CN104821056A - Intelligent guarding method based on radar and video integration - Google Patents
Intelligent guarding method based on radar and video integration Download PDFInfo
- Publication number
- CN104821056A CN104821056A CN201510215440.3A CN201510215440A CN104821056A CN 104821056 A CN104821056 A CN 104821056A CN 201510215440 A CN201510215440 A CN 201510215440A CN 104821056 A CN104821056 A CN 104821056A
- Authority
- CN
- China
- Prior art keywords
- radar
- target
- monitor
- video
- image area
- 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 43
- 230000010354 integration Effects 0.000 title abstract 3
- 230000001360 synchronised effect Effects 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims description 22
- 230000033001 locomotion Effects 0.000 claims description 12
- 238000005498 polishing Methods 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000010339 dilation Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000009193 crawling Effects 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 3
- 239000012925 reference material Substances 0.000 claims description 3
- 230000009545 invasion Effects 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000192 social effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19606—Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19697—Arrangements wherein non-video detectors generate an alarm themselves
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention discloses an intelligent guarding method based on radar and video integration. The intelligent guarding method comprises the steps that 1) radar monitors and video monitors are distributed in a specified monitoring area; 2) the radar monitors performs real-time monitoring, and when entering of an invasion target is monitored, the three-dimensional position coordinates of the monitored invasion target are outputted and early warning information is emitted, and the video monitored are controlled and started to acquire current synchronous images to be outputted simultaneously; 3) the three-dimensional position coordinates monitored by the radar monitors are mapped into corresponding position coordinates in the synchronous images so that radar detection coordinates are obtained; and 4) the invasion target is identified in the synchronous images according to the radar detection coordinates, and whether the invasion target is a target required to be alarmed is judged according to the image data of the identified invasion target so as to confirm alarm information. The intelligent guarding method based on radar and video integration has advantages of being simple in realization method so that intelligent identification and alarm of the invasion target can be realized and alarm accuracy rate is high.
Description
Technical field
The present invention relates to circumference or area protection technical field, particularly relate to a kind of intelligence warning method based on radar and video fusion.
Background technology
Along with the high speed development of society, all starting to be equipped with circumference or region prevention device in places such as oil, large-scale enterprises and institutions, prison, airports, to report to the police when there being suspicious object to enter, reducing suspicious object to the threat monitoring place.But in current circumference or area outlook method, usually be all monitored by single watch-dog, such as carry out early warning by single radar monitor, or by single video monitor with real-time monitor video image, the information that this single monitor mode obtains is not comprehensive and its intelligence degree is low, can not effectively identify suspicious object, cannot determine whether target is the target needing to report to the police, such as suspicious object is pedestrian or other toy (cats, dog, bird etc.), thus also easily wrong report is caused by the impact of external environment.Although existing practitioner proposes method in conjunction with video analysis and other assistant analysis to identify intrusion target, such as Chinese patent application discloses a kind of intrusion target monitoring method towards perimeter protection, by computer auxiliaring means and Video Analysis Technology, detect through target, the intrusion target occurred in intellectualized detection perimeter surveillance video after target special medical treatment extraction and target classification three steps, but the method needs to perform complicated video analysis process, be unfavorable for performing actuation of an alarm fast, simultaneously it is still only depend on the analysis that video data carries out, be unfavorable for the intrusion target of the identification prepared.
Summary of the invention
The technical problem to be solved in the present invention is just: the technical matters existed for prior art, the invention provides that a kind of implementation method is simple, the Intelligent Recognition that can realize intrusion target and warning and the high intelligence warning method based on radar and video fusion of warning accuracy rate.
For solving the problems of the technologies described above, the technical scheme that the present invention proposes is:
A kind of intelligence warning method based on radar and video fusion, step comprises:
1) in appointment guarded region, arrange that radar monitor and video monitor perform monitoring in real time;
2) when described radar monitor has monitored intrusion target, export the three-dimensional location coordinates of the intrusion target monitored and send early warning information, controlling described video monitor simultaneously and export the current synchronous images collected;
3) three-dimensional location coordinates of the described intrusion target monitored by radar monitor is mapped as corresponding position coordinates in described synchronous images, obtains the radar detection coordinate of intrusion target in described synchronous images;
4) the radar detection coordinate obtained according to described step 3) identifies intrusion target in described synchronous images, and determines whether to need alarm target to determine warning message according to the view data of the intrusion target identified.
As a further improvement on the present invention: the coordinate corresponding relation in the plane of delineation that the target monitored according to the radar monitor set up in advance in described step 3) gathers at video monitor, the three-dimensional location coordinates of the described intrusion target monitored by radar monitor is mapped as corresponding position coordinates in described synchronous images; The establishment step of described coordinate corresponding relation is: utilize calibration technique to calculate the inner parameter of video monitor, set up video monitor coordinate model; According to the position relationship between radar monitor and video monitor, set up the coordinate corresponding relation in the plane of delineation that target that radar monitor under world coordinate system monitors gathers at video monitor.
As a further improvement on the present invention: the concrete steps identifying intrusion target in described step 4) in described synchronous images are:
4.11) extract the foreground information in described synchronous images, and calculate the connected domain barycentric coordinates of all objects in described foreground information, obtain the barycentric coordinates of all foreground targets;
4.12) the radar detection coordinate that the barycentric coordinates of foreground target described in each obtain with described step 3) is respectively mated, go out the intrusion target in described synchronous images according to bee-line matched rule match cognization.
Foreground information in described synchronous images is extracted especially by setting up adaptive Gaussian mixture model-universal background model as a further improvement on the present invention: described step 4.11).
As a further improvement on the present invention, described step 4.11) frontly also comprise removal shadow step, concrete steps are: shade outside sensing chamber; What calculate penumbra region takes scale factor; Take required polishing scale factor when scale factor calculation removes shade according to described, return illumination according to described polishing scale factor to shadow region, and retain the texture in shade, obtain the image after removing shade.
As a further improvement on the present invention, described step 4.11) afterwards, step 4.12) frontly also comprise filter step, concrete steps are: utilize the geometrical property of the pedestrian target of morphological dilations operational method and required detection to set up constraint condition, according to described constraint condition to described step 4.11) foreground target that obtains carries out filtering to purify to described foreground target.
As a further improvement on the present invention, the concrete steps of alarm target are determined whether to need to be in described step 4):
4.21) obtain the view data of the intrusion target identified in described synchronous images and calculate corresponding image area, and the standard alarm image area that the position coordinates place obtaining described intrusion target place is corresponding;
4.22) image area of the described intrusion target calculated is compared with described standard alarm image area, if the difference of the image area of described intrusion target and described standard alarm image area is in preset threshold range, then be judged to need alarm target, otherwise be judged to not need alarm target.
As a further improvement on the present invention, described step 4.21) according to the corresponding relation between the position coordinates set up in advance and standard alarm image area, obtain the standard alarm image area that the position coordinates place at described intrusion target place is corresponding; The concrete steps that described corresponding relation is set up are: gather the image area of reference material at diverse location coordinate place by video monitor, and as the standard alarm image area at each position coordinate place, the standard alarm image area at described each position coordinate place is set up corresponding relation between position coordinates and standard alarm image area by curve.
As a further improvement on the present invention, target travel mode identification step 5 is also comprised) after described step 4), concrete steps are: obtained the velocity information of monitoring the intrusion target obtained by radar monitor, judge the mode of motion of intrusion target according to described velocity information; Obtain the deflection of minimum enclosed rectangle, the characteristic parameter of length breadth ratio in the view data of intrusion target, according to described characteristic parameter identification intrusion target whether for crawling at ground motion.
As a further improvement on the present invention: described radar monitor is monostatic radar.
Compared with prior art, the invention has the advantages that:
1) the present invention is based on the intelligence warning method of radar and video fusion, by using radar monitor and video monitor simultaneously, the advantage that can make full use of both realizes complementary, can the information such as position coordinates, movement velocity of invader in Real-time Obtaining radar monitoring region by radar monitor, video monitor can obtain video data, comprehensive Detection Information can be obtained, avoid causing perimeter protection high rate of false alarm because single watch-dog obtains the impact of information not comprehensively or by external environment;
2) the present invention is based on the intelligence warning method of radar and video fusion, the image information collected by the position coordinate data of being monitored by radar monitor and video monitor is merged, image recognition is performed with the location coordinate information obtained in conjunction with radar monitor, from video image, the same intrusion target that radar monitor monitors can be identified fast and accurately, and antijamming capability is strong; Combine the type of the view data differentiation intrusion target of the intrusion target identified simultaneously, to determine warning message, realize Weigh sensor and warning.
3) the present invention is based on the intelligence warning method of radar and video fusion, further by calculating whether the image area identification intrusion target of intrusion target is the target needing to report to the police, utilize the image area of different target thing to there are differences the Intelligent Recognition of realize target type, implementation method is simple and warning accuracy rate is high;
5) the present invention is based on the intelligence warning method of radar and video fusion, the velocity information of intrusion target is further obtained by radar monitor, the mode of motion of target can be identified, the characteristic parameter such as minimum enclosed rectangle deflection, length breadth ratio according to intrusion target can also identify that whether intrusion target is for crawling at ground motion, thus the data that can effectively monitor in conjunction with radar monitor and video monitor perform intrusion target and identify more comprehensively, analyze, thus provide comprehensive warning message.
Accompanying drawing explanation
Fig. 1 is the present embodiment based on the realization flow schematic diagram of the intelligence warning method of radar and video fusion.
What Fig. 2 was the present embodiment based on the intelligence warning method of radar and video fusion realizes principle schematic.
Fig. 3 is the schematic flow sheet setting up coordinate corresponding relation between radar monitor and video monitor in the present embodiment.
Fig. 4 is the realization flow schematic diagram setting up corresponding relation between position coordinates and standard alarm image area in the present embodiment.
Fig. 5 is the idiographic flow schematic diagram of step 4) in the present embodiment.
Embodiment
Below in conjunction with Figure of description and concrete preferred embodiment, the invention will be further described, but protection domain not thereby limiting the invention.
As shown in Figure 1, 2, based on the intelligence warning method of radar and video fusion in the present embodiment, step comprises:
1) in appointment guarded region, arrange that radar monitor and video monitor perform monitoring in real time;
2) when radar monitor has monitored intrusion target, export the three-dimensional location coordinates of the intrusion target monitored and send early warning information, controlling video monitor simultaneously and export the current synchronous images collected;
3) radar video information fusion: the three-dimensional location coordinates of the intrusion target monitored by radar monitor is mapped as corresponding position coordinates in synchronous images, obtains the radar detection coordinate of intrusion target in synchronous images;
4) video image analysis: identify intrusion target according to the radar detection coordinate that step 3) obtains in synchronous images, and determine whether to need alarm target to determine warning message according to the view data of the intrusion target identified.
Radar monitor investigative range is wide, distance and being quick on the draw, and when there being invader to enter radar monitoring region, radar will send early warning information, and prompting has invader to enter.But the type of invader can not be distinguished or identify to radar monitor, thus easily causes wrong report.The image information that video monitor gathers is enriched, and can identify Detection of content, but the depth information of more difficult acquisition object and movable information etc.The present embodiment is monitored appointment guarded region by using radar monitor and video monitor simultaneously, by the information such as position coordinates, movement velocity of invader in radar monitor Real-time Obtaining radar monitoring region, video monitor is then for obtaining the video data of guarded region, can realize complementary in conjunction with the advantage of radar monitor and video monitor, obtain comprehensive Detection Information, avoid causing wrong report because single watch-dog obtains the impact of information not comprehensively or by external environment.
The present embodiment is merged by the position coordinate data of being monitored by radar monitor and video image information, the 3D virtual borderlines of the intrusion target monitored by radar monitor is corresponding 2D coordinate in the plane of delineation, recycling maps the radar detection coordinate obtained and identify intrusion target from the synchronous images of video monitor collection, the location coordinate information that radar monitor obtains effectively is combined in the image recognition processes of intrusion target, thus can realize identifying fast and accurately, and antijamming capability is strong; The view data simultaneously combining the intrusion target identified differentiates the type of intrusion target, to determine warning message, thus realize Weigh sensor and warning, the personnel of monitor area can be broken in or other need the target of reporting to the police and determine whether to need to report to the police by Timeliness coverage, effective reduction intrusion target to the threat of guarded region, its economy brought and social effect remarkable.
In the present embodiment, coordinate corresponding relation in the plane of delineation that the target monitored according to the radar monitor set up in advance in step 3) gathers at video monitor, the three-dimensional location coordinates of the intrusion target monitored by radar monitor is mapped as the position coordinates in synchronous images.The establishment step of coordinate corresponding relation is: utilize calibration technique to calculate the inner parameter of video monitor, set up video monitor coordinate model; According to video monitor coordinate model and the position relationship between radar monitor and video monitor, set up the coordinate corresponding relation in the plane of delineation that target that radar monitor under world coordinate system monitors gathers at video monitor.
As shown in Figure 3, the present embodiment video monitor is video camera, first utilizes the inner parameter of camera calibration technique computes video camera, sets up camera coordinates model; According to the position relationship of video camera and radar monitor, set up the coordinate corresponding relation between video camera and radar under world coordinate system; Finally just can realize the information of radar monitor according to coordinate corresponding relation and video information merges, the 3D world coordinates realizing radar monitor detection to convert in video image corresponding 2D image coordinate p ' (u ', v '), the positional information monitored to make full use of radar monitor corresponds in video image.
In the present embodiment, the concrete steps identifying intrusion target in step 4) in synchronous images are:
4.11) extract the foreground information in synchronous images, and calculate the connected domain barycentric coordinates of all objects in foreground information, obtain the barycentric coordinates of all foreground targets;
4.12) the radar detection coordinate that the barycentric coordinates of each foreground target obtain with step 3) is respectively mated, go out the intrusion target in synchronous images according to bee-line matched rule match cognization.
The present embodiment extracts the barycentric coordinates of all foreground targets from synchronous images, mate with radar detection coordinate again, to set up the matching relationship between information that same object monitors at radar monitor and video monitor, make the target one_to_one corresponding that the target detected in image can detect with radar monitor, thus match cognization goes out the same intrusion target that radar monitor monitors from synchronous images.
According to perimeter system fixed installation, feature that background image is static, the present embodiment step 4.11) in be extract foreground information in synchronous images by setting up adaptive Gaussian mixture model-universal background model, adaptive real-time background modeling method specifically can be adopted slightly to extract foreground target.By setting up adaptive background model, making it possible to be applicable to the background environment different, upgrading background information immediately with the change according to background environment, effectively extract the information of foreground moving.
In the present embodiment, step 4.11) frontly also comprise removal shadow step, concrete steps are: shade outside sensing chamber; What calculate penumbra region takes scale factor, and wherein penumbra region is the transitional region between prospect and background, and take scale factor and specifically get ratio shared by background pixel value, its span is [0,1]; According to taking required polishing scale factor when scale factor calculation removes shade, returning illumination according to polishing scale factor to shadow region, and retaining the texture in shade, obtaining the image after removing shade.Shadow algorithm is dispelled by increasing image, the interference that the shadow decreasing object brings to detection and indentification, so just can avoid in follow-up object matching identifying due to the interference of shade cause occur wrong report situation, effectively raise outdoor environment detect accuracy.
In the present embodiment, remove after shadow step, step 4.1) frontly also comprise filter step, concrete steps are: utilize the geometrical property of the pedestrian target of morphological dilations operational method and required detection to set up constraint condition, carry out filtering to purify to foreground target according to constraint condition to the foreground target obtained.The prospect of background modeling segmentation may can produce a large amount of noises due to illumination, leaf or other trickle object interference, thus utilize morphological dilations computing, detect target geometrical property set up constraint condition carry out filtering, effectively can to purify prospect, thus the flase drop because illumination, leaf, sleet etc. cause can be reduced.
In the present embodiment, in step 4), determine whether that the concrete steps needing alarm target are:
4.21) obtain the view data of the intrusion target identified in synchronous images and calculate corresponding image area, and the standard alarm image area that the position coordinates place obtaining intrusion target place is corresponding;
4.22) image area of the intrusion target calculated is compared with standard alarm image area, if the difference of the image area of intrusion target and standard alarm image area is in preset threshold range, then be judged to need alarm target, otherwise be judged to not need alarm target.
Due at same position place, the image area of the different target thing collected has very big-difference, and such as the image area of same position place pedestrian and other animals is widely different, and image area thus can be utilized to differentiate the type of target.Same object also there are differences in the image area at diverse location place, after the present embodiment identifies intrusion target from the synchronous images of video monitor collection, calculate the image area y ' of intrusion target, according to the position coordinates of the intrusion target that radar monitor monitors, whether the image area y ' of the intrusion target calculated and the standard alarm image area y corresponding to this position are compared, distinguishing intrusion target with this is the target needing to report to the police.The present embodiment take pedestrian as the target needing to report to the police, because the image area y ' that actual computation may be caused to go out in image acquisition, image zooming-out process exists error, therefore a compare threshold (the present embodiment gets 0.5) is set for standard alarm image area y, if the image area y ' of intrusion target is greater than the compare threshold of setting with the ratio value of standard alarm image area y, then can judge that this target is as pedestrian, need to perform warning, otherwise other toys (cat, dog, bird etc.) can be judged as, not need to perform warning.
In the present embodiment, step 4.21) according to the corresponding relation between the position coordinates set up in advance and standard alarm image area, obtain the standard alarm image area that the position coordinates place at intrusion target place is corresponding; The concrete steps that corresponding relation is set up are: gather the image area of reference material at diverse location coordinate place by video monitor, and as the standard alarm image area at each position coordinate place, the standard alarm image area at each position coordinate place is set up corresponding relation between position coordinates and standard alarm image area by curve.
The present embodiment is using pedestrian as the target needing to report to the police, by setting up the corresponding relation between position coordinates and standard alarm image area along the real area in pedestrian contour region in the image coordinate system corresponding to camera light direction of principal axis different distance position under statistics pedestrian alive boundary coordinate system, as shown in Figure 4, before the present embodiment stands in video monitor using the adult of standard figure as standard body, (the present embodiment gets a point every 1 meter from distance video monitor 5 meters to 50 meters at the image of different distance point to gather human body by video monitor, get about 50 points altogether), calculate the image area at different distance point place.If image area is y, distance be x, utilizes these discrete points of least square fitting, the funtcional relationship y=f(x of foundation distance x and area y), funtcional relationship y=f(x) be corresponding relation between position coordinates and standard alarm image area.Utilize radar can the distance in detecting objects z direction, then combining image treatment technology set up the funtcional relationship of object different distance x and corresponding image area y, in this, as the arbiter of succeeding target classification, to identify that whether target is for needs alarm target.
As shown in Figure 5, in the present embodiment, the detailed implementation step of step 4) is:
First shadow removal is carried out to image.Utilize the color space of color space PCS(based on perception of outdoor illumination particularity and improvement) shade outside sensing chamber, what then calculate penumbra region takes scale factor, last basis take scale factor calculation remove shade answer the polishing scale factor of polishing, corresponding illumination is returned to shadow region, reduction natural reality image by polishing scale factor;
Then, adaptive background model is set up;
Secondly, utilize morphological dilations computing, the geometrical property of pedestrian target of required detection sets up constraint condition and carry out filtering, filter the interfere information that some cause due to illumination, leaf, sleet etc.;
Then, the information matches relation of same object at radar monitor and video monitor is set up.The connected domain barycentric coordinates p (u of all objects in calculating prospect
i, v
i), 2D image coordinate p ' that radar monitor is detected (u ', v ') to search for one by one with the barycentric coordinates of all foreground targets and mate, using p and p ' 2 lowest distance value d as matching condition, the information of the same object that two watch-dogs are detected is corresponding, goes out with match cognization from synchronous images the same intrusion target that radar monitor monitors.
Finally, the funtcional relationship y=f(x according to position coordinates and standard alarm image area), the image area s of the intrusion target identified and same position place standard alarm image area y is compared, to judge that intrusion target is pedestrian or other toys.
In the present embodiment, target travel mode identification step 5 is also comprised) after step 4), concrete steps are: obtained the velocity information of monitoring the intrusion target obtained by radar monitor, judge the mode of motion of intrusion target according to velocity information, comprise the mode of motion such as walking or race; Obtain the deflection of minimum enclosed rectangle, the characteristic parameter of length breadth ratio in the view data of intrusion target, according to characteristic parameter identification intrusion target whether for crawling at ground motion.The data of monitoring in conjunction with radar monitor and video monitor can also the information such as acquisition speed information and characteristic parameter, to differentiate the mode of motion of intrusion target, thus provides warning message more comprehensively.While the present embodiment sends warning by upper computer software, the type of the intrusion target that display is detected and invasion mode, make warning message more directly perceived.
In the present embodiment, radar monitoring implement body adopts monostatic radar, and monostatic radar generally can detect the scope of positive and negative 7 meters of x horizontal direction, positive and negative 3 meters of y vertical direction, the 150 meters of distances in z direction, can obtain position and the velocity information of the detection of a target.When there being invader to enter guarded region, can report to the police immediately, system enters alert status.When adopting monostatic radar, only need to be fixed on a monitoring alarm post with video monitor, do not need to need as correlation radar the protection that a pair warning post just can complete guarded region, therefore structure is simple, integrated level is high and cost is low.Traditional microwave correlation radar carries out early warning, can not obtain position and the velocity information of the detection of a target, and need a pair radar to carry out real-time protection to guarded region, complex structure, integrated level are low and cost is high simultaneously.
Above-mentioned just preferred embodiment of the present invention, not does any pro forma restriction to the present invention.Although the present invention discloses as above with preferred embodiment, but and be not used to limit the present invention.Therefore, every content not departing from technical solution of the present invention, according to the technology of the present invention essence to any simple modification made for any of the above embodiments, equivalent variations and modification, all should drop in the scope of technical solution of the present invention protection.
Claims (10)
1. the intelligence warning method based on radar and video fusion, it is characterized in that, step comprises:
1) in appointment guarded region, arrange that radar monitor and video monitor perform monitoring in real time;
2) when described radar monitor has monitored intrusion target, export the three-dimensional location coordinates of the intrusion target monitored and send early warning information, controlling described video monitor simultaneously and export the current synchronous images collected;
3) three-dimensional location coordinates of the described intrusion target monitored by radar monitor is mapped as corresponding position coordinates in described synchronous images, obtains the radar detection coordinate of intrusion target in described synchronous images;
4) the radar detection coordinate obtained according to described step 3) identifies intrusion target in described synchronous images, and determines whether to need alarm target to determine warning message according to the view data of the intrusion target identified.
2. the intelligence warning method based on radar and video fusion according to claim 1, it is characterized in that: the coordinate corresponding relation in the plane of delineation that the target monitored according to the radar monitor set up in advance in described step 3) gathers at video monitor, the three-dimensional location coordinates of the described intrusion target monitored by radar monitor is mapped as corresponding position coordinates in described synchronous images; The establishment step of described coordinate corresponding relation is: utilize calibration technique to calculate the inner parameter of video monitor, set up video monitor coordinate model; According to described video monitor coordinate model and the position relationship between radar monitor and video monitor, set up the coordinate corresponding relation in the plane of delineation that target that radar monitor under world coordinate system monitors gathers at video monitor.
3. the intelligence warning method based on radar and video fusion according to claim 1, it is characterized in that, the concrete steps identifying intrusion target in described step 4) in described synchronous images are:
4.11) extract the foreground information in described synchronous images, and calculate the connected domain barycentric coordinates of all objects in described foreground information, obtain the barycentric coordinates of all foreground targets;
4.12) the radar detection coordinate that the barycentric coordinates of foreground target described in each obtain with described step 3) is respectively mated, go out the intrusion target in described synchronous images according to bee-line matched rule match cognization.
4. the intelligence warning method based on radar and video fusion according to claim 3, is characterized in that, described step 4.11) in extract foreground information in described synchronous images particular by setting up adaptive Gaussian mixture model-universal background model.
5. the intelligence warning method based on radar and video fusion according to claim 4, is characterized in that, described step 4.11) frontly also comprise removal shadow step, concrete steps are: shade outside sensing chamber; What calculate penumbra region takes scale factor; Take required polishing scale factor when scale factor calculation removes shade according to described, return illumination according to described polishing scale factor to shadow region, and retain the texture in shade, obtain the image after removing shade.
6. the intelligence warning method based on radar and video fusion according to claim 5, it is characterized in that, described step 4.11) afterwards, step 4.12) frontly also comprise filter step, concrete steps are: utilize the geometrical property of the pedestrian target of morphological dilations operational method and required detection to set up constraint condition, according to described constraint condition to described step 4.11) foreground target that obtains carries out filtering to purify to described foreground target.
7., according to the intelligence warning method based on radar and video fusion in claim 1 ~ 6 described in any one, it is characterized in that, in described step 4), determine whether that the concrete steps needing alarm target are:
4.21) obtain the view data of the intrusion target identified in described synchronous images and calculate corresponding image area, and the standard alarm image area that the position coordinates place obtaining described intrusion target place is corresponding;
4.22) image area of the described intrusion target calculated is compared with described standard alarm image area, if the difference of the image area of described intrusion target and described standard alarm image area is in preset threshold range, then be judged to need alarm target, otherwise be judged to not need alarm target.
8. the intelligence warning method based on radar and video fusion according to claim 7, it is characterized in that: described step 4.21) according to the corresponding relation between the position coordinates set up in advance and standard alarm image area, obtain the standard alarm image area that the position coordinates place at described intrusion target place is corresponding; The concrete steps that described corresponding relation is set up are: gather the image area of reference material at diverse location coordinate place by video monitor, and as the standard alarm image area at each position coordinate place, the standard alarm image area at described each position coordinate place is set up corresponding relation between position coordinates and standard alarm image area by curve.
9. according to the intelligence warning method based on radar and video fusion in claim 1 ~ 6 described in any one, it is characterized in that, target travel mode identification step 5 is also comprised) after described step 4), concrete steps are: obtained the velocity information of monitoring the intrusion target obtained by radar monitor, judge the mode of motion of intrusion target according to described velocity information; Obtain the deflection of minimum enclosed rectangle, the characteristic parameter of length breadth ratio in the view data of intrusion target, according to described characteristic parameter identification intrusion target whether for crawling at ground motion.
10., according to the intelligence warning method based on radar and video fusion in claim 1 ~ 6 described in any one, it is characterized in that: described radar monitor is monostatic radar.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510215440.3A CN104821056B (en) | 2015-04-30 | 2015-04-30 | Intelligent warning method based on radar and video fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510215440.3A CN104821056B (en) | 2015-04-30 | 2015-04-30 | Intelligent warning method based on radar and video fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104821056A true CN104821056A (en) | 2015-08-05 |
| CN104821056B CN104821056B (en) | 2018-03-20 |
Family
ID=53731338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510215440.3A Active CN104821056B (en) | 2015-04-30 | 2015-04-30 | Intelligent warning method based on radar and video fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104821056B (en) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157507A (en) * | 2016-07-08 | 2016-11-23 | 武汉三江中电科技有限责任公司 | A kind of transmission line of electricity solid preventer based on radar and video fusion |
| CN106291539A (en) * | 2016-07-29 | 2017-01-04 | 山东康威通信技术股份有限公司 | A kind of phased-array radar target identification system based on location filtering algorithm and method |
| CN106447680A (en) * | 2016-11-23 | 2017-02-22 | 湖南华诺星空电子技术有限公司 | Method for radar and vision fused target detecting and tracking in dynamic background environment |
| CN107622618A (en) * | 2016-07-15 | 2018-01-23 | 保定市天河电子技术有限公司 | A kind of transmission line of electricity protective survey apparatus and method |
| CN107770480A (en) * | 2016-08-15 | 2018-03-06 | 保定市天河电子技术有限公司 | A kind of safety defense monitoring system and method |
| CN108152808A (en) * | 2017-11-23 | 2018-06-12 | 安徽四创电子股份有限公司 | A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar |
| CN109643480A (en) * | 2016-07-22 | 2019-04-16 | 路晟（上海）科技有限公司 | Security system and method |
| CN109982043A (en) * | 2019-04-02 | 2019-07-05 | 西安华腾微波有限责任公司 | A kind of information processing method and device of intelligent monitoring |
| CN110097726A (en) * | 2018-01-30 | 2019-08-06 | 保定市天河电子技术有限公司 | A kind of prevention regional aim monitoring method and system |
| CN110126885A (en) * | 2018-02-02 | 2019-08-16 | 保定市天河电子技术有限公司 | A kind of railway circumference intrusion target monitoring method and system |
| CN110171774A (en) * | 2018-12-27 | 2019-08-27 | 李芳龙 | Crane applications based on artificial intelligence (AI) technology |
| CN110491060A (en) * | 2019-08-19 | 2019-11-22 | 深圳市优必选科技股份有限公司 | A kind of robot and its method for safety monitoring, device and storage medium |
| CN110542899A (en) * | 2019-07-25 | 2019-12-06 | 浙江大华技术股份有限公司 | Radar measurement data processing method and device, radar system and readable storage medium |
| CN110633625A (en) * | 2019-07-31 | 2019-12-31 | 北京木牛领航科技有限公司 | Identification method and system |
| CN110658518A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Target intrusion detection method and device |
| CN110865366A (en) * | 2019-10-12 | 2020-03-06 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN110873863A (en) * | 2018-08-29 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Target display method, radar system and electronic equipment |
| CN111045000A (en) * | 2018-10-11 | 2020-04-21 | 阿里巴巴集团控股有限公司 | Monitoring system and method |
| CN111200722A (en) * | 2019-12-09 | 2020-05-26 | 湖州米欧康电子科技有限公司 | Low-altitude management system and signal management method |
| CN111308456A (en) * | 2020-04-08 | 2020-06-19 | 加特兰微电子科技(上海)有限公司 | Target position judging method and device, millimeter wave radar and storage medium |
| CN111340864A (en) * | 2020-02-26 | 2020-06-26 | 浙江大华技术股份有限公司 | Monocular estimation-based three-dimensional scene fusion method and device |
| CN111653054A (en) * | 2020-04-16 | 2020-09-11 | 国家核安保技术中心 | Physical protection system for nuclear facilities |
| CN111913177A (en) * | 2020-08-11 | 2020-11-10 | 中国原子能科学研究院 | Method and device for detecting target object and storage medium |
| CN112133050A (en) * | 2020-09-15 | 2020-12-25 | 朱新培 | Perimeter alarm device based on microwave radar and method thereof |
| CN112147604A (en) * | 2020-09-08 | 2020-12-29 | 成都红云鼎科技有限公司 | Intrusion track calculation method based on radar coordinate conversion |
| CN112333417A (en) * | 2020-04-30 | 2021-02-05 | 深圳Tcl新技术有限公司 | Doorbell disturbance-free mode starting method and device and computer-readable storage medium |
| CN112349055A (en) * | 2020-11-05 | 2021-02-09 | 通号通信信息集团有限公司 | Target monitoring device and method based on radar and video linkage |
| WO2021023106A1 (en) * | 2019-08-02 | 2021-02-11 | 杭州海康威视数字技术股份有限公司 | Target recognition method and apparatus, and camera |
| CN112565863A (en) * | 2020-11-26 | 2021-03-26 | 深圳Tcl新技术有限公司 | Video playing method and device, terminal equipment and computer readable storage medium |
| CN112614290A (en) * | 2020-12-10 | 2021-04-06 | 中科蓝卓(北京)信息科技有限公司 | Radar video cooperative target detection device and method |
| CN112672047A (en) * | 2020-12-20 | 2021-04-16 | 英特睿达(山东)电子科技有限公司 | Image acquisition system and image processing method |
| CN112731385A (en) * | 2020-12-24 | 2021-04-30 | 北京木牛领航科技有限公司 | Personnel control method, device and medium based on millimeter wave radar |
| CN112866645A (en) * | 2021-01-12 | 2021-05-28 | 二连浩特赛乌素机场管理有限公司 | Anti-invasion artificial intelligence radar video monitoring system |
| CN113727011A (en) * | 2020-05-26 | 2021-11-30 | 杭州海康威视数字技术股份有限公司 | Video monitoring method, image acquisition system, electronic device and storage medium |
| CN114419825A (en) * | 2022-03-29 | 2022-04-29 | 中国铁路设计集团有限公司 | High-speed rail perimeter intrusion monitoring device and method based on millimeter wave radar and camera |
| CN114495398A (en) * | 2020-11-13 | 2022-05-13 | 北京机械设备研究所 | Intelligent protection device and protection method under outdoor unattended condition |
| CN115035697A (en) * | 2021-03-05 | 2022-09-09 | 中国电子科技集团公司第五十四研究所 | Linkage alarm device and alarm system |
| WO2023197896A1 (en) * | 2022-04-13 | 2023-10-19 | 青岛海尔空调器有限总公司 | Security monitoring method and device, and smart home device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101268383A (en) * | 2005-08-04 | 2008-09-17 | 埃森技术Enc株式会社 | Smart video monitoring system and method communicating with auto-tracking radar system |
| US20100013917A1 (en) * | 2003-08-12 | 2010-01-21 | Keith Hanna | Method and system for performing surveillance |
| CN101799968A (en) * | 2010-01-13 | 2010-08-11 | 任芳 | Detection method and device for oil well intrusion based on video image intelligent analysis |
| CN102254396A (en) * | 2011-07-06 | 2011-11-23 | 北京国铁华晨通信信息技术有限公司 | Intrusion detection method and device based on video |
| CN103366483A (en) * | 2013-06-27 | 2013-10-23 | 深圳市智美达科技有限公司 | Monitoring alarm system |
-
2015
- 2015-04-30 CN CN201510215440.3A patent/CN104821056B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100013917A1 (en) * | 2003-08-12 | 2010-01-21 | Keith Hanna | Method and system for performing surveillance |
| CN101268383A (en) * | 2005-08-04 | 2008-09-17 | 埃森技术Enc株式会社 | Smart video monitoring system and method communicating with auto-tracking radar system |
| CN101799968A (en) * | 2010-01-13 | 2010-08-11 | 任芳 | Detection method and device for oil well intrusion based on video image intelligent analysis |
| CN102254396A (en) * | 2011-07-06 | 2011-11-23 | 北京国铁华晨通信信息技术有限公司 | Intrusion detection method and device based on video |
| CN103366483A (en) * | 2013-06-27 | 2013-10-23 | 深圳市智美达科技有限公司 | Monitoring alarm system |
Non-Patent Citations (2)
| Title |
|---|
| 林鸿生等: "三维成像激光雷达图像与摄像机图像的融合", 《内燃机与动力装置》 * |
| 陈亦望等: "使用微多普勒信息识别伪装人体目标动作的新方法", 《解放军理工大学学报》 * |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157507A (en) * | 2016-07-08 | 2016-11-23 | 武汉三江中电科技有限责任公司 | A kind of transmission line of electricity solid preventer based on radar and video fusion |
| CN106157507B (en) * | 2016-07-08 | 2018-04-17 | 武汉三江中电科技有限责任公司 | A kind of transmission line of electricity solid protective device based on radar and video fusion |
| CN107622618A (en) * | 2016-07-15 | 2018-01-23 | 保定市天河电子技术有限公司 | A kind of transmission line of electricity protective survey apparatus and method |
| CN109643480A (en) * | 2016-07-22 | 2019-04-16 | 路晟（上海）科技有限公司 | Security system and method |
| CN106291539A (en) * | 2016-07-29 | 2017-01-04 | 山东康威通信技术股份有限公司 | A kind of phased-array radar target identification system based on location filtering algorithm and method |
| CN106291539B (en) * | 2016-07-29 | 2018-12-18 | 山东康威通信技术股份有限公司 | A kind of phased-array radar target identification system and method based on positioning filtering algorithm |
| CN107770480A (en) * | 2016-08-15 | 2018-03-06 | 保定市天河电子技术有限公司 | A kind of safety defense monitoring system and method |
| CN107770480B (en) * | 2016-08-15 | 2020-10-16 | 保定市天河电子技术有限公司 | Security monitoring system and method |
| CN106447680A (en) * | 2016-11-23 | 2017-02-22 | 湖南华诺星空电子技术有限公司 | Method for radar and vision fused target detecting and tracking in dynamic background environment |
| CN106447680B (en) * | 2016-11-23 | 2019-09-17 | 湖南华诺星空电子技术有限公司 | The object detecting and tracking method that radar is merged with vision under dynamic background environment |
| CN108152808A (en) * | 2017-11-23 | 2018-06-12 | 安徽四创电子股份有限公司 | A kind of circumference intelligent predicting method for early warning based on millimetre-wave radar |
| CN110097726A (en) * | 2018-01-30 | 2019-08-06 | 保定市天河电子技术有限公司 | A kind of prevention regional aim monitoring method and system |
| CN110097726B (en) * | 2018-01-30 | 2022-05-17 | 保定市天河电子技术有限公司 | Method and system for monitoring target in precautionary area |
| CN110126885A (en) * | 2018-02-02 | 2019-08-16 | 保定市天河电子技术有限公司 | A kind of railway circumference intrusion target monitoring method and system |
| CN110126885B (en) * | 2018-02-02 | 2022-04-22 | 保定市天河电子技术有限公司 | Railway perimeter intrusion target monitoring method and system |
| CN110658518B (en) * | 2018-06-29 | 2022-01-21 | 杭州海康威视数字技术股份有限公司 | Target intrusion detection method and device |
| CN110658518A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Target intrusion detection method and device |
| CN110873863A (en) * | 2018-08-29 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Target display method, radar system and electronic equipment |
| CN111045000A (en) * | 2018-10-11 | 2020-04-21 | 阿里巴巴集团控股有限公司 | Monitoring system and method |
| CN110171774A (en) * | 2018-12-27 | 2019-08-27 | 李芳龙 | Crane applications based on artificial intelligence (AI) technology |
| CN109982043A (en) * | 2019-04-02 | 2019-07-05 | 西安华腾微波有限责任公司 | A kind of information processing method and device of intelligent monitoring |
| CN110542899A (en) * | 2019-07-25 | 2019-12-06 | 浙江大华技术股份有限公司 | Radar measurement data processing method and device, radar system and readable storage medium |
| US11921189B2 (en) | 2019-07-25 | 2024-03-05 | Zhejiang Dahua Technology Co., Ltd. | Radar systems and methods using the same |
| CN110633625A (en) * | 2019-07-31 | 2019-12-31 | 北京木牛领航科技有限公司 | Identification method and system |
| WO2021023106A1 (en) * | 2019-08-02 | 2021-02-11 | 杭州海康威视数字技术股份有限公司 | Target recognition method and apparatus, and camera |
| CN110491060A (en) * | 2019-08-19 | 2019-11-22 | 深圳市优必选科技股份有限公司 | A kind of robot and its method for safety monitoring, device and storage medium |
| CN110865366B (en) * | 2019-10-12 | 2023-04-18 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN110865366A (en) * | 2019-10-12 | 2020-03-06 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN111200722A (en) * | 2019-12-09 | 2020-05-26 | 湖州米欧康电子科技有限公司 | Low-altitude management system and signal management method |
| CN111340864A (en) * | 2020-02-26 | 2020-06-26 | 浙江大华技术股份有限公司 | Monocular estimation-based three-dimensional scene fusion method and device |
| CN111340864B (en) * | 2020-02-26 | 2023-12-12 | 浙江大华技术股份有限公司 | Three-dimensional scene fusion method and device based on monocular estimation |
| CN111308456B (en) * | 2020-04-08 | 2023-05-23 | 加特兰微电子科技(上海)有限公司 | Target position judging method and device, millimeter wave radar and storage medium |
| CN111308456A (en) * | 2020-04-08 | 2020-06-19 | 加特兰微电子科技(上海)有限公司 | Target position judging method and device, millimeter wave radar and storage medium |
| CN111653054A (en) * | 2020-04-16 | 2020-09-11 | 国家核安保技术中心 | Physical protection system for nuclear facilities |
| CN111653054B (en) * | 2020-04-16 | 2021-11-26 | 国家核安保技术中心 | Physical protection system for nuclear facilities |
| CN112333417A (en) * | 2020-04-30 | 2021-02-05 | 深圳Tcl新技术有限公司 | Doorbell disturbance-free mode starting method and device and computer-readable storage medium |
| CN113727011A (en) * | 2020-05-26 | 2021-11-30 | 杭州海康威视数字技术股份有限公司 | Video monitoring method, image acquisition system, electronic device and storage medium |
| CN111913177A (en) * | 2020-08-11 | 2020-11-10 | 中国原子能科学研究院 | Method and device for detecting target object and storage medium |
| CN112147604A (en) * | 2020-09-08 | 2020-12-29 | 成都红云鼎科技有限公司 | Intrusion track calculation method based on radar coordinate conversion |
| CN112133050A (en) * | 2020-09-15 | 2020-12-25 | 朱新培 | Perimeter alarm device based on microwave radar and method thereof |
| CN112349055A (en) * | 2020-11-05 | 2021-02-09 | 通号通信信息集团有限公司 | Target monitoring device and method based on radar and video linkage |
| CN114495398A (en) * | 2020-11-13 | 2022-05-13 | 北京机械设备研究所 | Intelligent protection device and protection method under outdoor unattended condition |
| CN112565863A (en) * | 2020-11-26 | 2021-03-26 | 深圳Tcl新技术有限公司 | Video playing method and device, terminal equipment and computer readable storage medium |
| CN112614290A (en) * | 2020-12-10 | 2021-04-06 | 中科蓝卓(北京)信息科技有限公司 | Radar video cooperative target detection device and method |
| CN112614290B (en) * | 2020-12-10 | 2022-08-09 | 中科蓝卓(北京)信息科技有限公司 | Radar video cooperative target detection device and method |
| CN112672047A (en) * | 2020-12-20 | 2021-04-16 | 英特睿达(山东)电子科技有限公司 | Image acquisition system and image processing method |
| CN112731385A (en) * | 2020-12-24 | 2021-04-30 | 北京木牛领航科技有限公司 | Personnel control method, device and medium based on millimeter wave radar |
| CN112866645A (en) * | 2021-01-12 | 2021-05-28 | 二连浩特赛乌素机场管理有限公司 | Anti-invasion artificial intelligence radar video monitoring system |
| CN115035697A (en) * | 2021-03-05 | 2022-09-09 | 中国电子科技集团公司第五十四研究所 | Linkage alarm device and alarm system |
| CN114419825A (en) * | 2022-03-29 | 2022-04-29 | 中国铁路设计集团有限公司 | High-speed rail perimeter intrusion monitoring device and method based on millimeter wave radar and camera |
| WO2023197896A1 (en) * | 2022-04-13 | 2023-10-19 | 青岛海尔空调器有限总公司 | Security monitoring method and device, and smart home device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104821056B (en) | 2018-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104821056A (en) | Intelligent guarding method based on radar and video integration | |
| CN113255481B (en) | Crowd state detection method based on unmanned patrol car | |
| CN105574501B (en) | A kind of stream of people's video detecting analysis system | |
| CA3094424C (en) | Safety monitoring and early-warning method for man-machine interaction behavior of underground conveyor belt operator | |
| CN105100757B (en) | Detector with integral structure | |
| CN107145851A (en) | Constructions work area dangerous matter sources intelligent identifying system | |
| CN109920185A (en) | One kind merging the mobile mesh calibration method of detection with video data based on millimetre-wave radar | |
| KR101788269B1 (en) | Method and apparatus for sensing innormal situation | |
| CN106128053A (en) | A kind of wisdom gold eyeball identification personnel stay hover alarm method and device | |
| CN103150549B (en) | A kind of road tunnel fire detection method based on the early stage motion feature of smog | |
| CN105141885A (en) | Method for video monitoring and device | |
| CN106778655B (en) | Human body skeleton-based entrance trailing entry detection method | |
| US10318817B2 (en) | Method and apparatus for surveillance | |
| CN114241298A (en) | Tower crane environment target detection method and system based on laser radar and image fusion | |
| CN106210634A (en) | A kind of wisdom gold eyeball identification personnel fall down to the ground alarm method and device | |
| CN110067274B (en) | Equipment control method and excavator | |
| CN104966062A (en) | Video monitoring method and device | |
| US20180029834A1 (en) | Monitoring of step rollers and maintenance mechanics of passenger conveyors | |
| CN106127814A (en) | A kind of wisdom gold eyeball identification gathering of people is fought alarm method and device | |
| CN106210633A (en) | Line detection alarm method and device are got in a kind of wisdom gold eyeball identification | |
| CN106210636A (en) | Wisdom gold eyeball people based on intelligent video technology and thing Activity recognition instrument | |
| CN106846297A (en) | Pedestrian's flow quantity detecting system and method based on laser radar | |
| CN114202646A (en) | Infrared image smoking detection method and system based on deep learning | |
| CN103577833A (en) | Abnormal intrusion detection method based on motion template | |
| CN107341455B (en) | Regional multi-feature detection method and detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Intelligent guarding method based on radar and video integration Effective date of registration: 20181030 Granted publication date: 20180320 Pledgee: Changsha bank Limited by Share Ltd University Town sub branch Pledgor: HUNAN NOVASKY ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: 2018430000092 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20191121 Granted publication date: 20180320 Pledgee: Changsha bank Limited by Share Ltd University Town sub branch Pledgor: HUNAN NOVASKY ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: 2018430000092 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Intelligent guarding method based on radar and video integration Effective date of registration: 20191209 Granted publication date: 20180320 Pledgee: Changsha bank Limited by Share Ltd. Xiangjiang New District sub branch Pledgor: HUNAN NOVASKY ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: Y2019980000927 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20201224 Granted publication date: 20180320 Pledgee: Changsha bank Limited by Share Ltd. Xiangjiang New District sub branch Pledgor: HUNAN NOVASKY ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: Y2019980000927 |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Building B7, Lugu Enterprise Plaza, No. 27 Wenxuan Road, High tech Development Zone, Changsha City, Hunan Province, 410221 Patentee after: Huanuo Xingkong Technology Co.,Ltd. Address before: Building B7, Lugu Enterprise Plaza, No. 27 Wenxuan Road, High tech Development Zone, Changsha City, Hunan Province, 410221 Patentee before: Hunan Huanuo Xingkong Electronic Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Building B7, Lugu Enterprise Plaza, No. 27 Wenxuan Road, High tech Development Zone, Changsha City, Hunan Province, 410221 Patentee after: Hunan Huanuo Xingkong Electronic Technology Co.,Ltd. Address before: 410205 building B7, Lugu Enterprise Square, 27 Wenxuan Road, national high tech Development Zone, Changsha City, Hunan Province Patentee before: HUNAN NOVASKY ELECTRONIC TECHNOLOGY Co.,Ltd. |