CN117315594B - Intelligent security video monitoring system based on Internet of things - Google Patents
Intelligent security video monitoring system based on Internet of things Download PDFInfo
- Publication number
- CN117315594B CN117315594B CN202311595300.4A CN202311595300A CN117315594B CN 117315594 B CN117315594 B CN 117315594B CN 202311595300 A CN202311595300 A CN 202311595300A CN 117315594 B CN117315594 B CN 117315594B
- Authority
- CN
- China
- Prior art keywords
- dog
- wandering
- dogs
- driving
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 241000282472 Canis lupus familiaris Species 0.000 claims abstract description 210
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 12
- 241001465754 Metazoa Species 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012876 topography Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 12
- 230000006872 improvement Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M29/00—Scaring or repelling devices, e.g. bird-scaring apparatus
- A01M29/16—Scaring or repelling devices, e.g. bird-scaring apparatus using sound waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Environmental Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Wood Science & Technology (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Birds (AREA)
- Insects & Arthropods (AREA)
- Pest Control & Pesticides (AREA)
- General Health & Medical Sciences (AREA)
- Zoology (AREA)
- Computational Linguistics (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of video monitoring. The invention relates to an intelligent security video monitoring system based on the Internet of things. The method comprises a non-recognition target building unit, a wandering dog finding unit, a wandering dog driving unit and a driving monitoring unit; the unidentified target establishing unit is used for acquiring a video picture of a security camera in a cell through the Internet of things, extracting the position of a cell signboard in the video picture, and listing dogs and figures appearing on the surface of the signboard as unidentified targets; the method comprises the steps of extracting the positions of the signs through the non-recognition target building unit, determining the dog images and the figures on the surfaces of the signs as non-recognition targets, avoiding recognition errors when driving the wandering dogs, recognizing the wandering dogs in the district through the wandering dog discovery unit, the wandering dog driving unit and the driving monitoring unit, and making corresponding driving routes to drive the wandering dogs out of the district.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to an intelligent security video monitoring system based on the Internet of things.
Background
Because the wandering dog can appear hurting personnel, in order to prevent getting into the wandering dog in the district, the mode that present district security protection adopted is equipment and personnel's combination generally, adopt supervisory equipment such as camera and cooperation security personnel's untimely patrol, thereby ensure district resident's safety, and establish wandering dog sign, remind district owner, but the wandering dog can appear the action of evading when hearing the people sound, lead to security personnel unable in time to discover the position of wandering dog when patrol, if direct discernment wandering dog just drives, the dog image on sign surface can mislead the recognition accuracy of equipment, and the dog that has the dog to be the owner raised can appear wrong drive, thereby make security protection equipment can not the furthest play a role, in order to reduce this kind of circumstances, in view this, an intelligent security protection video monitoring system based on thing networking is provided.
Disclosure of Invention
The invention aims to provide an intelligent security video monitoring system based on the Internet of things, which aims to solve the problems in the background technology.
In order to achieve the above purpose, the intelligent security video monitoring system based on the Internet of things comprises an unidentified target building unit, a wandering dog finding unit, a wandering dog driving unit and a driving monitoring unit;
the unidentified target building unit is used for collecting video pictures of the security cameras in the cells through the Internet of things, extracting the positions of the cell identification plates in the video pictures, and listing dogs and figures appearing on the surfaces of the identification plates as unidentified targets;
the wandering dog finding unit is used for capturing the face in the video picture acquired by the unidentified target establishing unit, performing biological recognition on the captured target, if the captured target is a dog, displaying the dynamic target as a wandering dog according to the recognition result, and meanwhile, judging the dog as a wandering dog if other dynamic targets are not present at the periphery, and sending the position of the security and protection camera for finding the wandering dog to the wandering dog driving unit;
the wandering dog driving unit is used for receiving the position of the camera sent by the wandering dog finding unit, simultaneously carrying out driving path analysis on the wandering dogs by combining with the topography of the district, obtaining driving paths aiming at the wandering dogs, and controlling the security cameras in the driving paths to send out sound to drive the wandering dogs;
the driving monitoring unit is used for setting a safe distance threshold value, simultaneously monitoring the driven wandering dogs in real time, capturing other targets in the safe distance threshold value of the wandering dogs, detecting ropes between the dogs and the portraits when other target identification results are portraits, judging the portraits to be the owners of the dogs if the dogs and the portraits are detected to be in rope connection, and stopping controlling the security camera to drive.
As a further improvement of the technical scheme, the unidentified target building unit builds regional network connection through the Internet of things equipment and the security cameras at different positions in the cell, so that video pictures and the security cameras are transmitted and controlled through the Internet of things.
As a further improvement of the technical scheme, the unidentified target establishing unit comprises a signboard marking module;
the signboard marking module is used for positioning the signboard on the acquired video image, extracting images of dogs and figures appearing on the surface of the signboard, and sending the extracted dogs and figures to the security camera capable of shooting the signboard as a static landform in combination with the signboard image, so that the security camera takes the received images as a target which is not recognized and captured.
As a further improvement of the technical scheme, the wandering dog discovery unit comprises the step of adopting an artificial intelligence technology to analyze the monitoring video in real time and automatically detect face recognition and animal recognition.
As a further improvement of the technical scheme, the wandering dog discovery unit comprises a wandering dog identification module;
the wandering dog identification module is used for capturing faces in video pictures, performing biological identification on the captured targets, if the captured targets are identified, displaying the dynamic targets as dogs, meanwhile, judging that the dogs are wandering dogs, and sending the positions of the security cameras for the wandering dogs to the wandering dog driving unit, otherwise, if the identification results are identified, displaying the dynamic targets as dogs, meanwhile, identifying the other dynamic targets as figures, and judging that the dogs are not wandering dogs.
As a further improvement of the technical scheme, the wandering dog driving unit comprises a position receiving module and a driving path analysis module;
the position receiving module is used for collecting a district topographic map and receiving the position information of the security camera sent by the rough handling dog identification module;
the driving path analysis module is used for positioning the position of the security camera and the position of the video picture in the district topographic map in combination with the position of the wandering dog, then carrying out path analysis on the position of the wandering dog, which is separated from the district, obtaining the driving path for the wandering dog, and controlling the security camera in the driving path to make sound to drive the wandering dog.
As a further improvement of the technical scheme, the driving path analysis module is used for installing a loudspeaker on the surface of the security camera, connecting the loudspeaker with the Internet of things equipment, searching a sound file for driving dogs in a network by the Internet of things equipment, sending the sound file to the loudspeaker, and sending the sound file by the loudspeaker.
As a further improvement of the technical scheme, the driving monitoring unit sets a questionnaire by sending a safe distance threshold to the community property, and takes the distance value filled in according to the community property as the safe distance threshold.
As a further improvement of the technical scheme, the driving monitoring unit comprises the driving monitoring module;
the driving monitoring module is used for monitoring the driven wander dog in real time, when other targets are captured in the safe distance threshold value of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, if rope connection is carried out between the dog and the figures, the figures are judged to be the owner of the dog, the control of the security camera is stopped, driving is carried out, otherwise, when other targets are captured in the safe distance threshold value of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, and if rope connection is not carried out between the dog and the figures, the security camera is controlled continuously to drive until the wander dog is driven out of the community.
Compared with the prior art, the invention has the beneficial effects that:
this an intelligent security video monitored control system based on thing networking draws the sign position through not discernment target establishment unit, with the dog image and the portrait on sign surface for not discernment target, avoid appearing discernment mistake when driving the unrestrained dog, through the unrestrained dog discovery unit, the unrestrained dog is driven the unit and is driven monitoring unit and discerned the unrestrained dog in the district, and formulate the route of driving that corresponds, drive the unrestrained dog out the district, drive the monitoring to the unrestrained dog simultaneously, and can remind industry owner to tie the dog rope, avoid the dog not to tie the rope and lead to appearing hurting people incident.
Drawings
Fig. 1 is a schematic diagram of the overall structure of the present invention.
The meaning of each reference sign in the figure is:
10. not identifying the target establishing unit; 20. a wandering dog finding unit; 30. a wandering dog expelling unit; 40. and driving the monitoring unit.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an objective of the present embodiment is to provide an intelligent security video monitoring system based on the internet of things, which includes an unidentified target establishing unit 10, a wandering dog finding unit 20, a wandering dog driving unit 30, and a driving monitoring unit 40;
the unidentified target establishing unit 10 is used for acquiring a video picture of a security camera in a cell through the internet of things, extracting the position of a cell signboard in the video picture, and listing dogs and figures appearing on the surface of the signboard as unidentified targets;
the unidentified target establishing unit 10 establishes regional network connection through the internet of things equipment and security cameras at different positions in the cell, so that video pictures and the security cameras are transmitted and controlled through the internet of things. The method comprises the following steps:
designing an Internet of things architecture: determining the layout of equipment and the position of a camera, and selecting a proper communication protocol such as WiFi, bluetooth, zigbee and the like;
connecting the Internet of things equipment: connecting the security camera to the Internet of things network, and enabling the security camera to be connected with the Internet of things network through wireless connection such as Ethernet;
configuring network settings: each camera is allocated with a unique IP address, a subnet mask and a gateway are set, and normal communication of the equipment is ensured;
video transmission is realized: and transmitting the shooting video of the camera to a designated receiving end through the Internet of things network. Real-time video transport may be implemented using streaming media transport protocols such as RTSP;
realize remote control: parameters and functions of the camera are remotely controlled through the Internet of things network, such as focal length adjustment, brightness adjustment, contrast adjustment and the like.
The unidentified target setting unit 10 includes a signboard marking module;
the signboard marking module is used for positioning the signboard on the acquired video image, extracting images of dogs and human images appearing on the surface of the signboard, and sending the extracted dogs and human images to the security camera capable of shooting the signboard to serve as a static landform in combination with the signboard images, so that the security camera can take the received images as a non-recognition and non-capture target. The method comprises the following steps:
target detection and positioning: performing target detection on the acquired video frames by using a computer vision algorithm, and identifying the position and the area of the signboard;
image segmentation and extraction: and dividing the signboard area by using an image processing algorithm, and extracting the dog and the portrait on the signboard. Extraction of dogs and figures may be achieved using image segmentation algorithms such as color, texture or deep learning based algorithms;
combining the image and sending to the security camera: synthesizing the extracted dog and portrait with the signboard images, and sending the synthesized images to a security camera capable of shooting the signboard;
setting security camera parameters: at the security camera head end, parameters of the security camera are set according to the received composite image, so that the security camera does not recognize and capture dogs and figures on the signboard.
The wandering dog finding unit 20 is configured to capture a face in the video frame acquired by the unidentified target establishing unit 10, perform biological recognition on the captured target, and if the captured target is a dog, the recognition result shows that the dynamic target is a dog, and meanwhile, no other dynamic targets are present in the periphery, that is, the dog is determined to be a wandering dog, and send the position of the security camera for finding the wandering dog to the wandering dog driving unit 30;
the wandering dog finding unit 20 performs real-time analysis on the monitoring video by adopting artificial intelligence technology, and automatically detects face recognition and animal recognition. The method comprises the following steps:
and (3) video acquisition: a camera or other monitoring equipment is used for collecting monitoring videos, and the videos are transmitted to an artificial intelligent system for processing;
video preprocessing: preprocessing the acquired video, including video decoding, inter-frame difference, denoising and other processing, so as to provide clearer and reliable video frames for subsequent analysis;
face recognition: and processing the video frame by using a face detection algorithm to detect the face appearing in the video. Then using a face recognition algorithm to recognize and match the detected face so as to determine the identity of the face;
and (3) animal identification: the video frames are processed, likewise using an object detection algorithm or a specific animal identification algorithm, to detect the animals present in the video. Deep learning models such as convolutional neural network CNN or recurrent neural network RNN, etc. may be used.
The wander finding unit 20 includes a wander identification module;
the wandering dog recognition module is used for capturing the face in the video picture, performing biological recognition on the captured target, if the captured target is the dog, displaying the dynamic target as the dog according to the recognition result, meanwhile, judging that the dog is a wandering dog, and sending the position of the security and protection camera for the wandering dog to the wandering dog driving unit 30, otherwise, if the captured target is the dog, displaying the dynamic target as the dog according to the recognition result, meanwhile, displaying other dynamic targets as the dog according to the periphery, and recognizing other dynamic targets as the human image, namely, judging that the dog is not the wandering dog. The method comprises the following steps:
facial capture: processing the video frame by using a face detection algorithm, detecting the face appearing in the video, and capturing the position of the face;
biological recognition: extracting biological characteristics of the captured facial image, and identifying by using a face identification algorithm to judge an individual to whom the face belongs;
judging a wandering dog: judging whether the identification result is a dog, if so, judging whether other dynamic targets exist around the dog;
transmitting position information: if the moving dog is judged to be without other dynamic targets around, the position information of the security camera is sent to the moving dog driving unit 30;
updating judgment: if the identification result is a dog, but other dynamic targets are arranged around the dog, and the other dynamic targets are identified as figures, the dog is judged not to be a wandering dog.
The wandering dog driving unit 30 is configured to receive the position of the camera sent by the wandering dog discovery unit 20, and perform driving path analysis on the wandering dogs in combination with the topography of the cell, obtain driving paths for the wandering dogs, and control the security cameras in the driving paths to send out sound to drive the wandering dogs;
the wandering dog expelling unit 30 includes a position receiving module and an expelling path analyzing module;
the position receiving module is used for collecting a district topographic map and receiving the position information of the security camera sent by the rough wave dog identification module at the same time: the method comprises the following steps:
cell topography acquisition and establishment: collecting a topographic map of a cell by using a map making tool or a mapping instrument, and establishing a corresponding topographic map database;
receiving security camera position information: receiving position information of a security camera sent by a wandering dog identification module and correlating the position information with a corresponding video picture;
the driving path analysis module is used for positioning the position of the security camera and the position of the video picture in the district topographic map in combination with the position of the wandering dog, then carrying out path analysis aiming at driving the wandering dog to leave the district, obtaining the driving path aiming at the wandering dog, and controlling the security camera in the driving path to send out sound to drive the wandering dog. The method comprises the following steps:
positioning the wandering dogs: positioning the current wave dog on the district topographic map by utilizing the topographic map information and the security camera position information, and determining the current position of the current wave dog;
path analysis: using a path planning algorithm, an optimal path from the current location of the puppy to the designated exit or specific area is calculated. A graph search algorithm Dijkstra algorithm may be used;
security camera control: and controlling the security cameras positioned on the driving paths according to the path analysis result, and making sound at proper time and position to drive the wandering dogs.
The driving path analysis module is used for installing a loudspeaker on the surface of the security camera, connecting the loudspeaker with the Internet of things equipment, searching a dog driving sound file in a network by the Internet of things equipment, sending the sound file to the loudspeaker, and sending the sound file by the loudspeaker. The method comprises the following steps:
and (3) installing a loudspeaker: a speaker device is installed at a proper position of the security camera and is connected to the Internet of things device;
the equipment of the Internet of things is connected with: and connecting the Internet of things equipment with a loudspeaker and a network. The Internet of things equipment, the loudspeaker and the network can be connected in a WiFi (wireless fidelity) mode, an Ethernet mode and the like;
sound file preparation: and preparing a dog expelling sound file in the Internet of things equipment. A suitable sound file may be selected from a sound library or a corresponding sound file may be generated using a speech synthesis technique;
positioning and searching the Internet of things equipment: positioning and searching in the Internet of things equipment through network connection to find a dog-driving sound file to be played;
transmitting a sound file: sending the selected sound file to the Internet of things equipment connected with the loudspeaker;
and (3) playing by a loudspeaker: and controlling a loudspeaker to start playing the sound file for driving the dog by the Internet of things equipment so as to drive the wandering dog.
The driving monitoring unit 40 is configured to set a safe distance threshold, monitor the driven wandering dog in real time, capture other targets within the safe distance threshold of the wandering dog, and detect the rope between the dog and the portrait if the rope is connected between the dog and the portrait, and determine the portrait as the owner of the dog if the rope is detected, and stop controlling the security camera to drive.
The driving monitoring unit 40 sets a questionnaire by transmitting a safe distance threshold value to the cell property, and uses the distance value filled in by the cell property as a safe distance threshold value. The method comprises the following steps:
preparing a questionnaire: designing a questionnaire comprising question description, options, filling modes and the like, and inquiring the setting of the district property about the safety distance threshold;
sending a questionnaire: the questionnaires are sent to the community property by means of e-mails, instant messaging tools and the like, and the filling purpose and importance are described;
property filling: the property receives the questionnaire and fills in, fills in proper safe distance values according to specific conditions, and submits replies;
threshold setting: and setting the distance value as a safe distance threshold according to the distance value filled in by the community property.
The driving monitoring module is used for monitoring the driven wander dog in real time, when other targets are captured in the safe distance threshold of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, if rope connection is carried out between the dog and the figures, the figures are judged to be the dog owners, the control of the security camera is stopped, driving is carried out, otherwise, when other targets are captured in the safe distance threshold of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, and if rope connection is not carried out between the dog and the figures, the security camera is controlled continuously to drive until the wander dog is driven out of the community. The formula is as follows:
judging a safety distance threshold value: if the distance between the target and the wandering dog is smaller than the safe distance threshold, the winding identification is carried out on the target, and the expression is as follows:
wherein distance is a Euclidean distance function of the calculated distance;
rope detection: the presence or absence of a rope connection between the dog and the portrait can be detected using image processing and computer vision techniques as follows:
if it is>And if the rope connection exists, judging that the dog owner is the dog owner, otherwise, continuing to drive the wandering dog.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. Intelligent security video monitored control system based on thing networking, its characterized in that: comprises an unidentified target establishing unit (10), a wandering dog finding unit (20), a wandering dog driving unit (30) and a driving monitoring unit (40);
the unidentified target building unit (10) is used for collecting video pictures of security cameras in the cells through the Internet of things, extracting the positions of the cell identification plates in the video pictures, and listing dogs and figures appearing on the surfaces of the identification plates as unidentified targets;
the wandering dog finding unit (20) is used for capturing the face in the video picture acquired by the unidentified target establishing unit (10), performing biological recognition on the captured target, displaying the dynamic target as a dog if the identification result shows that the dog is a wandering dog, judging that the dog is a wandering dog if the periphery has no other dynamic targets, and sending the position of the security and protection camera for finding the wandering dog to the wandering dog driving unit (30);
the wandering dog driving unit (30) is used for receiving the position of the camera sent by the wandering dog finding unit (20), simultaneously carrying out driving path analysis on the wandering dogs by combining with the topography of the district, obtaining driving paths aiming at the wandering dogs, and controlling the security cameras in the driving paths to send out sound to drive the wandering dogs;
the driving monitoring unit (40) is used for setting a safe distance threshold value, simultaneously monitoring the driven wandering dogs in real time, capturing other targets within the safe distance threshold value of the wandering dogs, detecting ropes between the dogs and the portraits simultaneously when other target identification results are portraits, judging the portraits as the owners of the dogs if the dogs and the portraits are detected to have rope connection, and stopping controlling the security cameras to drive;
the wandering dog driving unit (30) comprises a position receiving module and a driving path analysis module;
the position receiving module is used for collecting a district topographic map and receiving the position information of the security camera sent by the rough handling dog identification module;
the driving path analysis module is used for positioning the position of the security camera and the position of the video picture in the topographic map of the district in combination with the position of the wandering dog, then carrying out path analysis on the situation that the wandering dog is driven to leave the inside of the district, obtaining the driving path for the wandering dog, and controlling the security camera in the driving path to send out sound to drive the wandering dog;
the driving path analysis module is used for installing a loudspeaker on the surface of the security camera, connecting the loudspeaker with the Internet of things equipment, searching a dog driving sound file in a network by the Internet of things equipment, sending the sound file to the loudspeaker, and sending the sound file by the loudspeaker;
the driving monitoring unit (40) sets a questionnaire by sending a safe distance threshold value to the community property, and takes the distance value filled in by the community property as a safe distance threshold value;
the driving monitoring unit (40) comprises a driving monitoring module;
the driving monitoring module is used for monitoring the driven wander dog in real time, when other targets are captured in the safe distance threshold value of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, if rope connection is carried out between the dog and the figures, the figures are judged to be the owner of the dog, the control of the security camera is stopped, driving is carried out, otherwise, when other targets are captured in the safe distance threshold value of the wander dog, and other target recognition results are figures, rope detection is carried out between the dog and the figures, and if rope connection is not carried out between the dog and the figures, the security camera is controlled continuously to drive until the wander dog is driven out of the community.
2. The intelligent security video monitoring system based on the internet of things according to claim 1, wherein: the unidentified target establishing unit (10) establishes regional network connection through the Internet of things equipment and security cameras at different positions in the cell, so that video pictures and the security cameras are transmitted and controlled through the Internet of things.
3. The intelligent security video monitoring system based on the internet of things according to claim 1, wherein: the unidentified target setting unit (10) includes a signboard marking module;
the signboard marking module is used for positioning the signboard on the acquired video image, extracting images of dogs and figures appearing on the surface of the signboard, and sending the extracted dogs and figures to the security camera capable of shooting the signboard as a static landform in combination with the signboard image, so that the security camera takes the received images as a target which is not recognized and captured.
4. The intelligent security video monitoring system based on the internet of things according to claim 1, wherein: the wandering dog discovery unit (20) adopts an artificial intelligence technology to analyze the monitoring video in real time and automatically detect face recognition and animal recognition.
5. The intelligent security video monitoring system based on the internet of things according to claim 1, wherein: the wandering dog finding unit (20) comprises a wandering dog identification module;
the wandering dog recognition module is used for capturing faces in video pictures, performing biological recognition on captured targets, if the captured targets are recognized as dogs, displaying the dynamic targets as dogs according to recognition results, judging that the dogs are wandering dogs, and sending the positions of security cameras for detecting the wandering dogs to a wandering dog driving unit (30), otherwise, if the dogs are recognized as dogs, displaying the dynamic targets as dogs according to recognition results, meanwhile, recognizing that the other dynamic targets are figures, and judging that the dogs are not wandering dogs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311595300.4A CN117315594B (en) | 2023-11-28 | 2023-11-28 | Intelligent security video monitoring system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311595300.4A CN117315594B (en) | 2023-11-28 | 2023-11-28 | Intelligent security video monitoring system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117315594A CN117315594A (en) | 2023-12-29 |
| CN117315594B true CN117315594B (en) | 2024-03-15 |
Family
ID=89273968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311595300.4A Active CN117315594B (en) | 2023-11-28 | 2023-11-28 | Intelligent security video monitoring system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117315594B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103783028A (en) * | 2014-01-10 | 2014-05-14 | 中国科学院长春光学精密机械与物理研究所 | Acousto-optical device for driving animals |
| CN107549033A (en) * | 2017-09-29 | 2018-01-09 | 南京华域云脑信息科技有限公司 | A kind of wandering canine quick control device |
| CN110533566A (en) * | 2019-08-23 | 2019-12-03 | 唐山哈船科技有限公司 | A kind of managing device and application method of vagrant dog |
| CN111994259A (en) * | 2020-09-08 | 2020-11-27 | 宁波拉修智能科技有限公司 | Unmanned aerial vehicle formula is unrestrained dog trapping apparatus |
| CN112580482A (en) * | 2020-12-14 | 2021-03-30 | 深圳优地科技有限公司 | Animal monitoring method, terminal and storage medium |
| CN213938115U (en) * | 2021-02-02 | 2021-08-10 | 上海慕客信信息科技有限公司 | Animal monitoring and driving system applied to residential area |
| CN115226702A (en) * | 2022-07-12 | 2022-10-25 | 南京信息职业技术学院 | Method and device for intercepting and driving small wild animals |
| CN116110002A (en) * | 2022-12-27 | 2023-05-12 | 广州西麦科技股份有限公司 | Small animal driving method and system based on image recognition |
| CN116385965A (en) * | 2023-03-17 | 2023-07-04 | 深圳市明源云科技有限公司 | Method, apparatus and computer readable storage medium for identifying a wandering animal |
| CN116994389A (en) * | 2023-06-29 | 2023-11-03 | 南京工业大学 | Monitoring alarm driving system and method based on artificial intelligence and image recognition |
-
2023
- 2023-11-28 CN CN202311595300.4A patent/CN117315594B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103783028A (en) * | 2014-01-10 | 2014-05-14 | 中国科学院长春光学精密机械与物理研究所 | Acousto-optical device for driving animals |
| CN107549033A (en) * | 2017-09-29 | 2018-01-09 | 南京华域云脑信息科技有限公司 | A kind of wandering canine quick control device |
| CN110533566A (en) * | 2019-08-23 | 2019-12-03 | 唐山哈船科技有限公司 | A kind of managing device and application method of vagrant dog |
| CN111994259A (en) * | 2020-09-08 | 2020-11-27 | 宁波拉修智能科技有限公司 | Unmanned aerial vehicle formula is unrestrained dog trapping apparatus |
| CN112580482A (en) * | 2020-12-14 | 2021-03-30 | 深圳优地科技有限公司 | Animal monitoring method, terminal and storage medium |
| CN213938115U (en) * | 2021-02-02 | 2021-08-10 | 上海慕客信信息科技有限公司 | Animal monitoring and driving system applied to residential area |
| CN115226702A (en) * | 2022-07-12 | 2022-10-25 | 南京信息职业技术学院 | Method and device for intercepting and driving small wild animals |
| CN116110002A (en) * | 2022-12-27 | 2023-05-12 | 广州西麦科技股份有限公司 | Small animal driving method and system based on image recognition |
| CN116385965A (en) * | 2023-03-17 | 2023-07-04 | 深圳市明源云科技有限公司 | Method, apparatus and computer readable storage medium for identifying a wandering animal |
| CN116994389A (en) * | 2023-06-29 | 2023-11-03 | 南京工业大学 | Monitoring alarm driving system and method based on artificial intelligence and image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117315594A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109922310B (en) | Target object monitoring method, device and system | |
| US20200394898A1 (en) | System and method for monitoring a property using drone beacons | |
| CN106341661B (en) | Patrol robot | |
| CN108055501A (en) | A kind of target detection and the video monitoring system and method for tracking | |
| US20180137362A1 (en) | Action recognition in a video sequence | |
| CN110633612B (en) | Monitoring method and system for inspection robot | |
| CN104135645A (en) | Video surveillance system and method for face tracking and capturing | |
| WO2019179468A1 (en) | Control method for smart device, apparatus, device, and storage medium | |
| CN112149513A (en) | Industrial manufacturing site safety helmet wearing identification system and method based on deep learning | |
| CN104902233B (en) | Comprehensive safety monitor system | |
| CN109446946B (en) | Multi-camera real-time detection method based on multithreading | |
| CN107232175A (en) | Scarer and its bird repellent method based on birds feature recognition | |
| CN111242025A (en) | Action real-time monitoring method based on YOLO | |
| CN112232211A (en) | Intelligent video monitoring system based on deep learning | |
| CN112911156B (en) | Patrol robot and security system based on computer vision | |
| US10789832B2 (en) | System and method for preventing false alarms due to display images | |
| CN107133611A (en) | A kind of classroom student nod rate identification with statistical method and device | |
| CN110532882A (en) | Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| CN110516600A (en) | A kind of bus passenger flow detection method based on Face datection | |
| CN111354011A (en) | Multi-moving-target information capturing and tracking system and method | |
| CN109634271A (en) | A kind of indoor moving service robot and its control method | |
| CN206331472U (en) | A kind of interactive robot based on Face datection | |
| CN117315594B (en) | Intelligent security video monitoring system based on Internet of things | |
| CN108960146A (en) | The image pre-processing method of recognition of face monitor video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |