by the ambient temperature data collection unit is expressed as follows:

[0022]

[0023] in, Indicates that the fire image data recognition unit recognizes the first The ambient temperature dataset of a building, Respectively represent Ambient temperature data of the first floor of the building, , No. Building No. Layer ambient temperature data, , No. Building No. Layer ambient temperature data.

[0024] As a preferred technical solution of the present invention, the environmental smoke data acquisition unit acquires environmental smoke data, wherein the environmental smoke data includes environmental carbon monoxide concentration and carbon dioxide concentration, and its specific expression is as follows:

[0025]

[0026] in, Indicates that the fire image data recognition unit recognizes the first Environmental smoke dataset for buildings, Respectively represent Carbon dioxide concentration on the first floor of the building, , No. Building No. The carbon dioxide concentration , No. Building No. The carbon dioxide concentration in the layer, Respectively represent Carbon monoxide concentration on the first floor of the building, , No. Building No. Carbon monoxide concentration, , No. Building No. Layer carbon monoxide concentration.

[0027] As a preferred technical solution of the present invention, the specific process of the video identification storage unit storing fights or accidents within the community is as follows:

[0028] Step C1, after detecting a fight or a traffic accident, record the current detection time;

[0029] Step C2, determine whether the road section is marked by other cameras in the overlapped marking unit of the video surveillance area, if not, store the complete video, if yes, execute step C3;

[0030] Step C3, reading the shooting time and distance from the fighting behavior or traffic accident location of all cameras that simultaneously captured the fighting behavior or traffic accident, and calculating the weight coefficient;

[0031] Step C4: retain the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored.

[0032] As a preferred technical solution of the present invention, the specific expression for calculating the weight coefficient in step C3 is as follows:

[0033]

[0034] in, Indicates The weight coefficient of the video captured by each camera, Indicates The current shooting time of each camera, Indicates The distance between each camera and the fight or traffic accident. Indicates The time when a camera first detects a fight or traffic accident. and represents the weight coefficient, and .

[0035] As a preferred technical solution of the present invention, the process of the comprehensive data analysis unit performing analysis is: judging the The maximum temperature of the building Whether it exceeds the safe temperature threshold, if so, determine the The highest CO2 concentration in the building or The highest carbon monoxide concentration in the building Whether it exceeds the corresponding safety concentration threshold. If at least one exceeds, it is judged that a fire has occurred.

[0036] The present invention also provides a video monitoring method based on the Internet of Things, based on the above-mentioned video monitoring system based on the Internet of Things, comprising the following steps:

[0037] Step 1: Identify pedestrians and vehicles through the video surveillance data recognition unit, and make a preliminary identification of the fire situation in the residence. If a fire occurs, execute step 4; if a fight or traffic accident occurs, execute step 2;

[0038] Step 2: After a fight or traffic accident is detected, the current detection time is recorded, the shooting time and the distance from the place where the fight or traffic accident occurred of all cameras that simultaneously captured the fight or traffic accident are read, and the weight coefficient is calculated;

[0039] Step 3: Keep the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored;

[0040] Step 4: Determine Whether the highest temperature of the building exceeds the safety threshold, if not, no fire warning will be issued, if exceeded, the highest carbon dioxide concentration or the Whether the highest carbon monoxide concentration in the building exceeds the corresponding safety concentration threshold, if exceeded, a fire warning will be issued.

[0041] Compared with the prior art, the present invention provides a video monitoring system and method based on the Internet of Things, which has the following beneficial effects:

[0042] 1. After detecting a fight or a traffic accident, the present invention records the current detection time, reads the shooting time and the distance from the place where the fight or the traffic accident occurred of all cameras that simultaneously shot the fight or the traffic accident, and calculates the weight coefficient to retain the group of videos with the highest weight coefficient, and every time interval Repeat the above steps until the fight or traffic accident is handled, and all the videos are spliced ​​and stored, so that both parties involved in the accident can quickly find the accident video.

[0043] 2. The present invention reads the first Building judgment Whether the highest temperature of the building exceeds the safety threshold, if not, no fire warning will be issued, if exceeded, the highest carbon dioxide concentration or the Whether the highest carbon monoxide concentration in the building exceeds the corresponding safety concentration threshold, if exceeded, a fire warning will be issued. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the system framework of the present invention;

[0045] Figure 2 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1-Figure 2 , a video monitoring system based on the Internet of Things, including a video monitoring module, a sensor data acquisition module, a data analysis module and a data early warning module;

[0048] The video surveillance module includes a video surveillance data recognition unit, a video surveillance area overlap labeling unit and a fire image data recognition unit. The video surveillance data recognition unit is used to identify residences, vehicles and pedestrians on each road section in the current video. The specific steps of the video surveillance data recognition unit are as follows:

[0049] Step A1, selecting a moving object in the current video image with a minimum rectangular frame, and obtaining a vertical height and a horizontal length of the minimum rectangular frame;

[0050] Step A2: Calculate the vertical height and horizontal length of the smallest rectangular frame identified to obtain the determination ratio. , and identify the types of moving objects based on the determination ratio, where the types of identified objects include vehicles and pedestrians.

[0051] in, Indicates the judgment ratio, Indicates the vertical height of the minimum rectangular box. Indicates the horizontal length of the minimum rectangular frame. When the target is judged to be a pedestrian, When the target is identified as a vehicle;

[0052] The video surveillance area overlap marking unit is used to mark the area where the surveillance screen of the current camera overlaps with the other surveillance screens. The marking of this area is completed when the surveillance equipment is initially installed. The fire image data recognition unit is used to identify whether a fire has occurred in the current residence in combination with the video surveillance data recognition unit. If a fire is identified, the sensor data acquisition module is called. If a fire is not identified, the sensor data acquisition module is not called. The specific steps are as follows:

[0053] Step B1, identifying the color change area identified in the video surveillance data identification unit;

[0054] Step B2: When the recognized residential color is consistent with the stored fire color, it is determined that a fire has occurred and the sensor data acquisition module is called, where image recognition is used to determine whether the residential area is on fire. After the initial recognition is completed, the subsequent module can be called for further recognition, thereby ensuring the diversity of recognition methods and the accuracy of recognition;

[0055] The sensor data acquisition module includes an ambient temperature data acquisition unit and an ambient smoke data acquisition unit. The ambient temperature data acquisition unit is used to collect ambient temperature data. The environmental smoke data collection unit is used to collect environmental smoke data. The environmental smoke data collection unit collects environmental smoke data, wherein the environmental smoke data includes environmental carbon monoxide concentration and carbon dioxide concentration: The sensor data acquisition module sends the collected ambient temperature data and ambient smoke data to the data analysis module, where Indicates that the fire image data recognition unit recognizes the first The ambient temperature dataset of a building, Respectively represent Ambient temperature data of the first floor of the building, , No. Building No. Layer ambient temperature data, , No. Building No. Layer ambient temperature data, Indicates that the fire image data recognition unit recognizes the first Environmental smoke dataset for buildings, Respectively represent Carbon dioxide concentration on the first floor of the building, , No. Building No. The carbon dioxide concentration , No. Building No. The carbon dioxide concentration in the layer, Respectively represent Carbon monoxide concentration on the first floor of the building, , No. Building No. Carbon monoxide concentration, , No. Building No. Layer carbon monoxide concentration.

[0056] The data analysis module includes a video identification storage unit and a comprehensive data analysis unit. The video identification storage unit stores fights or accidents in the community based on the video surveillance data recognition unit and the video surveillance area overlap labeling unit in the video surveillance module. The specific process of the video identification storage unit storing fights or accidents in the community is as follows:

[0057] Step C1, after detecting a fight or a traffic accident, record the current detection time;

[0058] Step C2, determine whether the road section is marked by other cameras in the overlapped marking unit of the video surveillance area, if not, store the complete video, if yes, execute step C3;

[0059] Step C3: read the shooting time and distance from the fighting behavior or traffic accident location of all cameras that simultaneously captured the fighting behavior or traffic accident.

[0060] And calculate the weight coefficient ;

[0061] Step C4: retain the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored.

[0062] in, Indicates The weight coefficient of the video captured by each camera, Indicates The current shooting time of each camera, Indicates The distance between each camera and the fight or traffic accident. Indicates The time when a camera first detects a fight or traffic accident. and represents the weight coefficient, and ;

[0063] The comprehensive data analysis unit determines whether a fire occurs based on the ambient temperature data and ambient smoke data collected by the fire image data recognition unit and the sensor data acquisition module. If a fire occurs, the data warning module is called, and if no fire occurs, the data warning module is not called;

[0064] The data early warning module issues early warnings to residents and properties after receiving data from the comprehensive data analysis unit.

[0065] The present invention also provides a video monitoring method based on the Internet of Things, based on the above-mentioned video monitoring system based on the Internet of Things, comprising the following steps:

[0066] Step 1: Identify pedestrians and vehicles through the video surveillance data recognition unit, and make a preliminary identification of the fire situation in the residence. If a fire occurs, execute step 4; if a fight or traffic accident occurs, execute step 2;

[0067] Step 2: After a fight or traffic accident is detected, the current detection time is recorded, the shooting time and the distance from the place where the fight or traffic accident occurred of all cameras that simultaneously captured the fight or traffic accident are read, and the weight coefficient is calculated;

[0068] Step 3: Keep the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored;

[0069] Step 4: Determine Whether the highest temperature of the building exceeds the safety threshold, if not, no fire warning will be issued, if exceeded, the highest carbon dioxide concentration or the Whether the highest carbon monoxide concentration in the building exceeds the corresponding safety concentration threshold, if exceeded, a fire warning will be issued.

[0070] Embodiment 1:

[0071] The color change area identified in the video surveillance data recognition unit is identified, and the fire color consistent with the standard database in the 15th to 17th layers is identified, accompanied by thick smoke, and the sensor data acquisition module is called at this time;

[0072] At this time, the carbon monoxide concentration and carbon dioxide concentration collected by the sensor data acquisition module during the fire identification process and the temperature of each floor are shown in Table 1 below:

[0073] Table 1

[0074]

[0075] The maximum temperature at this time and the highest CO2 concentration , No. The highest carbon monoxide concentration in the building , all exceed the safe value, so it can be judged that a fire has occurred and an early warning is issued;

[0076] Embodiment 2:

[0077] When a fight occurs, the monitoring equipment automatically detects the fight (how to detect the fight is a prior art and will not be elaborated on here). There are three cameras at the location where the fight occurs, and the distances from the location of the accident are 30m, 10m, and 5m respectively. Camera 1 is in the first time interval. , at this time the weight coefficient , and the recognition time of camera 2 in the first time interval is , weight coefficient , and the recognition time of camera 3 in the first time interval is , at this time the weight coefficient , in the first time interval, the picture of camera 3 is selected as the main picture, and so on. When the weight coefficient of camera 2 in the second time interval is higher than the other two, camera 2 is selected as the main picture, and the picture of the second time interval is spliced ​​with the picture of the first time interval, and so on. Finally, the accident video is stored separately for easy retrieval. After all three parties in the accident have copied the original video, the content is cleaned up regularly;

[0078] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A video surveillance system based on the Internet of Things, characterized in that: It includes video monitoring module, sensor data acquisition module, data analysis module and data early warning module; The video surveillance module includes a video surveillance data recognition unit, a video surveillance area overlap marking unit and a fire image data recognition unit. The video surveillance data recognition unit is used to recognize residences, vehicles and pedestrians in each road section in the current video. The video surveillance area overlap marking unit is used to mark the area where the surveillance picture of the current camera overlaps with the other surveillance pictures. The fire image data recognition unit is used to identify whether a fire occurs in the current residence in combination with the video surveillance data recognition unit. If a fire is identified, the sensor data acquisition module is called, and if a fire is not identified, the sensor data acquisition module is not called; The sensor data acquisition module includes an ambient temperature data acquisition unit and an ambient smoke data acquisition unit. The ambient temperature data acquisition unit is used to acquire ambient temperature data, and the ambient smoke data acquisition unit is used to acquire ambient smoke data. The sensor data acquisition module sends the acquired ambient temperature data and ambient smoke data to the data analysis module. The data analysis module includes a video identification storage unit and a comprehensive data analysis unit. The video identification storage unit stores fights or accidents in the community based on the video surveillance data identification unit and the video surveillance area overlap labeling unit in the video surveillance module. The comprehensive data analysis unit determines whether a fire occurs based on the ambient temperature data and ambient smoke data collected by the fire image data identification unit and the sensor data acquisition module. If a fire occurs, the data warning module is called, and if no fire occurs, the data warning module is not called; The specific process of the video identification storage unit storing fights or incidents within the community is as follows: Step C1, after detecting a fight or a traffic accident, record the current detection time; Step C2, determine whether the road section is marked by other cameras in the overlapped marking unit of the video surveillance area, if not, store the complete video, if yes, execute step C3; Step C3, reading the shooting time and distance from the fighting behavior or traffic accident site of all cameras that simultaneously captured the fighting behavior or traffic accident, and calculating the weight coefficient. The specific expression for calculating the weight coefficient in step C3 is as follows: ； in, Indicates The weight coefficient of the video captured by each camera, Indicates The current shooting time of each camera, Indicates The distance between each camera and the fight or traffic accident. Indicates The time when a camera first detects a fight or traffic accident. and represents the weight coefficient, and ; Step C4: retain the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored; The data early warning module issues early warnings to residents and properties after receiving data from the comprehensive data analysis unit.

2. The video surveillance system based on the Internet of Things according to claim 1, characterized in that: The specific steps of the video surveillance data identification unit are as follows: Step A1, selecting a moving object in the current video image with a minimum rectangular frame, and obtaining a vertical height and a horizontal length of the minimum rectangular frame; Step A2: Calculate the vertical height and horizontal length of the identified minimum rectangular frame to obtain a determination ratio, and identify the type of the moving object based on the determination ratio, wherein the types of the identified objects include vehicles and pedestrians.

3. The video surveillance system based on the Internet of Things according to claim 2 is characterized in that: The expressions for calculating the vertical height and horizontal length of the identified minimum rectangular frame in step A2 are as follows: ； in, Indicates the judgment ratio, Indicates the vertical height of the minimum rectangular box. Indicates the horizontal length of the minimum rectangular frame. When the target is judged to be a pedestrian, The identified target is judged to be a vehicle.

4. The video surveillance system based on the Internet of Things according to claim 1, characterized in that: The specific steps of fire recognition by the fire image data recognition unit are as follows: Step B1, identifying the color change area identified in the video surveillance data identification unit; Step B2: When the identified residential color is consistent with the stored fire color, it is determined that a fire has occurred and the sensor data acquisition module is called.

5. The video surveillance system based on the Internet of Things according to claim 1, characterized in that: The ambient temperature data collected by the ambient temperature data collection unit is expressed as follows: ； in, Indicates that the fire image data recognition unit recognizes the first The ambient temperature dataset of a building, Respectively represent Ambient temperature data of the first floor of the building, , No. Building No. Layer ambient temperature data, , No. Building No. Layer ambient temperature data.

6. The video surveillance system based on the Internet of Things according to claim 1, characterized in that: The environmental smoke data collection unit collects environmental smoke data, wherein the environmental smoke data includes carbon monoxide concentration and carbon dioxide concentration, and its specific expression is as follows: ； in, Indicates that the fire image data recognition unit recognizes the first Environmental smoke dataset for buildings, Respectively represent Carbon dioxide concentration on the first floor of the building, , No. Building No. The carbon dioxide concentration , No. Building No. The carbon dioxide concentration in the layer, Respectively represent Carbon monoxide concentration on the first floor of the building, , No. Building No. Carbon monoxide concentration, , No. Building No. Layer carbon monoxide concentration.

7. The video surveillance system based on the Internet of Things according to claim 6, characterized in that: The process of the comprehensive data analysis unit performing the analysis is as follows: The maximum temperature of the building Whether it exceeds the safe temperature threshold, if so, determine the The highest CO2 concentration in the building or The highest carbon monoxide concentration in the building Whether it exceeds the corresponding safety concentration threshold. If at least one exceeds, it is judged that a fire has occurred.

8. A video monitoring method based on the Internet of Things, applied to the video monitoring system based on the Internet of Things according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Identify pedestrians and vehicles through the video surveillance data recognition unit, and make a preliminary identification of the fire situation in the residence. If a fire occurs, execute step 4; if a fight or traffic accident occurs, execute step 2; Step 2: After a fight or traffic accident is detected, the current detection time is recorded, the shooting time and the distance from the place where the fight or traffic accident occurred of all cameras that simultaneously captured the fight or traffic accident are read, and the weight coefficient is calculated; Step 3: Keep the group of videos with the highest weight coefficient and Repeat the above steps until the fight or traffic accident is handled and all the videos are spliced ​​and stored; Step 4: Determine Whether the highest temperature of the building exceeds the safety threshold, if not, no fire warning will be issued, if exceeded, the highest carbon dioxide concentration or the Whether the highest carbon monoxide concentration in the building exceeds the corresponding safety concentration threshold, if exceeded, a fire warning will be issued.

Images