CN104282150A - Recognition device and system of moving target - Google Patents
Recognition device and system of moving target Download PDFInfo
- Publication number
- CN104282150A CN104282150A CN201410513251.XA CN201410513251A CN104282150A CN 104282150 A CN104282150 A CN 104282150A CN 201410513251 A CN201410513251 A CN 201410513251A CN 104282150 A CN104282150 A CN 104282150A
- Authority
- CN
- China
- Prior art keywords
- moving target
- velocity characteristic
- resemblance
- motor vehicle
- bicycle
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
Abstract
The embodiment of the invention discloses a recognition device and system of a moving target. The device comprises a monitoring image collecting unit, a moving target determining unit, an extracting unit and a recognition unit. The monitoring image collecting unit is used for collecting monitoring images of a monitoring zone according to a preset time interval. The moving target determining unit is used for determining whether the moving target exists in the monitoring images. The extracting unit is used for extracting the appearance feature and/or the speed feature of the moving target when the moving target exists in the monitoring images. The recognition unit is used for recognizing the type of the moving target according to the appearance feature and/or the speed feature of the moving target. The type of the moving target can be a motor vehicle or a non-motor vehicle or a pedestrian. According to the device and system, recognition of the motor vehicle, the non-motor vehicle and the pedestrian in a mixed lane can be achieved, and then comprehensive monitoring of the motor vehicle, the non-motor vehicle and the pedestrian in the mixed lane is achieved.
Description
Technical field
The present invention relates to technical field of intelligent traffic, particularly relate to a kind of recognition device and system of moving target.
Background technology
Along with the development of society; the raising of people's awareness of safety, in important locations such as some traffic main arteries, fastlink and crossroads, can arrange video monitoring equipment usually; to capture the vehicle of above-mentioned important location dealing and to identify, and then realize the monitoring to above-mentioned important location.Wherein, video monitoring equipment is main, is by identifying vehicle to the Car license recognition of motor vehicle, and can not identifies the bicycle and pedestrian not having car plate.
Such as, but at bicycle and the more Special section of pedestrian, the gateway etc. of the combination area of city and country and community, often has some mixed runways, allow motor vehicle, bicycle and pedestrian to pass through simultaneously.Ensure the safety of these Special section, just need monitor motor vehicle, bicycle and pedestrian comprehensively.
As previously mentioned, existing video monitoring equipment can only realize the monitoring to motor vehicle, and cannot realize monitoring bicycle and pedestrian.Therefore need a kind of recognition device and system of moving target badly, to realize the identification to motor vehicle in mixed runway, bicycle and pedestrian, and then realize the overall monitor to motor vehicle in mixed runway, bicycle and pedestrian.
Summary of the invention
Provide a kind of recognition device and system of moving target in the embodiment of the present invention, to realize the identification to motor vehicle in mixed runway, bicycle and pedestrian, and then realize the overall monitor to motor vehicle in mixed runway, bicycle and pedestrian.
In order to solve the problems of the technologies described above, the embodiment of the invention discloses following technical scheme:
First aspect, provides a kind of recognition device of moving target, comprising:
Monitoring image collecting unit, for according to prefixed time interval, the monitoring image in acquisition monitoring region;
Moving target determining unit, for determining whether there is moving target in monitoring image;
Extraction unit, for when there is moving target in monitoring image, extracts resemblance and/or the velocity characteristic of moving target;
Recognition unit, for according to the resemblance of moving target and/or velocity characteristic, identifies the type of moving target; The type of moving target comprises motor vehicle, bicycle and pedestrian.
In conjunction with first aspect, in the first possible implementation of first aspect, described recognition unit comprises:
First form fit subelement, for matching the resemblance of the resemblance of moving target with the motor vehicle prestored;
First motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
First Speed coupling subelement, for when it fails to match for the resemblance of moving target and the resemblance of motor vehicle that prestores, matches with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively by the velocity characteristic of moving target;
First bicycle recognin unit, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
First pedestrian's recognin unit, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian.
In conjunction with first aspect, in the implementation that first aspect the second is possible, described recognition unit comprises:
Second speed coupling subelement, for matching the velocity characteristic of moving target with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
Second bicycle recognin unit, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
Second pedestrian's recognin unit, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian;
Second form fit subelement, for when all it fails to match for the velocity characteristic of velocity characteristic and the velocity characteristic of bicycle prestored of moving target and pedestrian, matches the resemblance of the resemblance of moving target with the motor vehicle prestored;
Second motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle.
In conjunction with first aspect, in the third possible implementation of first aspect, described recognition unit comprises:
3rd form fit subelement, for matching the resemblance of moving target with the resemblance of the resemblance of the motor vehicle prestored, the resemblance of bicycle and pedestrian respectively;
3rd motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
3rd bicycle recognin unit, for when the match is successful with the resemblance of bicycle prestored for the resemblance of moving target, identifies that the type of moving target is bicycle;
The third line people recognin unit, for when the match is successful with the resemblance of pedestrian prestored for the resemblance of moving target, identifies that the type of moving target is pedestrian.
In conjunction with first aspect, in first aspect the 4th kind of possible implementation, described recognition unit comprises:
4th speeds match subelement, for matching the velocity characteristic of moving target with the velocity characteristic of the velocity characteristic of the motor vehicle prestored, the velocity characteristic of bicycle and pedestrian respectively;
4th motor vehicle recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and motor vehicle, identifies that the type of moving target is motor vehicle;
4th bicycle recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and bicycle, identifies that the type of moving target is bicycle;
Fourth line people recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and pedestrian, identifies that the type of moving target is pedestrian.
In conjunction with first aspect, in first aspect the 5th kind of possible implementation, described moving target determining unit comprises:
Whether the first detection sub-unit, for existing pre-set image feature in test and monitoring image;
First determines subelement, for when there is pre-set image feature, determines to there is moving target in monitoring image.
In conjunction with first aspect, in first aspect the 6th kind of possible implementation, described moving target determining unit comprises:
Second detection sub-unit, whether the background area for the M width monitoring image detecting continuous acquisition changes, described M be more than or equal to 2 integer;
Second determines subelement, for when a change, determines to there is moving target in monitoring image.
In conjunction with first aspect, in the 7th kind of possibility implementation of first aspect, after the type of described identification moving target, also comprise:
Extraction unit, for extracting identification information from the moving target identified;
Suspicion matching unit, for by identification information and the suspected vehicles information that prestores or suspect's information match;
Alarm unit, for when the match is successful, sends warning message.
In conjunction with first aspect, in the 8th kind of possibility implementation of first aspect, before the monitoring image in described acquisition monitoring region, also comprise:
Optical detecting unit, whether the light intensity for test and monitoring region reaches default light intensity;
Light filling unit, for when not reaching default light intensity, carries out light filling to guarded region.
Second aspect, provides a kind of recognition system of moving target, comprises the recognition device of terminal server and moving target;
The recognition device of described moving target, for identifying the moving target of guarded region, and is sent to described terminal server by identified moving target;
Described terminal server, for storing described moving target by the classification of motor vehicle, bicycle and pedestrian.
Beneficial effect of the present invention comprises: first monitoring image collecting unit, can according to the time interval of presetting, the monitoring image in acquisition monitoring region; Secondly, moving target determining unit, can determine whether there is moving target in gathered monitoring image; Again, extraction unit, can work as in monitoring image when there is moving target, extracts resemblance and/or the velocity characteristic of moving target; Finally, recognition unit, according to the resemblance of extracted moving target and/or velocity characteristic, can identify that the type of moving target is motor vehicle, bicycle or pedestrian; Therefore visible, adopt Apparatus and system of the present invention, the identification to motor vehicle in mixed runway, bicycle and pedestrian can be realized, and then achieve the overall monitor to motor vehicle, bicycle and pedestrian.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, for those of ordinary skills, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
One structural representation of the recognition device of the moving target that Fig. 1 provides for the embodiment of the present invention;
Another structural representation of the recognition device of the moving target that Fig. 2 provides for the embodiment of the present invention;
The another structural representation of the recognition device of the moving target that Fig. 3 provides for the embodiment of the present invention;
Another structural representation of the recognition device of the moving target that Fig. 4 provides for the embodiment of the present invention;
The another structural representation of the recognition device of the moving target that Fig. 5 provides for the embodiment of the present invention;
Another structural representation of the recognition device of the moving target that Fig. 6 provides for the embodiment of the present invention;
The another structural representation of the recognition device of the moving target that Fig. 7 provides for the embodiment of the present invention;
Another structural representation of the recognition device of the moving target that Fig. 8 provides for the embodiment of the present invention;
The another structural representation of the recognition device of the moving target that Fig. 9 provides for the embodiment of the present invention;
One schematic flow sheet of the recognition methods of the moving target that Figure 10 provides for the embodiment of the present invention;
One schematic flow sheet of the recognition methods of the moving target that Figure 11 provides for the embodiment of the present invention;
Another schematic flow sheet of the recognition methods of the moving target that Figure 12 provides for the embodiment of the present invention;
The another schematic flow sheet of the recognition methods of the moving target that Figure 13 provides for the embodiment of the present invention;
Another schematic flow sheet of the recognition methods of the moving target that Figure 14 provides for the embodiment of the present invention;
The another schematic flow sheet of the recognition methods of the moving target that Figure 15 provides for the embodiment of the present invention;
Another schematic flow sheet of the recognition methods of the moving target that Figure 16 provides for the embodiment of the present invention;
The another schematic flow sheet of the recognition methods of the moving target that Figure 17 provides for the embodiment of the present invention;
Another schematic flow sheet of the recognition methods of the moving target that Figure 18 provides for the embodiment of the present invention;
Another structural representation of the recognition device of the moving target that Figure 19 provides for the embodiment of the present invention.
Embodiment
Embodiments provide a kind of recognition device of moving target, as shown in Figure 1, at least comprise: monitoring image collecting unit 11, moving target determining unit 12, extraction unit 13 and recognition unit 14, wherein:
Monitoring image collecting unit 11, for according to preset the time interval, the monitoring image in acquisition monitoring region;
In embodiments of the present invention, monitoring image collecting unit 11 can be camera or video frequency pick-up head.
And when monitoring image collecting unit 11 is video frequency pick-up head, the monitor video in the continuable acquisition monitoring region of video frequency pick-up head; Then according to the time interval of presetting, from monitor video, monitoring image is obtained.The form of monitoring image can be specially the forms such as BMP, JPEG and GIF.
In actual applications, for traffic control department, monitoring image collecting unit 11 can be the monitoring probe or CCTV camera that are arranged on mixed runway, direct acquisition monitoring image; For private area such as gateway, community and parking lots, also independent monitoring probe or CCTV camera need be set on road side.When arranging separately monitoring probe or CCTV camera, setting angle and the direction of monitoring probe or CCTV camera need be regulated, whole guarded region can be photographed to make monitoring probe or CCTV camera.
Consider that moving target is at the travelling speed of guarded region and the needs of velocity characteristic extracting moving target, if not interval Preset Time acquisition monitoring image, just there will be the monitoring image that a large amount of content repeats, take a large amount of internal memory, reduce the speed identifying moving target type.
When acquisition monitoring image, default time interval user can according to selection sets itself, certainly, in other embodiments, also can profit set with the following methods, such as: the actual range obtaining guarded region, as 100m, and in guarded region, the speed of moving target, as 2m/s, finally in conjunction with the quantity of the minimum required monitoring image of type of identifiable design moving target, as 5, the time interval of so presetting can be set to 100m/ (2m/s*5)=10s.
Moving target determining unit 12, for determining whether there is moving target in monitoring image;
In embodiments of the present invention, the function of moving target determining unit 12 can specifically be realized by image processor; And image processor can specifically be arranged in monitoring probe or CCTV camera.
In actual applications, in some time period in some prison territory, exploratory area, such as in the commuter time section of gateway, community, may seldom have moving target to occur, so this just causes in gathered monitoring image and may not have moving target.And to not having the monitoring image of moving target analyze and identify, without any meaning.Therefore, before moving target is identified, first need determine whether there is moving target in monitoring image.
In embodiments of the present invention, according to the change of background region of a series of monitoring images of continuous acquisition, can determine whether there is moving target in monitoring image.Such as: the background of a frame monitoring image of continuous acquisition can be compared, if the background of monitoring image changes, think to there is moving target in monitoring image.
In other embodiments of the present invention, also according to the characteristic information of moving target, can determine whether there is moving target in monitoring image; And when in monitoring image during existing characteristics information, can think to there is moving target in monitoring image.And the characteristic information of dissimilar moving target is also not quite similar, the characteristic information of such as motor vehicle can be the car light of motor vehicle, front face air inlet grid, the tailstock and car bonnet etc., and the characteristic information of bicycle can be the car shape of bicycle, vehicle seat, handlebar and rear vehicle seat etc., the characteristic information of pedestrian then can be face, arms and legs etc.In actual applications, user can sets itself customizing messages according to demand, does not repeat them here.
Extraction unit 13, for when there is moving target in monitoring image, extracts resemblance and/or the velocity characteristic of moving target;
In embodiments of the present invention, the function of extraction unit 13 also can specifically be realized by image processor; And image processor can specifically be arranged in monitoring probe or CCTV camera.
When determining moving target, needing the position of further setting movement target, extracting the profile of moving target, as the resemblance of moving target.
Utilize the monitoring image of continuous acquisition, obtain the displacement of moving target reality, and the time of mobile above-mentioned distance; Utilize the above-mentioned Distance geometry time, calculate the speed of moving target, as the velocity characteristic of moving target.In embodiments of the present invention, the velocity characteristic calculating moving target with the following method can be adopted: suppose that monitoring image collecting unit 11 is in time t, collect N width monitoring image, certainly, in N width monitoring image, all there is moving target; According to the movement locus of moving target in N width monitoring image, calculate the actual motion distance s of moving target, finally according to formula V=s/t, calculate the velocity characteristic of moving target.
Recognition unit 14, for according to the resemblance of moving target and/or velocity characteristic, identifies the type of moving target; The type of moving target comprises motor vehicle, bicycle and pedestrian.
In embodiments of the present invention, the function of recognition unit 14 also can specifically be realized by image processor; And image processor can specifically be arranged in monitoring probe or CCTV camera.
Therefore in embodiments of the present invention, first monitoring image collecting unit 11, can according to the time interval of presetting, the monitoring image in acquisition monitoring region; Secondly, moving target determining unit 12, can determine whether there is moving target in gathered monitoring image; Again, extraction unit 13, can work as in monitoring image when there is moving target, extracts resemblance and/or the velocity characteristic of moving target; Finally, recognition unit 14, according to the resemblance of extracted moving target and/or velocity characteristic, can identify that the type of moving target is motor vehicle, bicycle or pedestrian; Therefore visible, adopt Apparatus and system of the present invention, the identification to motor vehicle in mixed runway, bicycle and pedestrian can be realized, and then achieve the overall monitor to motor vehicle, bicycle and pedestrian.
It should be noted that, bicycle of the present invention espespecially electric motor car and automatic vehicle etc.And before extraction unit 13 of the present invention works, can first utilize the car plate of license plate retrieving unit to moving target to extract; As in moving target can extracting directly to car plate, be then motor vehicle by moving target Direct Recognition.As do not extracted car plate, recycling extraction unit 13 extracts resemblance and/or the velocity characteristic of moving target further.
In another possible embodiments of the present invention, as shown in Figure 2, the recognition unit 13 in above-mentioned all embodiments can comprise:
First form fit subelement 21, for matching the resemblance of the resemblance of moving target with the motor vehicle prestored;
As previously mentioned, the resemblance of moving target can be specially the profile of moving target, and in the built-in storage unit that the resemblance of motor vehicle can be stored in advance in monitoring probe or CCTV camera or DOC.
Consider, moving target distance is different according to the distance of machine machine or camera lens, by different for the large young pathbreaker of the moving target caused in captured monitoring image.In actual applications, first the resemblance of stored motor vehicle can be carried out convergent-divergent, be scaled consistent with the resemblance of moving target after, then to mate;
First motor vehicle recognin unit 22, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
When the resemblance of moving target is greater than default similarity with the similarity of the resemblance of the motor vehicle prestored, can think that the match is successful, identify that the type of moving target is motor vehicle; And when similarity is less than or equal to default similarity, namely think that coupling is unsuccessful.The size user presetting Similarity value can sets itself as required.
First Speed coupling subelement 23, for matching the velocity characteristic of moving target with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
In embodiments of the present invention, in the velocity characteristic of bicycle and the velocity characteristic of the pedestrian built-in storage unit that can be stored in advance in monitoring probe or CCTV camera or DOC.
The velocity characteristic user of bicycle can sets itself as required, also can carry out statistical study to the travelling speed of a large amount of bicycle, obtain the velocity characteristic of bicycle.And the velocity characteristic of bicycle can be a concrete numerical value, also can be a value range.Equally, the velocity characteristic of pedestrian also can user's sets itself as required, also user can carry out statistical study to the velocity characteristic of a large amount of pedestrian, obtain the velocity characteristic of pedestrian.And the velocity characteristic of pedestrian can be a concrete numerical value equally, also can be a value range.And no matter the velocity characteristic of pedestrian is a concrete numerical value, be still a value range, the size of its numerical value is all less than the concrete numerical value of the velocity characteristic of bicycle.
First bicycle recognin unit 24, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
When the velocity characteristic of bicycle is a concrete numerical value, when the velocity characteristic of moving target is less than predetermined deviation value with the deviation of the velocity characteristic of the bicycle prestored, namely think that the match is successful; Otherwise think that coupling is unsuccessful.
And when the velocity characteristic of bicycle is a value range, when the velocity characteristic of moving target is positioned at the scope of the velocity characteristic of the bicycle prestored, namely think that the match is successful; Otherwise think that coupling is unsuccessful.
First pedestrian's recognin unit 25, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian.
Equally, when the velocity characteristic of pedestrian is a concrete numerical value, when the velocity characteristic of moving target is less than predetermined deviation value with the deviation of the velocity characteristic of the pedestrian prestored, namely think that the match is successful; Otherwise think that coupling is unsuccessful.
And when the velocity characteristic of pedestrian is a value range, when the velocity characteristic of pedestrian is positioned at the scope of the velocity characteristic of the pedestrian prestored, namely think that the match is successful; Otherwise think that coupling is unsuccessful.
In actual applications, consider that the resemblance of non-motor-car is obviously different from bicycle and pedestrian, and due to reasons such as shooting angle, the resemblance of bicycle and pedestrian is not easily distinguishable sometimes; Therefore, in embodiments of the present invention, adopt the resemblance of bicycle to identify bicycle, and adopt velocity characteristic to distinguish bicycle and pedestrian.Therefore adopt method of the present invention, adopt the former monitoring probe that arranged or CCTV camera to realize, without the need to additional configuration hardware, and method is simple, easy.Meanwhile, due to the present embodiment, first adopt resemblance to carry out cognitron motor-car, then adopt velocity characteristic to identify bicycle and pedestrian, method described in visible the present embodiment, is applicable to motor vehicle more, and bicycle and the less guarded region of pedestrian.
In another possible embodiments of the present invention, as shown in figure 19, the recognition unit 13 in above-mentioned all embodiments can comprise:
Second speed coupling subelement 191, for matching the velocity characteristic of moving target with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
Second bicycle recognin unit 192, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
Second pedestrian's recognin unit 193, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian;
Second form fit subelement 194, for when all it fails to match for the velocity characteristic of velocity characteristic and the velocity characteristic of bicycle prestored of moving target and pedestrian, matches the resemblance of the resemblance of moving target with the motor vehicle prestored;
Second motor vehicle recognin unit 195, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle.
Therefore, in an embodiment of the present invention, first utilize the velocity characteristic of moving target to identify bicycle and pedestrian; If all unidentified success, then adopt resemblance to identify that whether it is for motor vehicle; Therefore said method, is applicable to pedestrian and non motorized vehicle all many, and the guarded region that motor vehicle is less.
In another possible embodiments of the present invention, as shown in Figure 3, the recognition unit 13 in above-mentioned all embodiments can comprise:
3rd form fit subelement 31, for matching the resemblance of moving target with the resemblance of the resemblance of the motor vehicle prestored, the resemblance of bicycle and pedestrian respectively;
3rd motor vehicle recognin unit 32, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
3rd bicycle recognin unit 33, for when the match is successful with the resemblance of bicycle prestored for the resemblance of moving target, identifies that the type of moving target is bicycle;
The third line people recognin unit 34, for when the match is successful with the resemblance of pedestrian prestored for the resemblance of moving target, identifies that the type of moving target is pedestrian.
Consider in actual applications, likely difference is less for the speed of bicycle and the speed of pedestrian, such as, under this extreme case that the speed of bicycle speed that is extremely slow and pedestrian is exceedingly fast; Now according to the method in the embodiment of the present invention, adopt resemblance to distinguish motor vehicle, bicycle and pedestrian, then greatly can reduce the probability by mistake identified.
In another possible embodiments of the present invention, as shown in Figure 4, the recognition unit 13 in above-mentioned all embodiments can comprise:
4th speeds match subelement 42, for matching the velocity characteristic of moving target with the velocity characteristic of the velocity characteristic of the motor vehicle prestored, the velocity characteristic of bicycle and pedestrian respectively;
4th motor vehicle recognin unit 43, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and motor vehicle, identifies that the type of moving target is motor vehicle;
4th bicycle recognin unit 44, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and bicycle, identifies that the type of moving target is bicycle;
Fourth line people recognin unit 45, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and pedestrian, identifies that the type of moving target is pedestrian.
Consider in practical application, due to the reason such as shooting angle of monitoring image, adopt the resemblance of moving target can not accurately distinguish bicycle and pedestrian, and adopt the device in the embodiment of the present invention, adopt velocity characteristic to identify that moving target is bicycle, motor vehicle or pedestrian, then can reduce the probability by mistake identified in the case.
In another possible embodiments of the present invention, as shown in Figure 5, the moving target determining unit 12 in above-mentioned all embodiments can comprise:
Whether the first detection sub-unit 51, for existing pre-set image feature in test and monitoring image;
In embodiments of the present invention, pre-set image feature can be the feature easy to identify of various types of moving target, the car light of such as motor vehicle, front face air inlet grid, the tailstock and car bonnet etc., the car shape of bicycle, vehicle seat, handlebar and rear vehicle seat etc., the face, arms and legs etc. of pedestrian.In actual applications, user can sets itself pre-set image feature, also by great many of experiments, obtains the feature easy to identify of various types of moving target, as pre-set image feature.
First determines subelement 52, for when there is pre-set image feature, determines to there is moving target in monitoring image.
In embodiments of the present invention, can work as and detect in monitoring image when there is any one pre-set image feature, namely determine to there is moving target in monitoring image; Such as, when can work as car light motor vehicle being detected, namely determine to there is moving target in monitoring image; Also can work as and detect in monitoring image when there is at least two kinds of pre-set image features, just determine to there is moving target in monitoring image; Such as, car light and front face air inlet grid that motor vehicle detected can be worked as simultaneously, just determine to there is moving target in monitoring image, and the arbitrary characteristic information in car light and front face air inlet grid detected, namely think to there is not moving target in monitoring image, like this, can avoid owing to detecting mistake, the misinterpretation caused.
Adopt method described in the present embodiment, mainly considering, there is not moving target in the monitoring image gathered in some period, if now, still identifies monitoring image, and this occupies the processing time of processor undoubtedly, reduces the speed identifying moving target.
In another possible embodiments of the present invention, as shown in Figure 6, the moving target determining unit 12 in above-mentioned all embodiments can comprise:
Second detection sub-unit 61, whether the background area for the M width monitoring image detecting continuous acquisition changes, M be more than or equal to 2 integer;
Second determines subelement 62, for when a change, determines whether there is moving target in monitoring image.
If consider, guarded region has moving target moving, and so the background area of the monitoring image of continuous acquisition is bound to change.Therefore, when the background area of monitoring image changes, can determine to there is moving target in monitoring image.
In another possible embodiments of the present invention, as shown in Figure 7, the device in above-mentioned all embodiments, after the type identifying moving target, also can comprise:
Extraction unit 71, for extracting identification information from the moving target identified;
In embodiments of the present invention, identification information can be the feature easy to identify of different types of movement target; Such as, the identification information of the moving target of motor vehicle type can be the car mark of motor vehicle, vehicle color, vehicle and the number-plate number etc.; The identification information of the moving target of pedestrian's classification can be the height, face etc. of pedestrian; The identification information of the moving target of bicycle classification can be the vehicle and color etc. of bicycle.
Suspicion matching unit 72, for by the identification information of extraction and the suspected vehicles information that prestores or suspect's information match;
In embodiments of the present invention, can by the identification information that extracts from motor vehicle or bicycle and suspected vehicles information match, such as: the identification information number-plate number of motor vehicle and the number-plate number of suspected vehicles are matched, if the match is successful, then think to there is suspected vehicles in moving target.
By the identification information that extracts from pedestrian and suspect's information match.Such as: mated with the face of suspect by the identification information face of pedestrian, if matched, then think to there is suspect in moving target;
Alarm unit 73, for when the match is successful, sends warning message;
In embodiments of the present invention, when the match is successful, can alarm sound be sent and show suspicion moving target as warning message, to remind traffic-police or other staff.In other embodiments of the present invention, when also can work as that the match is successful, suspect and/or the identification information of suspected vehicles and the particular location of guarded region etc. are sent to the server in police office as warning message, to notify that police personnel exists suspect and/or suspected vehicles herein.
Therefore, adopt said apparatus of the present invention, can realize automatically detecting suspected vehicles and suspicion personnel, and when suspected vehicles and suspect being detected, also automatically can send warning message.
In another possible embodiments of the present invention, as shown in Figure 8, the device in above-mentioned all embodiments, also can comprise:
Optical detecting unit 81, whether the light intensity for test and monitoring region reaches default light intensity;
Light filling unit 82, for when not reaching default light intensity, carries out light filling to guarded region.
The function of light filling unit can specifically be realized by arbitrary in light compensating lamp, flashlamp, jointly can be realized by light compensating lamp and flashlamp.
Consider that, when night or extraneous insufficient light, captured monitoring image may not be high-visible, thus cause and can not identify moving target.Therefore, before shooting monitoring image, the light intensity in test and monitoring region; And when the light intensity of guarded region is not enough, light filling is carried out to guarded region, thus guarantees that captured monitoring image is high-visible, and then accurately identify moving target.
The invention also discloses a kind of recognition system of moving target, as shown in Figure 9, recognition device 91 and the terminal server 92 of the moving target in above-mentioned all embodiments can be comprised;
Wherein, the recognition device 91 of moving target, for identifying the moving target of guarded region, and is sent to terminal server 92 by the moving target of identification;
Terminal server 92, for pressing the classification storing moving target of motor vehicle, bicycle and pedestrian.
Concrete, the identification information of the moving target of extraction can be sent to terminal server by the recognition device 91 of moving target; Accordingly, terminal server 92 can the identification information of storing moving target.
Consider, due to need of work, traffic control department or public security department, need to check that certain period is by the motor vehicle of guarded region, bicycle and pedestrian sometimes.Adopt device of the present invention, traffic control department or public security department, only need search the moving target of required type in terminal server, and need not checking monitoring video again.Such as: whether public security officer need check is having license plate number to be that the motor vehicle of XXX is through guarded region B day, adopt system of the present invention, public security officer only only need search in the motor vehicle stored B day at terminal server 92 and carry out searching, and need not watch B day all monitoring video.Therefore, adopt device of the present invention, can increase work efficiency.
For convenience of description, various unit is divided into describe respectively with function when describing above device.Certainly, the function of each unit can be realized in same or multiple software and/or hardware when implementing of the present invention.
Apparatus and system embodiment described above is only schematic, the unit wherein illustrated as separating component or can may not be and physically separates, parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The invention also discloses a kind of recognition methods of moving target, as shown in Figure 10, at least comprise the following steps:
Step S101: according to prefixed time interval, the monitoring image in acquisition monitoring region;
Step S102: determine whether there is moving target in monitoring image;
Step S103: when there is moving target in monitoring image, extracts resemblance and/or the velocity characteristic of moving target;
Step S104: according to resemblance and/or the velocity characteristic of moving target, identifies the type that fortune target is known; The type of moving target comprises motor vehicle, bicycle and pedestrian.
Therefore, in embodiments of the present invention, first can according to the time interval of presetting, the monitoring image in acquisition monitoring region; Secondly can determine whether there is moving target in gathered monitoring image; Again, can work as in monitoring image when there is moving target, extract resemblance and/or the velocity characteristic of moving target; Finally, according to the resemblance of extracted moving target and/or velocity characteristic, can identify that the type of moving target is motor vehicle, bicycle or pedestrian; Therefore visible, adopt method of the present invention, the identification to motor vehicle in mixed runway, bicycle and pedestrian can be realized, and then achieve the overall monitor to motor vehicle, bicycle and pedestrian.
In another embodiment of the present invention, as shown in figure 11, the step S104 in above-mentioned all embodiments can comprise:
Step S111: the resemblance of the resemblance of moving target with the motor vehicle prestored is matched; When the match is successful, enter step S112; Otherwise enter step S113;
Step S112: the type of identification moving target is motor vehicle;
Step S113: the velocity characteristic of moving target is matched with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
Step S114: when the match is successful for velocity characteristic and the velocity characteristic of bicycle prestored of moving target, identify that the type of moving target is bicycle;
Step S115: when the match is successful for velocity characteristic and the velocity characteristic of pedestrian prestored of moving target, identify that the type of moving target is pedestrian.
In another embodiment of the invention, as shown in figure 12, the step S104 in above-mentioned all embodiments can at least comprise:
Step S122: the velocity characteristic of moving target is matched with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
Step S123: when the match is successful for velocity characteristic and the velocity characteristic of bicycle prestored of moving target, identify that the type of moving target is bicycle;
Step S124: when the match is successful for velocity characteristic and the velocity characteristic of pedestrian prestored of moving target, identify that the type of moving target is pedestrian;
Step S125: when all it fails to match for the velocity characteristic of velocity characteristic and the velocity characteristic of bicycle prestored of moving target and pedestrian, the resemblance of the resemblance of moving target with the motor vehicle prestored is matched;
Step S126: when the match is successful for resemblance and the resemblance of motor vehicle prestored of moving target, identify that the type of moving target is motor vehicle.
In another embodiment of the present invention, as shown in figure 13, the step S104 in above-mentioned all embodiments can at least comprise:
Step S131: the resemblance of moving target is matched with the resemblance of the resemblance of the motor vehicle prestored, the resemblance of bicycle and pedestrian respectively;
Step S132: when the match is successful for resemblance and the resemblance of motor vehicle prestored of moving target, identify that the type of moving target is motor vehicle;
Step S133: when the match is successful for resemblance and the resemblance of bicycle prestored of moving target, identify that the type of moving target is bicycle;
Step S134: when the match is successful for resemblance and the resemblance of pedestrian prestored of moving target, identify that the type of moving target is pedestrian.
In another embodiment of the invention, as shown in figure 14, the step S104 in above-mentioned all embodiments can at least comprise:
Step S141: the velocity characteristic of moving target is matched with the velocity characteristic of the velocity characteristic of the motor vehicle prestored, the velocity characteristic of bicycle and pedestrian respectively;
Step S142: when the match is successful for the velocity characteristic of the velocity characteristic of moving target and motor vehicle, identify that the type of moving target is motor vehicle;
Step S143: when the match is successful for the velocity characteristic of the velocity characteristic of moving target and bicycle, identify that the type of moving target is bicycle;
Step S144: when the match is successful for the velocity characteristic of the velocity characteristic of moving target and pedestrian, identify that the type of moving target is pedestrian.
In another possible embodiments of the present invention, as shown in figure 15, the step S102 in above-mentioned all embodiments can comprise:
Step S151: whether there is pre-set image feature in test and monitoring image;
Step S152: when there is pre-set image feature, determines to there is moving target in monitoring image.
In another possible embodiments of the present invention, as shown in figure 16, the step S102 in above-mentioned all embodiments can comprise:
Step S161: whether the background area of M width monitoring image detecting continuous acquisition changes, M be more than or equal to 2 integer; ;
Step S162: when a change, determines to there is moving target in monitoring image.
In another possible embodiments of the present invention, as shown in figure 17, after the step S103 in above-mentioned all embodiments, also can comprise:
Step S171: extract identification information from the moving target identified;
Step S172: by identification information and the suspected vehicles information prestored or suspect's information match;
Step S173: when the match is successful, sends warning message.
In another possible embodiments of the present invention, as shown in figure 18, before the step S101 in above-mentioned all embodiments, also can comprise:
Step S181: whether the light intensity in test and monitoring region reaches default light intensity;
Step S182: when not reaching default light intensity, carries out light filling to guarded region.
The above is only the specific embodiment of the present invention, those skilled in the art is understood or realizes the present invention.To be apparent to one skilled in the art to the multiple amendment of these embodiments, General Principle as defined herein can without departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention can not be restricted to these embodiments shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (10)
1. a recognition device for moving target, is characterized in that, comprising:
Monitoring image collecting unit, for according to prefixed time interval, the monitoring image in acquisition monitoring region;
Moving target determining unit, for determining whether there is moving target in monitoring image;
Extraction unit, for when there is moving target in monitoring image, extracts resemblance and/or the velocity characteristic of moving target;
Recognition unit, for according to the resemblance of moving target and/or velocity characteristic, identifies the type of moving target; The type of moving target comprises motor vehicle, bicycle and pedestrian.
2. device according to claim 1, is characterized in that, described recognition unit comprises:
First form fit subelement, for matching the resemblance of the resemblance of moving target with the motor vehicle prestored;
First motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
First Speed coupling subelement, for when it fails to match for the resemblance of moving target and the resemblance of motor vehicle that prestores, matches with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively by the velocity characteristic of moving target;
First bicycle recognin unit, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
First pedestrian's recognin unit, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian.
3. device according to claim 1, is characterized in that, described recognition unit comprises:
Second speed coupling subelement, for matching the velocity characteristic of moving target with the velocity characteristic of the bicycle prestored and the velocity characteristic of pedestrian respectively;
Second bicycle recognin unit, for when the match is successful with the velocity characteristic of bicycle prestored for the velocity characteristic of moving target, identifies that the type of moving target is bicycle;
Second pedestrian's recognin unit, for when the match is successful with the velocity characteristic of pedestrian prestored for the velocity characteristic of moving target, identifies that the type of moving target is pedestrian;
Second form fit subelement, for when all it fails to match for the velocity characteristic of velocity characteristic and the velocity characteristic of bicycle prestored of moving target and pedestrian, matches the resemblance of the resemblance of moving target with the motor vehicle prestored;
Second motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle.
4. device according to claim 1, is characterized in that, described recognition unit comprises:
3rd form fit subelement, for matching the resemblance of moving target with the resemblance of the resemblance of the motor vehicle prestored, the resemblance of bicycle and pedestrian respectively;
3rd motor vehicle recognin unit, for when the match is successful with the resemblance of motor vehicle prestored for the resemblance of moving target, identifies that the type of moving target is motor vehicle;
3rd bicycle recognin unit, for when the match is successful with the resemblance of bicycle prestored for the resemblance of moving target, identifies that the type of moving target is bicycle;
The third line people recognin unit, for when the match is successful with the resemblance of pedestrian prestored for the resemblance of moving target, identifies that the type of moving target is pedestrian.
5. device according to claim 1, is characterized in that, described recognition unit comprises:
4th speeds match subelement, for matching the velocity characteristic of moving target with the velocity characteristic of the velocity characteristic of the motor vehicle prestored, the velocity characteristic of bicycle and pedestrian respectively;
4th motor vehicle recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and motor vehicle, identifies that the type of moving target is motor vehicle;
4th bicycle recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and bicycle, identifies that the type of moving target is bicycle;
Fourth line people recognin unit, for when the match is successful for the velocity characteristic of the velocity characteristic of moving target and pedestrian, identifies that the type of moving target is pedestrian.
6. device according to claim 1, is characterized in that, described moving target determining unit comprises:
Whether the first detection sub-unit, for existing pre-set image feature in test and monitoring image;
First determines subelement, for when there is pre-set image feature, determines to there is moving target in monitoring image.
7. device according to claim 1, is characterized in that, described moving target determining unit comprises:
Second detection sub-unit, whether the background area for the M width monitoring image detecting continuous acquisition changes, described M be more than or equal to 2 integer;
Second determines subelement, for when a change, determines to there is moving target in monitoring image.
8. device according to claim 1, is characterized in that, after the type of described identification moving target, also comprises:
Extraction unit, for extracting identification information from the moving target identified;
Suspicion matching unit, for by identification information and the suspected vehicles information that prestores or suspect's information match;
Alarm unit, for when the match is successful, sends warning message.
9. device according to claim 1, is characterized in that, before the monitoring image in described acquisition monitoring region, also comprises:
Optical detecting unit, whether the light intensity for test and monitoring region reaches default light intensity;
Light filling unit, for when not reaching default light intensity, carries out light filling to guarded region.
10. a recognition system for moving target, is characterized in that, comprises the recognition device of terminal server and the moving target as described in any one of claim 1-9;
The recognition device of described moving target, for identifying the moving target of guarded region, and is sent to described terminal server by identified moving target;
Described terminal server, for storing described moving target by the classification of motor vehicle, bicycle and pedestrian.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410513251.XA CN104282150B (en) | 2014-09-29 | 2014-09-29 | Recognition device and system of moving target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410513251.XA CN104282150B (en) | 2014-09-29 | 2014-09-29 | Recognition device and system of moving target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104282150A true CN104282150A (en) | 2015-01-14 |
| CN104282150B CN104282150B (en) | 2017-01-11 |
Family
ID=52256992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410513251.XA Active CN104282150B (en) | 2014-09-29 | 2014-09-29 | Recognition device and system of moving target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104282150B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250862A (en) * | 2016-08-06 | 2016-12-21 | 张阳 | Type of sports recognition methods and system |
| CN107447699A (en) * | 2016-12-14 | 2017-12-08 | 北京无线电计量测试研究所 | A kind of high-adaptability cycle path intelligent gate system |
| CN107460837A (en) * | 2016-12-14 | 2017-12-12 | 北京无线电计量测试研究所 | A kind of cycle path intelligent gate system |
| CN107590486A (en) * | 2017-10-11 | 2018-01-16 | 广州杰赛科技股份有限公司 | Motion estimate method and system, bicycle flow statistical method and equipment |
| CN108256541A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | Car plate index identification method and device |
| CN108492573A (en) * | 2018-03-09 | 2018-09-04 | 姜鹏飞 | A kind of identification of non-motor vehicle, localization method and system |
| CN109040664A (en) * | 2018-06-01 | 2018-12-18 | 深圳市商汤科技有限公司 | video stream processing method and device, electronic equipment and storage medium |
| CN109151312A (en) * | 2018-09-04 | 2019-01-04 | 广州视源电子科技股份有限公司 | Focusing method, device and video presenter |
| CN109302583A (en) * | 2018-10-11 | 2019-02-01 | 福建睿思特科技股份有限公司 | Public security prevention and control system and public security preventing control method |
| CN109960961A (en) * | 2017-12-14 | 2019-07-02 | 中国电信股份有限公司 | Pedestrian recognition method and device |
| CN110147731A (en) * | 2019-04-16 | 2019-08-20 | 深圳云天励飞技术有限公司 | Vehicle type recognition method and Related product |
| CN110738858A (en) * | 2019-10-31 | 2020-01-31 | 浙江大华技术股份有限公司 | Camera image processing method, coder-decoder and storage device |
| CN112131916A (en) * | 2019-06-25 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Target snapshot method and device, electronic equipment and storage medium |
| CN112257811A (en) * | 2020-11-11 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Ship classification method and device, electronic equipment and storage medium |
| CN113077623A (en) * | 2021-03-12 | 2021-07-06 | 南通大学 | Statistical system for measuring traffic volume by categories and working method |
| CN113920706A (en) * | 2021-08-28 | 2022-01-11 | 北京工业大学 | Abnormal event prevention and control method based on image recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006018339A (en) * | 2004-06-30 | 2006-01-19 | Hitachi Ltd | License plate recognition device and method |
| CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
| CN101388145A (en) * | 2008-11-06 | 2009-03-18 | 北京汇大通业科技有限公司 | Auto alarming method and device for traffic safety |
| CN101587640A (en) * | 2008-05-20 | 2009-11-25 | 奥城同立科技开发（北京）有限公司 | Anti-glare road traffic camera system |
| CN101587641A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Detection and identification system for vehicle license plate |
| CN102592457A (en) * | 2012-02-13 | 2012-07-18 | 山东鼎讯智能交通科技有限公司 | Compound type interval velocity-measuring system based on internet of things technology and method thereof |
| US20130265423A1 (en) * | 2012-04-06 | 2013-10-10 | Xerox Corporation | Video-based detector and notifier for short-term parking violation enforcement |
-
2014
- 2014-09-29 CN CN201410513251.XA patent/CN104282150B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006018339A (en) * | 2004-06-30 | 2006-01-19 | Hitachi Ltd | License plate recognition device and method |
| CN101017573A (en) * | 2007-02-09 | 2007-08-15 | 南京大学 | Method for detecting and identifying moving target based on video monitoring |
| CN101587640A (en) * | 2008-05-20 | 2009-11-25 | 奥城同立科技开发（北京）有限公司 | Anti-glare road traffic camera system |
| CN101587641A (en) * | 2008-05-21 | 2009-11-25 | 上海新联纬讯科技发展有限公司 | Detection and identification system for vehicle license plate |
| CN101388145A (en) * | 2008-11-06 | 2009-03-18 | 北京汇大通业科技有限公司 | Auto alarming method and device for traffic safety |
| CN102592457A (en) * | 2012-02-13 | 2012-07-18 | 山东鼎讯智能交通科技有限公司 | Compound type interval velocity-measuring system based on internet of things technology and method thereof |
| US20130265423A1 (en) * | 2012-04-06 | 2013-10-10 | Xerox Corporation | Video-based detector and notifier for short-term parking violation enforcement |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250862A (en) * | 2016-08-06 | 2016-12-21 | 张阳 | Type of sports recognition methods and system |
| CN107447699A (en) * | 2016-12-14 | 2017-12-08 | 北京无线电计量测试研究所 | A kind of high-adaptability cycle path intelligent gate system |
| CN107460837A (en) * | 2016-12-14 | 2017-12-12 | 北京无线电计量测试研究所 | A kind of cycle path intelligent gate system |
| CN107447699B (en) * | 2016-12-14 | 2019-10-25 | 北京无线电计量测试研究所 | A kind of high-adaptability cycle path intelligent gate system |
| CN108256541A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | Car plate index identification method and device |
| CN108256541B (en) * | 2016-12-29 | 2021-01-12 | 杭州海康威视数字技术股份有限公司 | License plate identification recognition method and device |
| CN107590486A (en) * | 2017-10-11 | 2018-01-16 | 广州杰赛科技股份有限公司 | Motion estimate method and system, bicycle flow statistical method and equipment |
| CN107590486B (en) * | 2017-10-11 | 2020-06-19 | 广州杰赛科技股份有限公司 | Moving object identification method and system, and bicycle flow statistical method and equipment |
| CN109960961A (en) * | 2017-12-14 | 2019-07-02 | 中国电信股份有限公司 | Pedestrian recognition method and device |
| CN108492573A (en) * | 2018-03-09 | 2018-09-04 | 姜鹏飞 | A kind of identification of non-motor vehicle, localization method and system |
| CN109040664A (en) * | 2018-06-01 | 2018-12-18 | 深圳市商汤科技有限公司 | video stream processing method and device, electronic equipment and storage medium |
| CN109151312A (en) * | 2018-09-04 | 2019-01-04 | 广州视源电子科技股份有限公司 | Focusing method, device and video presenter |
| CN109302583A (en) * | 2018-10-11 | 2019-02-01 | 福建睿思特科技股份有限公司 | Public security prevention and control system and public security preventing control method |
| CN110147731A (en) * | 2019-04-16 | 2019-08-20 | 深圳云天励飞技术有限公司 | Vehicle type recognition method and Related product |
| CN112131916A (en) * | 2019-06-25 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Target snapshot method and device, electronic equipment and storage medium |
| CN110738858A (en) * | 2019-10-31 | 2020-01-31 | 浙江大华技术股份有限公司 | Camera image processing method, coder-decoder and storage device |
| CN112257811A (en) * | 2020-11-11 | 2021-01-22 | 珠海大横琴科技发展有限公司 | Ship classification method and device, electronic equipment and storage medium |
| CN112257811B (en) * | 2020-11-11 | 2022-04-19 | 珠海大横琴科技发展有限公司 | Ship classification method and device, electronic equipment and storage medium |
| CN113077623A (en) * | 2021-03-12 | 2021-07-06 | 南通大学 | Statistical system for measuring traffic volume by categories and working method |
| CN113920706A (en) * | 2021-08-28 | 2022-01-11 | 北京工业大学 | Abnormal event prevention and control method based on image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104282150B (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104282150A (en) | Recognition device and system of moving target | |
| US10713499B2 (en) | Real-time video triggering for traffic surveillance and photo enforcement applications using near infrared video acquisition | |
| US9542609B2 (en) | Automatic training of a parked vehicle detector for large deployment | |
| TWI430212B (en) | Abnormal behavior detection system and method using automatic classification of multiple features | |
| US9791766B2 (en) | Portable license plate reader, speed sensor and face recognition system | |
| KR102197946B1 (en) | object recognition and counting method using deep learning artificial intelligence technology | |
| KR101971878B1 (en) | Video surveillance system and method using deep-learning based car number recognition technology in multi-lane environment | |
| CN203346814U (en) | Dual-lane integrated community intelligent lane barrier management system based on vehicle license plate recognition technology | |
| CN202077142U (en) | Vehicle-mounted intelligent video detecting and analyzing system | |
| CN101739809A (en) | Automatic alarm and monitoring system for pedestrian running red light | |
| CN201307337Y (en) | Automatic alarming and monitoring device for traffic-lights nonobservance of pedestrian | |
| CN102496285A (en) | Method for determining red-light running of vehicles at intersection based on video detection and signal control system | |
| CN101587641A (en) | Detection and identification system for vehicle license plate | |
| CN103366565A (en) | Method and system of detecting pedestrian running red light based on Kinect | |
| US11025865B1 (en) | Contextual visual dataspaces | |
| CN202422425U (en) | Video-detection-based intelligent signal control system for crossing | |
| Shobayo et al. | Development of smart plate number recognition system for fast cars with web application | |
| CN110826356B (en) | Non-motor vehicle violation detection system, method and server | |
| CN104408931A (en) | Incomplete sign license plate identification system and method | |
| WO2017015297A1 (en) | Multi-stream based traffic enforcement for complex scenarios | |
| CN109377694B (en) | Monitoring method and system for community vehicles | |
| WO2019198076A1 (en) | Real-time raw data- and sensor fusion | |
| CN103914682A (en) | Vehicle license plate recognition method and system | |
| CN103903448A (en) | Method for traffic intersection rule breaking detection based on vehicle license plate recognition technology | |
| CN103886761B (en) | Intelligent bayonet system and the operation method thereof of road exception parking can be found fast |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100193, room 2, zone 205, international software building, building 9, Zhongguancun Software Park, Beijing, Haidian District Applicant after: BEIJING DIGITAL ZHITONG TECHNOLOGY CO., LTD. Address before: 100193, room 2, zone 205, international software building, building 9, Zhongguancun Software Park, Beijing, Haidian District Applicant before: Beijing Hanwang Intelligent Traffic Technology Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |