CN105060051A - Scene detection platform for intense fighting in elevator - Google Patents
Scene detection platform for intense fighting in elevator Download PDFInfo
- Publication number
- CN105060051A CN105060051A CN201510469000.0A CN201510469000A CN105060051A CN 105060051 A CN105060051 A CN 105060051A CN 201510469000 A CN201510469000 A CN 201510469000A CN 105060051 A CN105060051 A CN 105060051A
- Authority
- CN
- China
- Prior art keywords
- elevator
- image
- gray
- target
- subset
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 230000000007 visual effect Effects 0.000 claims abstract description 21
- 238000013075 data extraction Methods 0.000 claims abstract description 5
- 230000008859 change Effects 0.000 claims description 42
- 230000003068 static effect Effects 0.000 claims description 18
- 238000000926 separation method Methods 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 10
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 239000003795 chemical substances by application Substances 0.000 claims description 5
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 229910052742 iron Inorganic materials 0.000 claims description 3
- 230000005055 memory storage Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 239000004065 semiconductor Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000010453 quartz Substances 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910052732 germanium Inorganic materials 0.000 description 1
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical compound [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0012—Devices monitoring the users of the elevator system
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a scene detection platform for intense fighting in an elevator. The scene detection platform comprises a CMOS visual sensing device, a scene detection device and a digital signal processor. The CMOS visual sensing device is used for shooting an elevator car to obtain an elevator car image. The scene detection device is connected with the CMOS visual sensing device and used for carrying out scene data extraction on the elevator car image. The digital signal processor is connected with the scene detection device and used for determining whether intense fighting scene alarming is carried out or not based on extracted scene data. By means of the scene detection platform, the scene of intense fighting in the elevator can be automatically detected in a targeted manner.
Description
Technical field
The present invention relates to wireless communication field, particularly relate to fierce fight scene detection platform in a kind of elevator.
Background technology
Urbanization is the development tendency of our times various countries, especially developing country, and along with the more lid of building is higher, the use of elevator is also day by day universal.
But, elevator its space that is in operation is hedged off from the outer world, close, improve to lawless person in narrow space the opportunity of violent crime at elevator, although there is the technical scheme that some are monitored elevator interior space video in prior art, but these technical schemes all need monitor staff's visual inspection monitor video, manually carry out the judgement of act of violence, and cannot accurately judge each Violent scene in prior art, thus different counter-measures cannot correspondingly be taked, such as, the scene of fierce fight between human body in elevator cannot be judged.
Therefore, need the detection scheme of the concrete Violent scene of a kind of new lift space, not only Violent scene can be detected in time, exactly, and can judge that the type of Violent scene is fierce fight between human body, be the information reference that associated monitoring department takes corresponding counter-measure to provide important.
Summary of the invention
In order to solve the problem, the invention provides fierce scene detection platform of wrestling in a kind of elevator that can organically combine with elevator agent structure, by comprising, background gray threshold is determined, the high-precision image processing of target identification mechanism, adopt the pattern identifying target after first accurately peeling off background, improve the accuracy that human body target detects, meanwhile, the analytical model of target solid can identify Violent scene concrete in elevator targetedly: fierce fight scene.
According to an aspect of the present invention, provide fierce fight scene detection platform in a kind of elevator, comprise CMOS visual sensing equipment, scene detection equipment and digital signal processor, described CMOS visual sensing equipment is used for taking to obtain lift car image to lift car, described scene detection equipment and described CMOS visual sensing equipment connection, extract for performing contextual data to described lift car image, described digital signal processor and described scene detection equipment connection, for determining whether that based on the contextual data extracted performing fierce fight scene reports to the police.
More specifically, in described elevator in fierce fight scene detection platform, also comprise: elevator agent structure, by elevator car body equipment, machine room control convenience, hoistway control convenience and stop control convenience composition, described elevator car body equipment comprises hoistway sensor, door opener, emergency terminal switch, lead boots, panel block in sedan-chair, sedan-chair frame, gate, safety tongs, trailing cable and car, described hoistway sensor, described door opener, described emergency terminal switch and describedly lead the top that boots are all arranged on described car, in described sedan-chair, panel block is arranged on the inside of described car, described sedan-chair frame is arranged on the exterior circumferential of described car, for fixing described car, described safety tongs is arranged on the bottom of described car, described trailing cable is arranged on the outside of described car, and described machine room control convenience comprises retarder, drag running wheel, track adjusting wheel, velocity limiter, drg, drag and draw machine, source switch and elevator power supply source, described hoistway control convenience comprises rail brackets, drag and draw steel rope, switch touches iron, guide rail, counterweight, compensated chain, compensated chain guide wheel, tightening device, fag end combination and energy disperser, described counterweight is fixed on the below of described car by described fag end combination, described compensated chain, described compensated chain guide wheel and described tightening device are successively set on the below of described counterweight in accordance with the order from top to bottom, and described stop control convenience is arranged on every first floor layer, comprises call box, floor indicator lamp and layer door, RS232 interface, for connecting outside RS232 equipment, receive the benchmark gray scale elevator image of outside RS232 device memory storage, preset gray threshold, preset interval detection time, preset shooting quantity, area change rate threshold value, range rate threshold value and norm track template set, described benchmark gray scale elevator image is for taking obtained image to the car holding human body in advance, and described standard trajectory template set includes various well-regulated path of motion template, static storage device, be connected with described RS232 interface, for receive and store described benchmark gray scale elevator image, described default gray threshold, described default detection time interval, described default shooting quantity, described area change rate threshold value, described range rate threshold value and described standard trajectory template set, elevator power supply source in described machine room control convenience comprises solar powered device, uninterrupted power supply (UPS) device, civil power access device, change-over switch and switch controller, described change-over switch and described solar powered device, described uninterrupted power supply (UPS) device is connected respectively with described civil power access device, described switch controller is connected with described change-over switch, when described switch controller detects civil power regular supply, described change-over switch is switched to described civil power access device to provide power supply by civil power, when described switch controller detects that commercial power supply interrupts, described change-over switch is switched to described uninterrupted power supply (UPS) device to provide power supply by described uninterrupted power supply (UPS) device, described switch controller is also during described uninterrupted power supply (UPS) device provides power supply, determine that whether controlling described change-over switch is switched to described solar powered device to be powered by described solar powered device according to the dump energy of described uninterrupted power supply (UPS) device, described CMOS visual sensing equipment is arranged in described car, is connected with described static storage device, to automatically snap the multiframe lift car image presetting shooting quantity successively based on interval described default detection time, described scene detection equipment is connected with described CMOS visual sensing equipment and described static storage device, to receive described multiframe lift car image respectively, described scene detection equipment comprises Image semantic classification subset, background gray threshold determination subset, background separation subset, target recognin equipment and data and extracts subset, described background gray threshold determination subset is connected with described static storage device, from 0-255, select gray value as preliminary election gray value successively, each grey scale pixel value and described preliminary election gray value in described benchmark gray scale elevator image are subtracted each other the gray scale difference value obtaining each pixel, by the summed square of the gray scale difference value of each pixel, value after addition is divided by sum of all pixels in described benchmark gray scale elevator image to obtain Threshold selection assessment data, and peek is worth the minimum preliminary election gray value gray threshold as a setting corresponding to Threshold selection assessment data, described Image semantic classification subset, described background separation subset, described target recognin equipment and described data are extracted subset and are combined for performing contextual data extraction process to each frame lift car image: described Image semantic classification subset and described CMOS visual sensing equipment connection, for performing contrast strengthen, wavelet filtering and gray processing process successively to each frame lift car image, to obtain each corresponding frame gray processing car image, described background separation subset is connected respectively with described Image semantic classification subset and described background gray threshold determination subset, takes absolute value to obtain each frame and remove background gray level image after the gray value of each pixel in each frame gray processing car image is deducted described background gray threshold, described target recognin equipment is connected respectively with described background separation subset and described static storage device, removes each frame to have in background gray level image all pixels that gray value is more than or equal to described default gray threshold and forms multiple target gray subimage, described data extract subset and described target recognin equipment connection, calculate the position of form center of relative distance between the area of each target, every two targets and each target based on described multiple target gray subimage, described digital signal processor extracts subset with described data and described static storage device is connected respectively, based on the area of each target corresponding to each frame lift car image, the position of form center of the relative distance between every two targets and each target calculates the real-time area change rate aviation value of each target, the real time kinematics track of the real-time relative distance rate of change aviation value between every two targets and each target, and be greater than described area change rate threshold value at the real-time area change rate aviation value that there is target, the real-time relative distance rate of change aviation value deposited between two targets be greater than described range rate threshold value and the real time kinematics track that there is target does not mate any one well-regulated path of motion template of described standard trajectory template set time, send and there is fierce fight scene signals, otherwise, send and there is not fierce fight scene signals, wireless communication interface, be connected respectively with described digital signal processor and described scene detection equipment, for when receiving described fierceness fight scene signals, described multiframe lift car image and described existence fierceness fight scene signals are sent to the internal network of elevator responsible department or the mobile terminal of elevator responsible official by cordless communication network, audio alert equipment, is connected with described digital signal processor, for when receiving described existence fierceness fight scene signals, playing and there is audio alert file corresponding to fierce scene signals of wrestling with described, wherein, described digital signal processor is based on the real-time area change rate aviation value of each target of areal calculation of each target corresponding to each frame lift car image, be specially, for each target, calculate the area change rate of this target of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time area change rate aviation value obtaining this target is averaged to the multiple area change rates calculated, described digital signal processor calculates the real-time relative distance rate of change aviation value between every two targets based on the relative distance between every two targets, be specially, for every two targets, calculate the relative distance rate of change of these two targets of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time relative distance rate of change aviation value obtaining these two targets is averaged to the multiple relative distance rate of changes calculated, described Image semantic classification subset, described background gray threshold determination subset, described background separation subset, described target recognin equipment and described data are extracted subset and are realized by different fpga chips respectively.
More specifically, in described elevator, fierceness is wrestled in scene detection platform: described default gray threshold value is between 0-10.
More specifically, in described elevator in fierce fight scene detection platform: described default detection time, interval value was between 1-5 second.
More specifically, in described elevator, fierceness is wrestled in scene detection platform: described default shooting quantity value is between 5-10.
More specifically, in described elevator, fierceness is wrestled in scene detection platform: described wireless communication interface is arranged on the outside top of described car, and described audio alert equipment is arranged on the inside of described car.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram of the interior fierce fight scene detection platform of elevator illustrated according to an embodiment of the present invention.
Detailed description of the invention
Below with reference to accompanying drawings the embodiment of fight scene detection platform fierce in elevator of the present invention is described in detail.
Current, elevator interior monitor mode is concrete not, valuable reference data cannot be provided for supervision department, such as, lack the detection scheme to fight scene fierce in elevator, if fierce fight scene in concrete elevator can be detected, supervision department just can make and report to the police immediately, gets rid of reasonable Security Personnel and rush towards scene and carry the reaction targetedly of suitable anti-riot instrument, thus safeguards the safe order of elevator place building effectively.
Wherein, in elevator, the feature of fierce fight scene is: the spacing of each human body target is suddenly big or suddenly small, and huge fluctuation appears in people's bulk area, and the path of motion of human body target is very chaotic.
In order to overcome above-mentioned deficiency, the present invention has built fierce fight scene detection platform in a kind of elevator, multiple high precision image check implement and elevator main body is organically combined, realize to expect concrete scene effective, detect in real time.
Fig. 1 is the block diagram of the interior fierce fight scene detection platform of elevator illustrated according to an embodiment of the present invention, described platform comprises CMOS visual sensing equipment 1, scene detection equipment 2 and digital signal processor 3, described CMOS visual sensing equipment 1 obtains lift car image for taking lift car, described scene detection equipment 2 is connected with described CMOS visual sensing equipment 1, extract for performing contextual data to described lift car image, described digital signal processor 3 is connected with described scene detection equipment 2, for determining whether that based on the contextual data extracted performing fierce fight scene reports to the police.
Then, continue to be further detailed the concrete structure of fight scene detection platform fierce in elevator of the present invention.
Described platform also comprises: elevator agent structure, by elevator car body equipment, machine room control convenience, hoistway control convenience and stop control convenience composition, described elevator car body equipment comprises hoistway sensor, door opener, emergency terminal switch, lead boots, panel block in sedan-chair, sedan-chair frame, gate, safety tongs, trailing cable and car, described hoistway sensor, described door opener, described emergency terminal switch and describedly lead the top that boots are all arranged on described car, in described sedan-chair, panel block is arranged on the inside of described car, described sedan-chair frame is arranged on the exterior circumferential of described car, for fixing described car, described safety tongs is arranged on the bottom of described car, described trailing cable is arranged on the outside of described car, and described machine room control convenience comprises retarder, drag running wheel, track adjusting wheel, velocity limiter, drg, drag and draw machine, source switch and elevator power supply source, described hoistway control convenience comprises rail brackets, drag and draw steel rope, switch touches iron, guide rail, counterweight, compensated chain, compensated chain guide wheel, tightening device, fag end combination and energy disperser, described counterweight is fixed on the below of described car by described fag end combination, described compensated chain, described compensated chain guide wheel and described tightening device are successively set on the below of described counterweight in accordance with the order from top to bottom, and described stop control convenience is arranged on every first floor layer, comprises call box, floor indicator lamp and layer door.
Described platform also comprises: RS232 interface, for connecting outside RS232 equipment, receive the benchmark gray scale elevator image of outside RS232 device memory storage, preset gray threshold, preset interval detection time, preset shooting quantity, area change rate threshold value, range rate threshold value and norm track template set, described benchmark gray scale elevator image is for taking obtained image to the car holding human body in advance, and described standard trajectory template set includes various well-regulated path of motion template.
Described platform also comprises: static storage device, be connected with described RS232 interface, for receive and store described benchmark gray scale elevator image, described default gray threshold, described default detection time interval, described default shooting quantity, described area change rate threshold value, described range rate threshold value and described standard trajectory template set.
Elevator power supply source in described machine room control convenience comprises solar powered device, uninterrupted power supply (UPS) device, civil power access device, change-over switch and switch controller, described change-over switch and described solar powered device, described uninterrupted power supply (UPS) device is connected respectively with described civil power access device, described switch controller is connected with described change-over switch, when described switch controller detects civil power regular supply, described change-over switch is switched to described civil power access device to provide power supply by civil power, when described switch controller detects that commercial power supply interrupts, described change-over switch is switched to described uninterrupted power supply (UPS) device to provide power supply by described uninterrupted power supply (UPS) device, described switch controller is also during described uninterrupted power supply (UPS) device provides power supply, determine that whether controlling described change-over switch is switched to described solar powered device to be powered by described solar powered device according to the dump energy of described uninterrupted power supply (UPS) device.
Described CMOS visual sensing equipment 1 is arranged in described car, is connected with described static storage device, to automatically snap the multiframe lift car image presetting shooting quantity successively based on interval described default detection time.
Described scene detection equipment 2 is connected with described CMOS visual sensing equipment 1 and described static storage device, to receive described multiframe lift car image respectively, described scene detection equipment 2 comprises Image semantic classification subset, background gray threshold determination subset, background separation subset, target recognin equipment and data and extracts subset;
Described background gray threshold determination subset is connected with described static storage device, from 0-255, select gray value as preliminary election gray value successively, each grey scale pixel value and described preliminary election gray value in described benchmark gray scale elevator image are subtracted each other the gray scale difference value obtaining each pixel, by the summed square of the gray scale difference value of each pixel, value after addition is divided by sum of all pixels in described benchmark gray scale elevator image to obtain Threshold selection assessment data, and peek is worth the minimum preliminary election gray value gray threshold as a setting corresponding to Threshold selection assessment data;
Described Image semantic classification subset, described background separation subset, described target recognin equipment and described data are extracted subset and are combined for performing contextual data extraction process to each frame lift car image:
Described Image semantic classification subset and described CMOS visual sensing equipment connection, for performing contrast strengthen, wavelet filtering and gray processing process successively to each frame lift car image, to obtain each corresponding frame gray processing car image; Described background separation subset is connected respectively with described Image semantic classification subset and described background gray threshold determination subset, takes absolute value to obtain each frame and remove background gray level image after the gray value of each pixel in each frame gray processing car image is deducted described background gray threshold; Described target recognin equipment is connected respectively with described background separation subset and described static storage device, removes each frame to have in background gray level image all pixels that gray value is more than or equal to described default gray threshold and forms multiple target gray subimage; Described data extract subset and described target recognin equipment connection, calculate the position of form center of relative distance between the area of each target, every two targets and each target based on described multiple target gray subimage.
Described digital signal processor 3 extracts subset with described data and described static storage device is connected respectively, based on the area of each target corresponding to each frame lift car image, the position of form center of the relative distance between every two targets and each target calculates the real-time area change rate aviation value of each target, the real time kinematics track of the real-time relative distance rate of change aviation value between every two targets and each target, and be greater than described area change rate threshold value at the real-time area change rate aviation value that there is target, the real-time relative distance rate of change aviation value deposited between two targets be greater than described range rate threshold value and the real time kinematics track that there is target does not mate any one well-regulated path of motion template of described standard trajectory template set time, send and there is fierce fight scene signals, otherwise, send and there is not fierce fight scene signals.
Described platform also comprises: wireless communication interface, be connected respectively with described digital signal processor 3 and described scene detection equipment 2, for when receiving described fierceness fight scene signals, described multiframe lift car image and described existence fierceness fight scene signals are sent to the internal network of elevator responsible department or the mobile terminal of elevator responsible official by cordless communication network.
Described platform also comprises: audio alert equipment, is connected with described digital signal processor 3, for when receiving described existence fierceness fight scene signals, playing and there is audio alert file corresponding to fierce scene signals of wrestling with described.
Wherein, described digital signal processor 3 is based on the real-time area change rate aviation value of each target of areal calculation of each target corresponding to each frame lift car image, be specially, for each target, calculate the area change rate of this target of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time area change rate aviation value obtaining this target is averaged to the multiple area change rates calculated; Described digital signal processor 3 calculates the real-time relative distance rate of change aviation value between every two targets based on the relative distance between every two targets, be specially, for every two targets, calculate the relative distance rate of change of these two targets of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time relative distance rate of change aviation value obtaining these two targets is averaged to the multiple relative distance rate of changes calculated; Described Image semantic classification subset, described background gray threshold determination subset, described background separation subset, described target recognin equipment and described data are extracted subset and are realized by different fpga chips respectively.
Alternatively, in described platform: described default gray threshold value is between 0-10; Described default detection time, interval value was between 1-5 second; Described default shooting quantity value is between 5-10; And described wireless communication interface is arranged on the outside top of described car, described audio alert equipment is arranged on the inside of described car.
In addition, CMOS (ComplementaryMetal-Oxide-Semiconductor), Chinese formal name used at school is complementary metal oxide semiconductor, and he is originally a kind of important chip in computer system, saves the data that System guides is the most basic.Manufacturing technology and the general computer chip of CMOS do not have difference, mainly utilize the quartz conductor that silicon and this two kinds of elements of germanium are made, make it on CMOS, co-exist the quartz conductor of band N (band-electricity) and P (band+electricity) level, the electric current that these two complementary effects the produce chip that can be processed is noted down and is interpreted to image.Found that CMOS also can as the imageing sensor in digital photography through processing afterwards.
For the portable use independent of electrical network, the CMOS technology famous with low power consumption characteristic has an obvious advantage: cmos image sensor designs for 5V and 3.3V power line voltage.CCD chip then needs the power line voltage of about 12V, employing electric pressure converter of therefore having to, thus causes power consumption to increase.In total power consumption, another benefit will be brought in control and system function integration to cmos sensor: he eliminates all external connection lines with other semiconductor elements.Nowadays the actuator of its high power consumption is abandoned, this is because carry out communicating consumed energy than much lower by the outside implementation of PCB or substrate at chip internal.
Cmos sensor also can be subdivided into passive type element sensor (PassivePixelSensorCMOS) and active pixel sensor (ActivePixelSensorCMOS).
Passive type element sensor (PassivePixelSensor is called for short PPS), be again passive type element sensor, he is made up of a back-biased photodiode and a switching valve.Photodiode is a PN junction be made up of P-type semiconductor and N-type semiconductor in essence, and he can be equivalent to a back-biased diode and a mos capacitance parallel connection.When switching valve is opened, photodiode is communicated with vertical alignment (Columnbus).The charge integration amplifier sensing circuit (Chargeintegratingamplifier) being positioned at alignment end keeps column line voltage to be a constant, when the signal charge of photodiode storage is read out, its voltage is reset to column line voltage level, meanwhile, the electric charge be directly proportional to optical signal is converted to electric charge by charge integration amplifier and exports.
Active pixel sensor (ActivePixelSensor is called for short APS), is again active element sensor.Almost while the invention of CMOSPPS dot structure, people recognize very soon in pixel, to introduce the performance that energy disperser or amplifier can improve pixel, have the amplifier of oneself in CMOSAPS in each pixel.The amplifier transistor being integrated in surface decreases the effective surface area of pixel element, reduces " packaging density ", the incident light of 40% ~ 50% is reflected.Another problem of this sensor is, how to make there is good coupling between the multichannel amplifier of sensor, and this can be realized preferably by the fixed pattern noise reducing residual level.Because each amplifier in CMOSAPS pixel is only excited, so the power dissipation ratio ccd image sensor of CMOSAPS is also little during this reads.
Adopt fierce fight scene detection platform in elevator of the present invention, the problem to fierce fight scene detection techniques scheme concrete in lift car is lacked for prior art, by the mode first determining background threshold, peel off background, determine human body target, finally determine concrete Violent scene according to human body target geometric configuration, fight scene fierce in elevator is performed and effectively detects, each equipment used and elevator agent structure organically combine, while guarantee elevator normally runs, maintain the safety of lift car closed inner environment.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (6)
1. fierce fight scene detection platform in an elevator, described platform comprises CMOS visual sensing equipment, scene detection equipment and digital signal processor, described CMOS visual sensing equipment is used for taking to obtain lift car image to lift car, described scene detection equipment and described CMOS visual sensing equipment connection, extract for performing contextual data to described lift car image, described digital signal processor and described scene detection equipment connection, for determining whether that based on the contextual data extracted performing fierce fight scene reports to the police.
2. fierce fight scene detection platform in elevator as claimed in claim 1, it is characterized in that, described platform also comprises:
Elevator agent structure, by elevator car body equipment, machine room control convenience, hoistway control convenience and stop control convenience composition, described elevator car body equipment comprises hoistway sensor, door opener, emergency terminal switch, lead boots, panel block in sedan-chair, sedan-chair frame, gate, safety tongs, trailing cable and car, described hoistway sensor, described door opener, described emergency terminal switch and describedly lead the top that boots are all arranged on described car, in described sedan-chair, panel block is arranged on the inside of described car, described sedan-chair frame is arranged on the exterior circumferential of described car, for fixing described car, described safety tongs is arranged on the bottom of described car, described trailing cable is arranged on the outside of described car, and described machine room control convenience comprises retarder, drag running wheel, track adjusting wheel, velocity limiter, drg, drag and draw machine, source switch and elevator power supply source, described hoistway control convenience comprises rail brackets, drag and draw steel rope, switch touches iron, guide rail, counterweight, compensated chain, compensated chain guide wheel, tightening device, fag end combination and energy disperser, described counterweight is fixed on the below of described car by described fag end combination, described compensated chain, described compensated chain guide wheel and described tightening device are successively set on the below of described counterweight in accordance with the order from top to bottom, and described stop control convenience is arranged on every first floor layer, comprises call box, floor indicator lamp and layer door,
RS232 interface, for connecting outside RS232 equipment, receive the benchmark gray scale elevator image of outside RS232 device memory storage, preset gray threshold, preset interval detection time, preset shooting quantity, area change rate threshold value, range rate threshold value and norm track template set, described benchmark gray scale elevator image is for taking obtained image to the car holding human body in advance, and described standard trajectory template set includes various well-regulated path of motion template;
Static storage device, be connected with described RS232 interface, for receive and store described benchmark gray scale elevator image, described default gray threshold, described default detection time interval, described default shooting quantity, described area change rate threshold value, described range rate threshold value and described standard trajectory template set;
Elevator power supply source in described machine room control convenience comprises solar powered device, uninterrupted power supply (UPS) device, civil power access device, change-over switch and switch controller, described change-over switch and described solar powered device, described uninterrupted power supply (UPS) device is connected respectively with described civil power access device, described switch controller is connected with described change-over switch, when described switch controller detects civil power regular supply, described change-over switch is switched to described civil power access device to provide power supply by civil power, when described switch controller detects that commercial power supply interrupts, described change-over switch is switched to described uninterrupted power supply (UPS) device to provide power supply by described uninterrupted power supply (UPS) device, described switch controller is also during described uninterrupted power supply (UPS) device provides power supply, determine that whether controlling described change-over switch is switched to described solar powered device to be powered by described solar powered device according to the dump energy of described uninterrupted power supply (UPS) device,
Described CMOS visual sensing equipment is arranged in described car, is connected with described static storage device, to automatically snap the multiframe lift car image presetting shooting quantity successively based on interval described default detection time;
Described scene detection equipment is connected with described CMOS visual sensing equipment and described static storage device, to receive described multiframe lift car image respectively, described scene detection equipment comprises Image semantic classification subset, background gray threshold determination subset, background separation subset, target recognin equipment and data and extracts subset; Described background gray threshold determination subset is connected with described static storage device, from 0-255, select gray value as preliminary election gray value successively, each grey scale pixel value and described preliminary election gray value in described benchmark gray scale elevator image are subtracted each other the gray scale difference value obtaining each pixel, by the summed square of the gray scale difference value of each pixel, value after addition is divided by sum of all pixels in described benchmark gray scale elevator image to obtain Threshold selection assessment data, and peek is worth the minimum preliminary election gray value gray threshold as a setting corresponding to Threshold selection assessment data; Described Image semantic classification subset, described background separation subset, described target recognin equipment and described data are extracted subset and are combined for performing contextual data extraction process to each frame lift car image: described Image semantic classification subset and described CMOS visual sensing equipment connection, for performing contrast strengthen, wavelet filtering and gray processing process successively to each frame lift car image, to obtain each corresponding frame gray processing car image; Described background separation subset is connected respectively with described Image semantic classification subset and described background gray threshold determination subset, takes absolute value to obtain each frame and remove background gray level image after the gray value of each pixel in each frame gray processing car image is deducted described background gray threshold; Described target recognin equipment is connected respectively with described background separation subset and described static storage device, removes each frame to have in background gray level image all pixels that gray value is more than or equal to described default gray threshold and forms multiple target gray subimage; Described data extract subset and described target recognin equipment connection, calculate the position of form center of relative distance between the area of each target, every two targets and each target based on described multiple target gray subimage;
Described digital signal processor extracts subset with described data and described static storage device is connected respectively, based on the area of each target corresponding to each frame lift car image, the position of form center of the relative distance between every two targets and each target calculates the real-time area change rate aviation value of each target, the real time kinematics track of the real-time relative distance rate of change aviation value between every two targets and each target, and be greater than described area change rate threshold value at the real-time area change rate aviation value that there is target, the real-time relative distance rate of change aviation value deposited between two targets be greater than described range rate threshold value and the real time kinematics track that there is target does not mate any one well-regulated path of motion template of described standard trajectory template set time, send and there is fierce fight scene signals, otherwise, send and there is not fierce fight scene signals,
Wireless communication interface, be connected respectively with described digital signal processor and described scene detection equipment, for when receiving described fierceness fight scene signals, described multiframe lift car image and described existence fierceness fight scene signals are sent to the internal network of elevator responsible department or the mobile terminal of elevator responsible official by cordless communication network;
Audio alert equipment, is connected with described digital signal processor, for when receiving described existence fierceness fight scene signals, playing and there is audio alert file corresponding to fierce scene signals of wrestling with described;
Wherein, described digital signal processor is based on the real-time area change rate aviation value of each target of areal calculation of each target corresponding to each frame lift car image, be specially, for each target, calculate the area change rate of this target of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time area change rate aviation value obtaining this target is averaged to the multiple area change rates calculated;
Wherein, described digital signal processor calculates the real-time relative distance rate of change aviation value between every two targets based on the relative distance between every two targets, be specially, for every two targets, calculate the relative distance rate of change of these two targets of two frame lift car images of adjacent shooting time according to the shooting time tandem of lift car image, and the real-time relative distance rate of change aviation value obtaining these two targets is averaged to the multiple relative distance rate of changes calculated;
Wherein, described Image semantic classification subset, described background gray threshold determination subset, described background separation subset, described target recognin equipment and described data extraction subset is realized by different fpga chips respectively.
3. fierce fight scene detection platform in elevator as claimed in claim 2, is characterized in that:
Described default gray threshold value is between 0-10.
4. fierce fight scene detection platform in elevator as claimed in claim 2, is characterized in that:
Described default detection time, interval value was between 1-5 second.
5. fierce fight scene detection platform in elevator as claimed in claim 2, is characterized in that:
Described default shooting quantity value is between 5-10.
6. fierce fight scene detection platform in elevator as claimed in claim 2, is characterized in that:
Described wireless communication interface is arranged on the outside top of described car, and described audio alert equipment is arranged on the inside of described car.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510469000.0A CN105060051B (en) | 2015-08-04 | 2015-08-04 | Fierce fight scene detection platform in elevator |
| CN201511002644.5A CN105502117A (en) | 2015-08-04 | 2015-08-04 | Detection platform for intense fight scene in elevator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510469000.0A CN105060051B (en) | 2015-08-04 | 2015-08-04 | Fierce fight scene detection platform in elevator |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511002644.5A Division CN105502117A (en) | 2015-08-04 | 2015-08-04 | Detection platform for intense fight scene in elevator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105060051A true CN105060051A (en) | 2015-11-18 |
| CN105060051B CN105060051B (en) | 2016-08-24 |
Family
ID=54489645
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511002644.5A Pending CN105502117A (en) | 2015-08-04 | 2015-08-04 | Detection platform for intense fight scene in elevator |
| CN201510469000.0A Active CN105060051B (en) | 2015-08-04 | 2015-08-04 | Fierce fight scene detection platform in elevator |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511002644.5A Pending CN105502117A (en) | 2015-08-04 | 2015-08-04 | Detection platform for intense fight scene in elevator |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN105502117A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184219A (en) * | 2015-08-04 | 2015-12-23 | 董岩 | Method for intelligent detection of fierce struggle scene in elevator |
| CN107687274A (en) * | 2016-08-04 | 2018-02-13 | 浙江大丰实业股份有限公司 | Automate danger arenas security platform |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106241534B (en) * | 2016-06-28 | 2018-12-07 | 西安特种设备检验检测院 | More people's boarding abnormal movement intelligent control methods |
| CN106241533B (en) * | 2016-06-28 | 2018-10-30 | 西安特种设备检验检测院 | Elevator occupant's comprehensive safety intelligent control method based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1919711A (en) * | 2006-09-20 | 2007-02-28 | 浙江工业大学 | Elevator inner violence-proof apparatus based on image and speech recognition technique |
| JP2009149412A (en) * | 2007-12-20 | 2009-07-09 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator mode changing device and elevator mode changing method |
| CN101998069A (en) * | 2009-08-27 | 2011-03-30 | 上海泰莱钢结构工程有限公司 | Image sensor |
| CN103803361A (en) * | 2013-12-27 | 2014-05-21 | 广州永日电梯有限公司 | Monitoring method based on wireless transmission |
| CN204324633U (en) * | 2014-11-06 | 2015-05-13 | 中国人民武装警察部队工程大学 | A kind of elevator safety monitoring and forewarn system |
-
2015
- 2015-08-04 CN CN201511002644.5A patent/CN105502117A/en active Pending
- 2015-08-04 CN CN201510469000.0A patent/CN105060051B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1919711A (en) * | 2006-09-20 | 2007-02-28 | 浙江工业大学 | Elevator inner violence-proof apparatus based on image and speech recognition technique |
| JP2009149412A (en) * | 2007-12-20 | 2009-07-09 | Mitsubishi Electric Building Techno Service Co Ltd | Elevator mode changing device and elevator mode changing method |
| CN101998069A (en) * | 2009-08-27 | 2011-03-30 | 上海泰莱钢结构工程有限公司 | Image sensor |
| CN103803361A (en) * | 2013-12-27 | 2014-05-21 | 广州永日电梯有限公司 | Monitoring method based on wireless transmission |
| CN204324633U (en) * | 2014-11-06 | 2015-05-13 | 中国人民武装警察部队工程大学 | A kind of elevator safety monitoring and forewarn system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184219A (en) * | 2015-08-04 | 2015-12-23 | 董岩 | Method for intelligent detection of fierce struggle scene in elevator |
| CN107687274A (en) * | 2016-08-04 | 2018-02-13 | 浙江大丰实业股份有限公司 | Automate danger arenas security platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105502117A (en) | 2016-04-20 |
| CN105060051B (en) | 2016-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105060051A (en) | Scene detection platform for intense fighting in elevator | |
| CN106315324A (en) | Elevator system capable of monitoring child's use and control method for same | |
| CN107633210B (en) | Construction site violation ascending monitoring system, method, device, medium and equipment | |
| Wen et al. | We help you watch your steps: Unobtrusive alertness system for pedestrian mobile phone users | |
| CN105181072A (en) | Automatic water level detection method | |
| CN108592811A (en) | A kind of building structure Fracture Deformation real-time dynamic monitoring system and recognition methods | |
| CN101587537A (en) | Method and system of crowd density statistics based on intelligent video identification technology | |
| CN203998490U (en) | A kind of elevator person number detection device | |
| CN105060039A (en) | Method for recognizing children in lift car | |
| US11900701B2 (en) | Left object detection device and left object detection method | |
| CN105060052A (en) | In-elevator violence incident early-warning system based on image processing | |
| CN104100154A (en) | Multi-functional handcuffs device | |
| CN109052098A (en) | Lift car overload detecting method based on image procossing | |
| CN104058306A (en) | Intelligent dispatching system of elevator | |
| CN105129566A (en) | Method for intelligently detecting safety of elevator | |
| CN105139577A (en) | Danger alarm method for inner corner of elevator based on wireless communication | |
| CN105129555A (en) | Method for recognizing suspicious elevator violence incident | |
| CN105110114A (en) | Children recognition system in elevator car | |
| CN105184219A (en) | Method for intelligent detection of fierce struggle scene in elevator | |
| CN105000443A (en) | Method for early warning of violent incidents in elevator based on image processing | |
| CN105552746B (en) | Intelligent base station signal intensity distribution box | |
| CN107341585A (en) | Intelligence community management system based on Internet of Things | |
| CN105185127B (en) | Traffic police's vehicle detection platform based on data communication | |
| US20220101364A1 (en) | Control apparatus and method | |
| CN105844909A (en) | Electric shock prevention distribution box |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Tian Guidong Inventor before: Dong Yan |
|
| COR | Change of bibliographic data | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160720 Address after: Eighteen Hainan village, Haian Town, Jiangsu City, Nantong Province, China (226600), Applicant after: Nantong Runya Electromechanical Technology Co., Ltd. Address before: Qingfeng street 053000 Hebei city of Hengshui province No. 66 Applicant before: Dong Yan |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |