CN114639172A - High-altitude parabolic early warning method and system, electronic equipment and storage medium - Google Patents
High-altitude parabolic early warning method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114639172A CN114639172A CN202210536465.3A CN202210536465A CN114639172A CN 114639172 A CN114639172 A CN 114639172A CN 202210536465 A CN202210536465 A CN 202210536465A CN 114639172 A CN114639172 A CN 114639172A
- Authority
- CN
- China
- Prior art keywords
- human body
- camera
- hand
- early warning
- depth map
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000035484 reaction time Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The embodiment of the application relates to the technical field of security monitoring, and discloses a high-altitude parabolic early warning method, a high-altitude parabolic early warning system, electronic equipment and a storage medium, wherein the method comprises the following steps: under the condition that a human body exists in the acquired first depth maps of the indoor scenes shot by the first cameras, continuously acquiring second depth maps of the indoor scenes shot by the first cameras, wherein the first cameras are arranged above the indoor side of the window and shoot the indoor scenes; determining hand key points in each second depth map respectively, and determining a hand region motion track of the human body according to the hand key points in each second depth map; if the motion trail of the hand region meets the preset parabola judgment standard, the suspected high-altitude parabola of the human body is determined, and a high-altitude parabola early warning prompt is sent.
Description
Technical Field
The embodiment of the application relates to the technical field of security monitoring, in particular to a high-altitude parabolic early warning method, a high-altitude parabolic early warning system, electronic equipment and a storage medium.
Background
With the improvement of productivity, cities are developed to be different and thrive, city buildings as important urban components have living, commercial and office functions, skyscrapers in various places are taken out, and the construction work is as good as fire, but with the rising of building height, the risk of throwing things at high altitude is improved.
The inventor of the application finds that the currently general high-altitude parabolic detection system is used for shooting by enabling a camera to face a window of a building or installing the camera on the ground to shoot sky, so that whether an object is thrown out of the high altitude is detected, the approximate falling point of the object is estimated, a high-altitude parabolic alarm is sent out based on the falling point to remind a pedestrian on the ground to avoid, but the object is thrown out of the window in the detection mode, the reaction time left for the pedestrian is short, and the high-altitude parabolic detection system still has great potential safety hazards.
Disclosure of Invention
An object of the embodiments of the present application is to provide a high altitude parabolic warning method, system, electronic device and storage medium, which can predict whether a person may throw objects in high altitude and make a warning when the person approaches a window, thereby greatly increasing the response time left for pedestrians, and better ensuring the safety of the pedestrians.
In order to solve the technical problem, an embodiment of the present application provides a high altitude parabolic warning method, including the following steps: under the condition that a human body exists in an acquired first depth map of an indoor scene shot by a first camera, continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera; the plurality of second depth maps are continuous in time sequence, and the first camera is arranged above the indoor side of the window and shoots the indoor scene; determining hand key points in each second depth map respectively, and determining a hand region motion trail of the human body according to the hand key points in each second depth map; if the motion trail of the hand region meets a preset parabola judgment standard, determining that the human body is suspected to be high-altitude parabolic, and sending a high-altitude parabolic early warning prompt; the high-altitude parabolic early warning prompt is used for indicating that the pedestrian leaves a preset dangerous area.
The embodiment of the present application further provides a high altitude parabolic early warning system, including: the system comprises a first camera, a human body detection module, a positioning module, a track description module and an early warning prompt module; the first camera is arranged above the indoor side of the window and used for shooting indoor scenes; the human body detection module is used for acquiring a first depth map of the indoor scene shot by the first camera and carrying out human body detection on the first depth map; the positioning module is used for continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera under the condition that a human body exists in the first depth map, and respectively determining a hand key point in each second depth map, wherein the plurality of second depth maps are continuous in time sequence; the track drawing module is used for determining a hand area motion track of a human body according to the hand key points in the second depth maps; the early warning prompting module is used for judging whether the hand region motion track meets a preset parabola judgment standard or not, determining the suspected high-altitude parabola of the human body and sending out a high-altitude parabola early warning prompt under the condition that the hand region motion track meets the parabola judgment standard, wherein the high-altitude parabola early warning prompt is used for indicating pedestrians to leave a preset dangerous region.
An embodiment of the present application further provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the high altitude parabolic warning method described above.
Embodiments of the present application further provide a computer-readable storage medium storing a computer program, where the computer program is executed by a processor to implement the high altitude parabolic warning method.
According to the high altitude parabolic early warning method, the system, the electronic device and the storage medium provided by the embodiment of the application, under the condition that a human body exists in an acquired first depth map of an indoor scene shot by a first camera, a plurality of second depth maps of the same indoor scene shot by the first camera are continuously acquired, wherein the plurality of second depth maps are continuous in time sequence, the first camera is arranged above the indoor side of a window and shoots the indoor scene, after the server acquires the plurality of second depth maps, hand key points are respectively determined in each second depth map, a hand region motion track of the human body is determined according to the hand key points in each second depth map, if the hand region motion track of the human body meets a preset parabolic judgment standard, the suspected high altitude parabolic early warning prompt is determined, wherein, the high-altitude parabolic early warning prompt is used for indicating pedestrians to leave a preset dangerous area, and considering that a current general high-altitude parabolic detection system is used, a camera used for shooting is used for shooting towards a window of a building, or the camera is installed on the ground surface and shoots towards the sky, an object is already thrown out of the window when in detection in such a detection mode, and the reaction time left for the pedestrians is short.
In addition, the determining the motion trajectory of the hand region of the human body according to the hand key points in each second depth map includes: sequentially taking each hand key point as a to-be-positioned point, and acquiring a depth value of the to-be-positioned point and a two-dimensional coordinate of the to-be-positioned point in the corresponding second depth map; obtaining a three-dimensional coordinate of the point to be located according to the depth value of the point to be located and the two-dimensional coordinate of the point to be located in the corresponding second depth map; according to the three-dimensional coordinates of each point to be positioned, curve fitting is carried out on each point to be positioned, the fitted curve is used as the motion trail of the hand area of the human body, in general, the uncivilized high-altitude parabolic behavior is that a person approaches a window and throws, throws and throws, no matter throwing from top to bottom or throwing from bottom to top, the hand state of the person has a motion action from back to front relative to the window, the motion trail of the motion action is a parabola or is close to the parabola, the depth map can not only determine the two-dimensional position of a point, but also know the depth value of the point, namely the distance between the point and a first camera (window), thereby the three-dimensional position coordinates of the key point of the hand can be solved, and the motion trail of the hand area of the human body can be scientifically and accurately fitted according to the change of the three-dimensional position coordinates of the key point of the hand with continuous time sequence, therefore, the accuracy of high-altitude parabolic early warning is improved.
In addition, the fitting of a curve to each point to be located according to the three-dimensional coordinates of each point to be located and taking the fitted curve as the motion trajectory of the hand region of the human body includes: respectively connecting hand key points corresponding to two second depth maps adjacent in time sequence according to the three-dimensional coordinates of each to-be-positioned point to obtain K-1 basic motion line segments; and performing curve fitting on the K-1 basic motion line segments, taking the fitted curve as the motion track of the hand region of the human body, considering that curve fitting is directly performed on each to-be-positioned point, the calculated amount is large, the fitting speed is low, firstly, the hand key points corresponding to two adjacent second depth maps in the time sequence are respectively connected to obtain K-1 basic motion line segments, and the K-1 basic motion line segments are fitted, the calculated amount is small, the fitting speed is high, so that the response speed of high altitude parabolic early warning can be further increased, and the safety of pedestrians is further ensured.
In addition, the continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera when a human body exists in the acquired first depth map of the indoor scene shot by the first camera includes: determining a hand area of a human body when the human body exists in an acquired first depth map of an indoor scene shot by a first camera; judging whether the hand area is in a holding state or not according to the outline of the hand area; the regional condition for holding the state of hand, acquire a plurality of in succession the first camera is shot the second depth map of indoor scene, people are before making the high altitude thing this kind of uneventful action of throwing, must hold the object of being thrown in the hand, and people move before the window, stretch lazy waist, when looking at the scenery, generally can not hold the object, consequently this application has human body and human hand region when holding the state in detecting first depth map, carries out the detection process of high altitude thing early warning again, can practice thrift computational resources, avoids unnecessary computational resource waste.
In addition, the high-altitude parabolic early warning prompt includes a preset avoidance prompt audio frequency and a preset avoidance prompt projection pattern, and if the hand region motion track meets the parabolic judgment standard, the suspected high-altitude parabolic body of the human body is determined, and the high-altitude parabolic early warning prompt is sent out, including: if the motion track of the hand area meets a preset parabola judgment standard, determining that the human body is suspected to be parabolic in high altitude, and playing the avoidance prompt audio; starting a second camera and continuously acquiring a plurality of third depth maps of the scene outside the window shot by the second camera; the plurality of third depth maps are continuous in time sequence, and the second camera is arranged above the outdoor side of the window and shoots the scene outside the window; respectively determining key points of a target object in each third depth map, and determining a motion track of the target object according to the key points of the target object in each third depth map; estimating a drop point area of the target object according to the motion track of the target object, projecting the avoidance prompt projection pattern to the drop point area, immediately playing an avoidance prompt audio by an audio system on the ground after high-altitude parabolic behavior is suspected to occur, giving early warning to ground pedestrians at the first time, meanwhile, starting to work by a second camera arranged above the outdoor side of the window, determining the motion track of the thrown target object so as to estimate the drop point area of the target object, then projecting the avoidance prompt projection pattern to the drop point area to strengthen early warning, attracting the attention of ground pedestrians as much as possible from two visual and auditory dimensions, and better ensuring the safety of the pedestrians.
In addition, the method for continuously acquiring a plurality of second depth maps of an indoor scene shot by a first camera when a human body exists in the acquired first depth map of the indoor scene shot by the first camera includes: when the M first depth maps are all provided with human bodies, a plurality of second depth maps of the indoor scene shot by the first cameras are continuously obtained, and considering that the first depth maps with human bodies can also be obtained when the first cameras shoot before people pass through a window, but no human bodies exist in the continuously collected second depth maps, the method obtains the M first depth maps with continuous time sequence for triggering judgment, and continuously obtains the second depth maps of the indoor scene shot by the first cameras when the M first depth maps with human bodies exist, so that operation resources can be friendly saved.
Additionally, after the determining that the human body is suspected of being a high altitude parabola, the method further comprises: opening a color lens of the first camera, and acquiring and outputting a first color image of the indoor scene shot by the first camera; the first color image comprises the complete human face of the human body, and after the person close to the window is determined to be suspected to be a high altitude parabola, the color lens of the first camera is immediately activated to shoot an indoor scene to obtain the first color image, and the identity of a high altitude parabola culprit is locked in real time, so that powerful fact evidence is provided for subsequent punishment and accountability.
Drawings
One or more embodiments are illustrated by the corresponding figures in the drawings, which are not meant to be limiting.
Fig. 1 is a first flowchart of a high altitude parabolic warning method according to an embodiment of the present application;
FIG. 2 is a schematic view of a first camera in relation to a window provided in an embodiment of the present application;
FIG. 3 is a flow chart of determining a motion trajectory of a hand region of a human body from hand keypoints in each second depth map in an embodiment of the present application;
fig. 4 is a flowchart illustrating curve fitting of each point to be located according to the three-dimensional coordinates of each point to be located and using the fitted curve as a motion trajectory of a hand region of a human body in an embodiment of the present application;
fig. 5 is a flowchart illustrating that, in an embodiment of the present application, when a human body exists in a first depth map of an indoor scene captured by a first camera, a plurality of second depth maps of the indoor scene captured by the first camera are continuously obtained;
FIG. 6 is a flowchart illustrating a method for determining a suspected high-altitude parabola from a human body and issuing a high-altitude parabola warning prompt according to an embodiment of the present disclosure;
fig. 7 is a flowchart of a high altitude parabolic warning method according to another embodiment of the present application;
FIG. 8 is a schematic diagram of a high altitude parabolic warning system provided in an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that in the various embodiments of the present application, numerous technical details are set forth in order to provide a better understanding of the present application. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present application, and the embodiments may be mutually incorporated and referred to without contradiction.
An embodiment of the present application relates to a high altitude parabolic warning method, which is applied to an electronic device, where the electronic device may be a terminal or a server, and the electronic device in this embodiment and the following embodiments are described by taking the server as an example.
The specific process of the high altitude parabolic warning method of this embodiment may be as shown in fig. 1, and includes:
In a specific implementation, as shown in fig. 2, a first camera is disposed above an indoor side of a window and photographs an indoor scene, a person is located indoors and can see scenes outside the first camera and the window when standing in front of the window, a server can acquire a first depth map photographed by the first camera on the indoor scene in real time and detect whether a human body exists in the first depth map based on a preset human body detection algorithm, and the server can continuously acquire a plurality of second depth maps of the indoor scene photographed by the first camera under the condition that the human body exists in the first depth map of the indoor scene photographed by the first camera, the plurality of second depth maps being continuous in time sequence, wherein the preset human body detection algorithm can be selected and set by a person skilled in the art according to actual needs.
In an example, if it is detected that no human body exists in the first depth map, the server may obtain a next first depth map of the indoor scene captured by the first camera, and detect whether a human body exists in the first depth map based on a preset human body detection algorithm.
In one example, a first camera performs real-time recording shooting on an indoor scene to obtain a real-time depth video of a target scene, video picture content corresponding to a latest frame in the real-time depth video is a first depth map of the indoor scene shot by the first camera, and after a human body is detected in the first depth map, a server can acquire video picture content corresponding to a plurality of continuous frames of which the time sequence is after the frame corresponding to the first depth map, wherein the video picture content corresponding to the plurality of continuous frames is a plurality of second depth maps of the indoor scene shot by the first camera.
In one example, the first depth maps are M, M is an integer greater than 1, the M first depth maps are continuous in time sequence, after the server acquires the M first depth maps, whether human bodies exist in the M first depth maps or not can be respectively detected, the server continuously acquires a plurality of second depth maps of the indoor scene shot by the first camera when detecting that human bodies exist in the M first depth maps, and the application acquires the M first depth maps which are continuous in time sequence for triggering judgment in consideration that the first depth maps of human bodies can be acquired when the first camera shoots before people pass through a window, but no human bodies exist in the continuously acquired second depth maps, can well save calculation and operation resources.
And step 102, determining hand key points in each second depth map, and determining a hand region motion track of the human body according to the hand key points in each second depth map.
Specifically, after the server acquires a plurality of second depth maps with continuous time sequences, the server may determine a hand key point in each second depth map, and then determine a hand region motion trajectory of the human body according to the hand key point in each second depth map.
In specific implementation, the server sequentially takes each second depth map as an image to be detected, the server can detect a human body region and a hand region in the image to be detected according to a preset detection algorithm such as a detection algorithm based on a depth value gradient, a central point of a circumscribed rectangle of the outline of the hand region is taken as a hand key point, and after all the hand key points in the image to be detected are detected, the server determines a motion trajectory of the hand region of the human body according to position changes among the hand key points.
And 103, if the motion track of the hand area of the human body meets a preset parabola judgment standard, determining suspected high-altitude parabola of the human body, and sending a high-altitude parabola early warning prompt.
Specifically, after the server determines the motion trajectory of the hand region of the human body, whether the motion trajectory of the hand region meets a preset parabola judgment standard or not can be judged, if the motion trajectory of the hand region meets the preset parabola judgment standard, a suspected high-altitude parabola of the human body can be determined, namely, the behavior of the human body is similar to that of the high-altitude parabola, the pedestrian on the floor has the risk of being hit, the server immediately sends out a high-altitude parabola early warning prompt to indicate that the pedestrian leaves the preset dangerous region, the pedestrian can receive the high-altitude parabola early warning prompt when the object is just thrown out of the window or is just thrown out of the window, and has sufficient response time to leave the building so as to avoid the object thrown out of the high altitude, wherein the preset parabola judgment standard can be selected and set by technicians in the field according to actual needs, the preset dangerous region can be selected and set by the technicians in the field according to factors such as the height of the building plan, the embodiment of the present application is not particularly limited to this.
In a specific implementation, the high-altitude parabolic motion is roughly divided into three types, namely, the ' throwing ' of the hand from top to bottom, ' throwing ' of the hand from bottom to top ' and the ' losing ' of the hand from being close to the body to being far away from the body, the motion tracks of the three types of motion are approximate to parabolas, and only the directions and the positions in the three-dimensional space are slightly different, so that if the server detects that the human body is close to a window, and the motion track of the hand area of the human body is approximate to a parabola, the human body is likely to make the high-altitude parabolic motion, the safety of pedestrians in the downstairs is threatened, and the pedestrians in the downstairs need to be reminded to avoid in time.
In an example, after the server determines a hand region motion trajectory of a human body, the hand region motion trajectory may be input into a pre-trained parabolic detection model, a detection result of the parabolic detection model on the hand region motion trajectory is obtained, if the hand region motion trajectory is determined to be a parabola by the parabolic detection model, the server determines a suspected high-altitude parabola of the human body and sends a high-altitude parabola early warning prompt, wherein the pre-trained parabolic detection model may be obtained by performing iterative training on the basis of a large number of parabolic samples and non-parabolic samples by a person skilled in the art, and the pre-trained model is used for determining the parabola, so that the detection speed of the high-altitude parabola can be further increased.
In this embodiment, a server continuously obtains a plurality of second depth maps of the same indoor scene shot by a first camera when a human body exists in an obtained first depth map of the indoor scene shot by the first camera, wherein the plurality of second depth maps are continuous in time sequence, the first camera is arranged above the indoor side of a window and shoots the indoor scene, after the server obtains the plurality of second depth maps, a hand key point is determined in each second depth map, a hand region motion track of the human body is determined according to the hand key point in each second depth map, if the hand region motion track of the human body meets a preset parabola judgment standard, the suspected high-altitude parabolic warning prompt of the human body is determined, and a high-altitude parabolic warning prompt is sent, wherein the high-altitude parabolic warning prompt is used for indicating that the pedestrian leaves a preset danger region, considering that the prior general high-altitude parabolic detection system is used for shooting a camera facing a window of a building or installing the camera on the ground to shoot sky, when the detection mode is used for detecting, an object is thrown out of the window, and the response time left for a pedestrian is short.
In an embodiment, the determining, by the server, the motion trajectory of the hand region of the human body according to the hand key points in each second depth map may be implemented by the steps shown in fig. 3, which specifically include:
and step 201, sequentially taking each hand key point as a point to be located, and acquiring a depth value of the point to be located and a two-dimensional coordinate of the point to be located in a corresponding second depth map.
Specifically, after the server determines the hand key points in each second depth map, the server may sequentially use each hand key point as the to-be-located point, traverse each to-be-located point, obtain the depth value of the current to-be-located point and the two-dimensional coordinate of the current to-be-located point in the corresponding second depth map, and then obtain the three-dimensional coordinate of the current to-be-located point according to the depth value of the current to-be-located point and the two-dimensional coordinate of the current to-be-located point in the corresponding second depth map.
And step 203, performing curve fitting on each point to be positioned according to the three-dimensional coordinates of each point to be positioned, and taking the fitted curve as the motion track of the hand area of the human body.
Specifically, after the server obtains the three-dimensional coordinates of each point to be positioned, a plurality of isolated points are actually determined in a three-dimensional space, the server performs curve fitting on each point to be positioned in a curve fitting mode according to the three-dimensional coordinates of each point to be positioned, and a fitted curve obtained through fitting is used as a motion track of a hand area of a human body.
In the specific implementation, the uncivilized high-altitude parabolic behavior is that a person approaches a window and throws, throws and throws, no matter throwing from top to bottom or throwing from bottom to top, the hand state of the person has a motion action from back to front relative to the window, the motion track of the motion action is a parabola or a motion track close to the parabola, the depth map can determine the two-dimensional position of a point and can also know the depth value of the point, namely the distance between the point and a first camera (window), therefore, the three-dimensional position coordinates of the hand key point can be calculated, the hand region motion track of the human body can be scientifically and accurately fitted according to the change of the three-dimensional position coordinates of the hand key point with continuous time sequence, and the accuracy of high-altitude parabolic early warning is improved.
In one example, the number of the second depth maps is K, where K is an integer greater than 1, and the server performs curve fitting on each point to be located according to the three-dimensional coordinates of each point to be located, and uses the fitted curve as a motion trajectory of a hand region of a human body, which may be implemented by the sub-steps shown in fig. 4, and specifically includes:
Specifically, the server obtains three-dimensional coordinates of each point to be located, namely after K isolated points are determined in a three-dimensional space, the three-dimensional coordinates of each point to be located can be respectively connected with the hand key points corresponding to two adjacent second depth maps in a time sequence to obtain K-1 basic motion line segments, curve fitting is carried out on the K-1 basic motion line segments, and the fitted curve is used as the motion trail of the hand region of the human body.
In the specific implementation, the curve fitting is directly carried out on each point to be positioned, the calculated amount is large, the fitting speed is low, the hand key points corresponding to two adjacent second depth maps in the time sequence are connected respectively to obtain K-1 basic motion line segments, and then the K-1 basic motion line segments are fitted, so that the calculated amount is small, the fitting speed is high, the response speed of high-altitude parabolic early warning can be further improved, and the safety of pedestrians is further guaranteed.
In an embodiment, when a human body exists in the acquired first depth map of the indoor scene captured by the first camera, the server continuously acquires the second depth maps of the indoor scenes captured by the plurality of first cameras, which may be implemented by the steps shown in fig. 5, and specifically includes:
in step 301, when a human body is present in the acquired first depth map of the indoor scene captured by the first camera, a hand region of the human body is determined.
In a specific implementation, the server obtains a first depth map of the indoor scene captured by the first camera again, and determines that the hand area of the human body exists in the first depth map according to a preset target area detection algorithm, such as a target area detection algorithm based on a depth value gradient, and the like, when the human body exists in the first depth map.
Specifically, after the server determines a hand region of a human body in the first depth map, whether the hand region is in a holding state or not can be judged according to the outline of the hand region, if the hand region of the human body is determined to be in the holding state, it is indicated that an object is held in a hand of the human body, that is, the high-altitude parabolic possibility exists, at the moment, the server continuously acquires a plurality of second depth maps of indoor scenes shot by the first camera, and the high-altitude parabolic monitoring process is continued; if the hand area of the human body is judged not to be in the holding state, the fact that no object exists in the hand of the human body is shown, the user can hardly go to high altitude for throwing, potential safety hazards do not exist, the server can quit the early warning, and the first depth map of the indoor scene shot by the first camera is obtained again.
In the concrete implementation, the object thrown out must be held in the hand before people do the high-altitude object throwing type of the unconscious behavior, and people generally cannot hold the object when moving in front of a window, stretching to the waist and looking at the scenery, so that when the detection result shows that a human body exists in the first depth map and the hand area of the human body is in the holding state, the detection process of the high-altitude object throwing early warning is carried out, the calculation resources can be saved, and the unnecessary calculation resource waste is avoided.
In one embodiment, the high-altitude parabolic warning prompt includes a preset avoidance prompt audio and a preset avoidance prompt projection pattern, and if the motion trajectory of the hand region meets a preset parabolic judgment standard, the server may determine that the human body is suspected to be a high-altitude parabolic object through the steps shown in fig. 6, and send out the high-altitude parabolic warning prompt, which is specifically as follows:
Specifically, after the server judges that the motion track of the hand region meets a preset parabola judgment standard, the suspected high-altitude parabola of the human body is determined, an avoidance prompting audio is played immediately, the avoidance prompting audio is played by playing equipment arranged on the ground, the server is communicated with the playing equipment arranged on the ground, after the suspected high-altitude parabola of the human body is determined, the server can issue a broadcast instruction to the playing equipment, and after the playing equipment receives the broadcast instruction, the avoidance prompting audio is played.
And 402, starting the second camera, and continuously acquiring third depth maps of the outdoor scenes shot by the second cameras.
In the specific implementation, the second camera is arranged above the outdoor side of the window and shoots the outdoor scene in real time, the server starts the second camera immediately after determining that the human body is suspected to be parabolic high above the sky, and continuously acquires a plurality of third depth maps of the outdoor scene shot by the second camera, wherein the plurality of third depth maps are continuous in time sequence.
In one example, the server may also perform step 401 and step 402 at the same time.
And step 403, respectively determining key points of the target object in each third depth map, and determining the motion track of the target object according to the key points of the target object in each third depth map.
In the specific implementation, the server determines key points of the target object in each third depth map, sequentially takes the key points of the target object as points to be estimated, acquires the depth value of the current point to be estimated and the two-dimensional coordinates of the current point to be estimated in the corresponding third depth map, obtains the three-dimensional coordinates of the point to be estimated according to the depth value of the point to be estimated and the two-dimensional coordinates of the point to be estimated in the corresponding third depth map, and finally performs curve fitting on the points to be estimated according to the three-dimensional coordinates of the points to be estimated, and takes the fitted curve as the motion track of the target object.
And step 404, estimating a point falling area of the target object according to the motion track of the target object, and projecting a projection avoiding prompt pattern to the point falling area.
Specifically, after the server determines the motion track of the target object, the drop point area of the target object can be estimated according to the motion track of the target object and by combining the height of the building, the temperature, the humidity, the wind speed and other factors in the day, and the projection pattern for avoiding and prompting is projected to the drop point area, so that the reminding is enhanced.
In the embodiment, after the high-altitude parabolic behavior is suspected to occur, the audio system on the ground immediately plays the avoidance prompt audio, early warning is given to ground pedestrians in the first time, meanwhile, the second camera arranged above the outdoor side of the window starts to work, the motion track of the thrown target object is determined, the falling point area of the target object is estimated, then the avoidance prompt projection pattern is projected to the falling point area to enhance early warning, the attention of the ground pedestrians is attracted from two dimensions of visual sense and auditory sense, and the safety of the pedestrians is better guaranteed.
Another embodiment of the present application relates to a high altitude parabolic warning method, and the following specifically describes implementation details of the high altitude parabolic warning method of the present embodiment, and the following is only implementation details provided for easy understanding, and is not necessary for implementing the present solution, and a specific flow of the high altitude parabolic warning method of the present embodiment may be as shown in fig. 7, and includes:
And 502, respectively determining hand key points in each second depth map, and determining a hand region motion track of the human body according to the hand key points in each second depth map.
In the specific implementation, the first camera is provided with a monocular structured light module and a color lens, the monocular structured light module can acquire depth information of an indoor scene, the color lens can acquire color information of the indoor scene, and after a server determines that a person close to a window is suspected to be a high altitude parabola, the color lens of the first camera is immediately activated to shoot the indoor scene to obtain a first color image which comprises a complete face of the human body, so that the identity of a high altitude parabola performer is locked in real time, and powerful fact evidence is provided for subsequent punishment and responsibility pursuit.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
The embodiments of the present application further relate to a high-altitude parabolic warning system, and the following specifically describes implementation details of the high-altitude parabolic warning system of the present embodiment, and the following is only implementation details provided for easy understanding, and is not necessary for implementing the present solution, and a schematic diagram of the high-altitude parabolic warning system of the present embodiment may be as shown in fig. 8, and includes: a first camera 601, a human detection module 602, a positioning module 603, a trajectory tracing module 604 and an early warning prompt module 605.
The first camera 601 is disposed above the indoor side of the window for capturing an indoor scene.
The human body detection module 602 is configured to obtain a first depth map of an indoor scene captured by the first camera 601, and perform human body detection on the first depth map.
The positioning module 603 is configured to continuously obtain second depth maps of the indoor scene captured by the plurality of first cameras 601 when a human body exists in the first depth map, and determine a hand key point in each of the second depth maps, where the plurality of second depth maps are continuous in time sequence.
The trajectory tracing module 604 is configured to determine a hand region motion trajectory of the human body according to the hand key points in the second depth maps.
The early warning prompting module 605 is configured to determine whether the motion trajectory of the hand region meets a preset parabola determination criterion, determine a suspected high-altitude parabola of the human body when the motion trajectory of the hand region meets the parabola determination criterion, and send a high-altitude parabola early warning prompt, where the high-altitude parabola early warning prompt is used to indicate that the pedestrian leaves a preset danger region.
It should be noted that, all the modules involved in this embodiment are logic modules, and in practical application, one logic unit may be one physical unit, may also be a part of one physical unit, and may also be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, a unit that is not so closely related to solving the technical problem proposed by the present application is not introduced in the present embodiment, but this does not indicate that there is no other unit in the present embodiment.
Another embodiment of the present application relates to an electronic device, as shown in fig. 9, including: at least one processor 701; and a memory 702 communicatively coupled to the at least one processor 701; the memory 702 stores instructions executable by the at least one processor 701, and the instructions are executed by the at least one processor 701, so that the at least one processor 701 can execute the high altitude parabolic warning method in the embodiments.
Where the memory and processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting together one or more of the various circuits of the processor and the memory. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, etc., which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. While the memory may be used to store data used by the processor in performing operations.
Another embodiment of the present application relates to a computer-readable storage medium storing a computer program. The computer program realizes the above-described method embodiments when executed by a processor.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the present application, and that various changes in form and details may be made therein without departing from the spirit and scope of the present application in practice.
Claims (10)
1. A high altitude parabolic early warning method is characterized by comprising the following steps:
under the condition that a human body exists in an acquired first depth map of an indoor scene shot by a first camera, continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera; the first camera is arranged above the indoor side of the window and shoots the indoor scene;
determining hand key points in each second depth map respectively, and determining a hand region motion trail of the human body according to the hand key points in each second depth map;
if the motion trail of the hand region meets a preset parabola judgment standard, determining that the human body is suspected to be high-altitude parabolic, and sending a high-altitude parabolic early warning prompt; the high-altitude parabolic early warning prompt is used for indicating that the pedestrian leaves a preset dangerous area.
2. The high altitude parabolic early warning method according to claim 1, wherein the determining of the motion trajectory of the hand region of the human body according to the hand key points in each of the second depth maps comprises:
sequentially taking each hand key point as a point to be located, and acquiring a depth value of the point to be located and a two-dimensional coordinate of the point to be located in the corresponding second depth map;
obtaining a three-dimensional coordinate of the point to be located according to the depth value of the point to be located and the two-dimensional coordinate of the point to be located in the corresponding second depth map;
and performing curve fitting on each to-be-positioned point according to the three-dimensional coordinates of each to-be-positioned point, and taking the fitted curve as the motion trail of the hand area of the human body.
3. The high altitude parabolic early warning method according to claim 2, wherein the number of the second depth maps is K, where K is an integer greater than 1, and the fitting of the curve to each of the points to be located according to the three-dimensional coordinates of each of the points to be located and the fitting of the fitted curve to the movement trajectory of the hand region of the human body includes:
respectively connecting hand key points corresponding to two second depth maps adjacent in time sequence according to the three-dimensional coordinates of each to-be-positioned point to obtain K-1 basic motion line segments;
and performing curve fitting on the K-1 basic motion line segments, and taking the fitted curve as the motion trail of the hand area of the human body.
4. The high altitude parabolic early warning method according to any one of claims 1 to 3, wherein the continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera under the condition that human bodies exist in the acquired first depth map of the indoor scene shot by the first camera comprises:
determining a hand area of a human body when the human body exists in an acquired first depth map of an indoor scene shot by a first camera;
judging whether the hand area is in a holding state or not according to the outline of the hand area;
and under the condition that the hand area is in a holding state, continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera.
5. The high-altitude parabolic early warning method according to any one of claims 1 to 3, wherein the high-altitude parabolic early warning prompt comprises a preset avoidance prompt audio frequency and a preset avoidance prompt projection pattern, and if the hand region motion trajectory meets a preset parabolic judgment standard, the suspected high-altitude parabolic body of the human body is determined, and the high-altitude parabolic early warning prompt is sent out, and the method comprises the following steps:
if the motion track of the hand area meets the parabola judgment standard, determining that the human body is suspected to be a high-altitude parabola, and playing the avoidance prompt audio;
starting a second camera and continuously acquiring a plurality of third depth maps of the scene outside the window shot by the second camera; the plurality of third depth maps are continuous in time sequence, and the second camera is arranged above the outdoor side of the window and shoots the scene outside the window;
respectively determining key points of a target object in each third depth map, and determining a motion track of the target object according to the key points of the target object in each third depth map;
and predicting a drop point area of the target object according to the motion trail of the target object, and projecting the evasion prompt projection pattern to the drop point area.
6. The high altitude parabolic early warning method according to any one of claims 1 to 3, wherein the number of the first depth maps is M, M is an integer greater than 1, the M first depth maps are consecutive in time sequence, and when a human body exists in an acquired first depth map of an indoor scene shot by a first camera, continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera comprises:
and under the condition that human bodies exist in the M first depth maps, continuously acquiring a plurality of second depth maps of the indoor scene shot by the first cameras.
7. The high altitude parabolic warning method according to any one of claims 1 to 3, wherein after the determination that the human body is suspected of being high altitude parabolic, the method further comprises:
opening a color lens of the first camera, and acquiring and outputting a first color image of the indoor scene shot by the first camera; wherein, the first color map comprises a complete human face of the human body.
8. A high altitude parabolic warning system, comprising: the system comprises a first camera, a human body detection module, a positioning module, a track description module and an early warning prompt module;
the first camera is arranged above the indoor side of the window and used for shooting indoor scenes;
the human body detection module is used for acquiring a first depth map of the indoor scene shot by the first camera and carrying out human body detection on the first depth map;
the positioning module is used for continuously acquiring a plurality of second depth maps of the indoor scene shot by the first camera under the condition that a human body exists in the first depth map, and respectively determining a hand key point in each second depth map, wherein the plurality of second depth maps are continuous in time sequence;
the track drawing module is used for determining a hand region motion track of a human body according to the hand key points in each second depth map;
the early warning prompting module is used for judging whether the hand region motion track meets a preset parabola judgment standard or not, determining the suspected high-altitude parabola of the human body and sending out a high-altitude parabola early warning prompt under the condition that the hand region motion track meets the parabola judgment standard, wherein the high-altitude parabola early warning prompt is used for indicating pedestrians to leave a preset dangerous region.
9. An electronic device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the high altitude parabolic warning method of any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the high altitude parabolic warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210536465.3A CN114639172B (en) | 2022-05-18 | 2022-05-18 | High-altitude parabolic early warning method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210536465.3A CN114639172B (en) | 2022-05-18 | 2022-05-18 | High-altitude parabolic early warning method and system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114639172A true CN114639172A (en) | 2022-06-17 |
| CN114639172B CN114639172B (en) | 2022-09-30 |
Family
ID=81952968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210536465.3A Active CN114639172B (en) | 2022-05-18 | 2022-05-18 | High-altitude parabolic early warning method and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114639172B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117423058A (en) * | 2023-11-02 | 2024-01-19 | 江苏三棱智慧物联发展股份有限公司 | High-altitude parabolic detection system and method based on urban safety eyes |
| CN118521944A (en) * | 2024-07-22 | 2024-08-20 | 浙江大华技术股份有限公司 | Method and device for determining throwing animal behaviors, storage medium and electronic device |
| CN118521944B (en) * | 2024-07-22 | 2024-10-22 | 浙江大华技术股份有限公司 | Method and device for determining throwing animal behaviors, storage medium and electronic device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839040A (en) * | 2012-11-27 | 2014-06-04 | 株式会社理光 | Gesture identification method and device based on depth images |
| CN104601939A (en) * | 2013-10-31 | 2015-05-06 | 深圳市东宝嘉科技有限公司 | Method and system for monitoring thrown object and eliminating risks of thrown object |
| US20190209909A1 (en) * | 2015-07-16 | 2019-07-11 | Blast Motion Inc. | Swing quality measurement system |
| CN110778265A (en) * | 2019-10-08 | 2020-02-11 | 赵奕焜 | Child safety protection artificial intelligence door and window system based on deep learning model |
| CN112818766A (en) * | 2021-01-18 | 2021-05-18 | 深圳英飞拓科技股份有限公司 | High-altitude parabolic detection alarm method and system based on computer vision |
| CN113239822A (en) * | 2020-12-28 | 2021-08-10 | 武汉纺织大学 | Dangerous behavior detection method and system based on space-time double-current convolutional neural network |
| CN113486777A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Behavior analysis method and device for target object, electronic equipment and storage medium |
-
2022
- 2022-05-18 CN CN202210536465.3A patent/CN114639172B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839040A (en) * | 2012-11-27 | 2014-06-04 | 株式会社理光 | Gesture identification method and device based on depth images |
| CN104601939A (en) * | 2013-10-31 | 2015-05-06 | 深圳市东宝嘉科技有限公司 | Method and system for monitoring thrown object and eliminating risks of thrown object |
| US20190209909A1 (en) * | 2015-07-16 | 2019-07-11 | Blast Motion Inc. | Swing quality measurement system |
| CN110778265A (en) * | 2019-10-08 | 2020-02-11 | 赵奕焜 | Child safety protection artificial intelligence door and window system based on deep learning model |
| CN113239822A (en) * | 2020-12-28 | 2021-08-10 | 武汉纺织大学 | Dangerous behavior detection method and system based on space-time double-current convolutional neural network |
| CN112818766A (en) * | 2021-01-18 | 2021-05-18 | 深圳英飞拓科技股份有限公司 | High-altitude parabolic detection alarm method and system based on computer vision |
| CN113486777A (en) * | 2021-07-02 | 2021-10-08 | 北京一维大成科技有限公司 | Behavior analysis method and device for target object, electronic equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117423058A (en) * | 2023-11-02 | 2024-01-19 | 江苏三棱智慧物联发展股份有限公司 | High-altitude parabolic detection system and method based on urban safety eyes |
| CN117423058B (en) * | 2023-11-02 | 2024-05-03 | 江苏三棱智慧物联发展股份有限公司 | High-altitude parabolic detection system and method based on urban safety eyes |
| CN118521944A (en) * | 2024-07-22 | 2024-08-20 | 浙江大华技术股份有限公司 | Method and device for determining throwing animal behaviors, storage medium and electronic device |
| CN118521944B (en) * | 2024-07-22 | 2024-10-22 | 浙江大华技术股份有限公司 | Method and device for determining throwing animal behaviors, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114639172B (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7131843B2 (en) | Monitoring system, management device and monitoring method | |
| RU2670429C1 (en) | Systems and methods of tracking moving objects on video image | |
| CN111294488B (en) | Image pickup apparatus, control method thereof, and storage medium | |
| US20190295243A1 (en) | Method and system for automated video image focus change detection and classification | |
| KR102376479B1 (en) | Method, device and system for controlling for automatic recognition of object based on artificial intelligence | |
| JP2007219948A (en) | User abnormality detection equipment and user abnormality detection method | |
| JP2010049296A (en) | Moving object tracking device | |
| CN112733690A (en) | High-altitude parabolic detection method and device and electronic equipment | |
| CN114639172B (en) | High-altitude parabolic early warning method and system, electronic equipment and storage medium | |
| CN112820014A (en) | Intelligent access control system control method, device, equipment and medium | |
| CN110633648A (en) | Face recognition method and system in natural walking state | |
| CN112653832A (en) | Monitoring method, device and equipment | |
| CN110270078A (en) | Football match special efficacy display systems, method and computer installation | |
| JP2022117996A (en) | Information processing device, data generation method, and program | |
| CN105320958B (en) | A kind of image-recognizing method and system based on location information | |
| CN108732948B (en) | Intelligent device control method and device, intelligent device and medium | |
| KR20190063350A (en) | Method of detecting a shooting direction and apparatuses performing the same | |
| CN114913470B (en) | Event detection method and device | |
| CN113518174A (en) | Shooting method, device and system | |
| KR101582585B1 (en) | UBIQUITOUS-CITY BASED MOVING ROUTE PREDICTION SYSTEM AND METHOD USING A PLURALITY OF CCTVs | |
| KR101088153B1 (en) | Combo type video surveillance system and method thereof | |
| KR101981648B1 (en) | Nighttime monitoring system with power saving function and method thereof | |
| JP2003329762A (en) | Object localization system | |
| KR102660024B1 (en) | Method for detection road event and apparatus for the same | |
| KR20120105782A (en) | Monitoring system for controlling masking of object and method 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230824 Address after: Room 799-4, 7th Floor, Building A3A4, Zhong'an Chuanggu Science and Technology Park, No. 900 Wangjiang West Road, Gaoxin District, Hefei Free Trade Experimental Zone, Anhui Province, 230031 Patentee after: Anhui Lushenshi Technology Co.,Ltd. Address before: 230091 room 611-217, R & D center building, China (Hefei) international intelligent voice Industrial Park, 3333 Xiyou Road, high tech Zone, Hefei, Anhui Province Patentee before: Hefei lushenshi Technology Co.,Ltd. |