CN103973952A - Four-dimensional human body recognition device - Google Patents
Four-dimensional human body recognition device Download PDFInfo
- Publication number
- CN103973952A CN103973952A CN201410205232.0A CN201410205232A CN103973952A CN 103973952 A CN103973952 A CN 103973952A CN 201410205232 A CN201410205232 A CN 201410205232A CN 103973952 A CN103973952 A CN 103973952A
- Authority
- CN
- China
- Prior art keywords
- human body
- image sensor
- sensor chip
- recognition device
- camera
- 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.)
- Pending
Links
Landscapes
- Image Input (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a four-dimensional human body recognition device which comprises a camera. The camera comprises an image sensor chip, a lens set and an infrared cut-off filter, wherein the lens set is arranged on the part, on the outer portion of the light incident side of the image sensor chip, on a light path, and the infrared cut-off filter is arranged on the part between the lens set and the image sensor chip of the camera, on the light path. According to the four-dimensional human body recognition device, due to the fact that the infrared cut-off filter is arranged between the lens set and the image sensor chip, a human body temperature parameter can be added and detected in a traditional 3d image by selecting the proper infrared cut-off filter, the four-dimensional detection of the human body is achieved, four-dimensional recognition can be conducted, and compared with traditional 3D recognition, the four-dimensional human body recognition device is better in recognition accuracy and recognition effect.
Description
Technical field
The present invention relates to human body recognition technology field, refer in particular to a kind of four-dimensional human body recognition device.
Background technology
Current, existing human body recognition device has started to adopt three-dimensional imaging technology to identify, existing human body recognition device mainly comprises image sensor chip for the camera that extracts characteristics of human body and is located at the assembly such as set of lenses of the light light incident side of image sensor chip, and the 3 D human body image absorbing carries out 3 D human body identification for assembly or the system of rear end.But this existing human body recognition device can not processed the infrared light in environment, full wave spectrum line all can scioptics group arrive on the induction chip of rear end.But this existing apparatus, for the treatment of the assembly of infrared light, although its camera can form coloured image by day, does not have cross-color, can only form the gray-scale map of black and white evening; Especially this device can not carry out temperature detection to human body and object, can not be well human body and periphery object and environment be distinguished, and causes recognition effect to be had a greatly reduced quality.
Summary of the invention
Technical problem to be solved by this invention is, provides a kind of four-dimensional human body recognition device, to promote human body recognition effect.
For solving the problems of the technologies described above, the invention provides following technical scheme: a kind of four-dimensional human body recognition device, comprise camera, described camera comprises:
Image sensor chip;
Be arranged at the set of lenses in the light path of light light incident side outside of described image sensor chip; And
Be arranged at the IR-cut filter in the light path between transparent group of described camera and image sensor chip.
Further, described image sensor chip is for can perceive the image sensor chip that wavelength is the mid and far infrared spectral line of 6 ~ 14 μ m.
Further, described image sensor chip is CMOS chip or CCD chip.
Further, described camera is also provided with many infrared LED lamps for light filling in the surrounding of described set of lenses.
Further, the cut-off wavelength of described IR-cut filter is positioned at outside the wavelength section of described infrared LED lamp.
Further, described camera is the infrared camera of 850nm or 920nm specification, and the long wave cut-off function of described IR-cut filter is in below 1100 ~ 1200nm.
Further, described IR-cut filter is a kind of IR-cut filter that visible ray can be filtered.
Adopt after technique scheme, the present invention at least has following beneficial effect: by IR-cut filter is set between set of lenses and image sensor chip, can be by selecting appropriate IR-cut filter, thereby can in traditional 3D rendering, increase and a human body temperature parameter be detected, thereby the four-dimension (4D) of having realized human body detects, and then can carry out four-dimension identification, than traditional 3D identification, its accuracy of identification and better effects if, especially can also distinguish well efficient human body and objects such as manikin, recognition effect is better.
Brief description of the drawings
Fig. 1 is the structural representation of the embodiment mono-of the four-dimensional human body recognition device of the present invention.
Fig. 2 is the Spectral Properties point diagram that passes through to arrive after ICF filter the light on image sensor chip of the embodiment mono-of the four-dimensional human body recognition device of the present invention.
Fig. 3 is the structural representation of the embodiment bis-of the four-dimensional human body recognition device of the present invention.
Fig. 4 is the Spectral Properties point diagram that passes through to arrive after ICF filter the light on image sensor chip of the embodiment bis-of the four-dimensional human body recognition device of the present invention.
Fig. 5 is the Spectral Properties point diagram that passes through to arrive after ICF filter the light on image sensor chip of the embodiment tri-of the four-dimensional human body recognition device of the present invention.
Embodiment
It should be noted that, in the situation that not conflicting, the feature in embodiment and embodiment in the application can mutually combine, and below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
Embodiment mono-
As shown in Figure 1, the invention provides a kind of four-dimensional human body recognition device, it comprises camera, and described camera comprises image sensor chip 1, be arranged at the set of lenses 2 in the light path of light light incident side of described image sensor chip 1 and be arranged at the IR-cut filter (ICF filter) 3 in the light path between described image sensor chip 1 and set of lenses 2.Described image sensor chip 1 can be CCD chip or CMOS chip.
Because the body temperature of human body is generally at 36 ~ 37.5 degrees Celsius, according to black body radiation rule, the centre wavelength scope of carrying out infrared radiation is 9.62 ~ 9.67 μ m; And from winter to summer room temperature excursion be about 0 ~ 40 degree Celsius, the centre wavelength scope of its infrared radiation is 9.54 ~ 10.94 μ m, be that 7 ~ 8 μ m calculate according to broadening of spectral lines, require the image sensor chip of rear end be able to sense to be about 6 ~ 14 μ m in the infrared line of wave band far away.And with respect to environment infrared radiation (the particularly infrared composition in sunlight on daytime), the ultrared energy density of human body radiation is relatively low, therefore require to adopt a kind of ICF filter the infrared and visible ray composition that is less than 6 μ m can be filtered out, the low relative effect of wave band energy that is greater than 14 microns is lower, need to ask the energy gap of this material to be less than this material of 0.25eV(and be generally compound, on infrared imaging, this type of material is used often), rear end infrared induction element can be effectively realized and the infrared light that human body or environment send the impact that reduces other light can be received.Spectral Properties point diagram by the light on the rear arrival image sensor chip 1 of ICF filter 3 as shown in Figure 2.
By increasing above-mentioned ICF filter 3, can identify the Infrared that human body and environment self send; And can distinguish the temperature contrast between human body and environment object.
By increase a temperature parameter in traditional 3D rendering, thereby the four-dimension (4D) of having realized human body detects, and then can carry out four-dimension identification, than traditional 3D identification, its accuracy of identification and better effects if.
Embodiment bis-
The recognition effect of embodiment mono-is very good, but, the cost of the ICF filter adopting due to embodiment mono-is relatively high, and the membrane material of ICF filter especially wherein and image sensor chip 1 often need specific customization or from foreign procurement, its application be very restricted.To this, the present invention also provides the present embodiment two that cost is relatively cheap.
The present embodiment be on the basis of common 3D camera, improve and, as shown in Figure 3, carry out light filling by added many infrared LED lamps 4 on the both sides of 3D camera, thereby realize the shooting to object under full dark surrounds.Identical with above-described embodiment 1, the same IR-cut filter (ICF filter) 3 that is provided with between set of lenses 2 and image sensor chip 1, to ensure the impact of infrared light on image quality under environment on daytime.
The cut-off wavelength of the described ICF filter 3 adopting in the present embodiment need to be walked around the spectrum line of infrared LED lamp 4, or get around the reception of the infrared band of infrared LED lamp 4 according to the opening and closing that environmental light intensity carries out ICF filter 3, generally select the infrared camera of 850nm, 920nm equal-specification, and the long wave cut-off function of ICF filter 3 is in below 1100 ~ 1200nm.In the present embodiment, the Spectral Properties point diagram by the light on the rear arrival image sensor chip 1 of ICF filter 3 as shown in Figure 4, the wavelength of A place arrow in figure representative infrared LED lamp pointed.
The four-dimensional human body recognition device of the present embodiment can be realized colored shooting on daytime, and take the image obtaining night is mainly the gray-scale map of black and white; But because the camera, the ICF filter that adopt are all ripe subassembly products of commonly using on the market, purchase cost is cheap, and whole implementation effect still can reach predetermined technique requirement, thereby the scheme of the present embodiment more easily realizes.
In the time carrying out human body identification, need gather respectively two cover samples under daytime and complete dark red outer light filling, finally train two cover grader files.
Embodiment tri-
The present embodiment three is consistent with above-described embodiment two on module composition, but some changes are made aspect the selecting of ICF filter 3, the present embodiment three is by selecting a kind of ICF filter 3 that visible ray can be filtered, thereby, no matter be daytime or night, camera system all can only become a kind of gray level image of black and white.
In the present embodiment three, the cut-off wavelength of ICF filter 3 need to be walked around the wavelength of the infrared band that infrared LED lamp 4 sends, or gets around the reception of the infrared band of infrared LED lamp according to the opening and closing that environmental light intensity carries out ICF filter 3.In the present embodiment, the Spectral Properties point diagram by the light on the rear arrival image sensor chip 1 of ICF filter 3 as shown in Figure 5, the wavelength of A place arrow in figure representative infrared LED lamp pointed.
The scheme of the present embodiment is in the time implementing, no matter daytime or evening are all to obtain black and white gray-scale map.
Because needs filter visible ray, the ICF filter adopting in the present embodiment also needs to propose special technical property requirements to corresponding filter manufacturer and manufactures, but, the present embodiment is relatively simple aspect later data processing, only need to gather next cover sample of complete dark red outer light filling condition, train a set of grader file.
On above-mentioned each embodiment basis, under current human perception algorithm condition by day, can obtain people's position and quantity, but cannot obtain the state of human body.In order to ensure the effect of later data processing, for different cameras, conventionally need to gather corresponding Sample Storehouse.By using corresponding camera to carry out, after the work such as sample collection, sample cutting, grader training and test, drawing assessment result, finally just can draw the effect of algorithm under complete dark red outer light filling condition.
Although illustrated and described embodiments of the invention, for the ordinary skill in the art, be appreciated that without departing from the principles and spirit of the present invention and can carry out multiple variation, amendment, replacement and modification to these embodiment, scope of the present invention is limited by claims and equivalency range thereof.
Claims (7)
1. a four-dimensional human body recognition device, comprises camera, it is characterized in that, described camera comprises:
Image sensor chip;
Be arranged at the set of lenses in the light path of light light incident side outside of described image sensor chip; And
Be arranged at the IR-cut filter in the light path between transparent group of described camera and image sensor chip.
2. the three-dimensional face Gender Classification device based on three-dimensional point cloud as claimed in claim 1, is characterized in that, described image sensor chip is for can perceive the image sensor chip that wavelength is the mid and far infrared spectral line of 6 ~ 14 μ m.
3. four-dimensional human body recognition device as claimed in claim 1 or 2, is characterized in that, described image sensor chip is CMOS chip or CCD chip.
4. four-dimensional human body recognition device as claimed in claim 1, is characterized in that, described camera is also provided with many infrared LED lamps for light filling in the surrounding of described set of lenses.
5. four-dimensional human body recognition device as claimed in claim 4, is characterized in that, the cut-off wavelength of described IR-cut filter is positioned at outside the wavelength section of described infrared LED lamp.
6. four-dimensional human body recognition device as claimed in claim 4, is characterized in that, described camera is the infrared camera of 850nm or 920nm specification, and the long wave cut-off function of described IR-cut filter is in below 1100 ~ 1200nm.
7. four-dimensional human body recognition device as claimed in claim 4, is characterized in that, described IR-cut filter is a kind of IR-cut filter that visible ray can be filtered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410205232.0A CN103973952A (en) | 2014-05-15 | 2014-05-15 | Four-dimensional human body recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410205232.0A CN103973952A (en) | 2014-05-15 | 2014-05-15 | Four-dimensional human body recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103973952A true CN103973952A (en) | 2014-08-06 |
Family
ID=51242954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410205232.0A Pending CN103973952A (en) | 2014-05-15 | 2014-05-15 | Four-dimensional human body recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103973952A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105919746A (en) * | 2016-05-24 | 2016-09-07 | 杨春燕 | Nursing bed with multi-angle adjusting function and blood purification function |
| CN105919745A (en) * | 2016-05-24 | 2016-09-07 | 许兰兰 | Sickbed for internal medicine department |
| CN105943273A (en) * | 2016-05-24 | 2016-09-21 | 李勇 | Cloud computing system |
| CN105943274A (en) * | 2016-05-24 | 2016-09-21 | 李红军 | A clinical nursing ward bed |
| CN107563321A (en) * | 2017-08-28 | 2018-01-09 | 无锡北斗星通信息科技有限公司 | A kind of human body target real-time analysis method |
| CN108470166A (en) * | 2018-04-04 | 2018-08-31 | 北京天目智联科技有限公司 | A kind of biological characteristic 3D 4 D datas recognition methods and system based on laser scanning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101047783A (en) * | 2006-03-31 | 2007-10-03 | 鸿富锦精密工业（深圳）有限公司 | Micro-camera device |
| CN101072299A (en) * | 2006-05-11 | 2007-11-14 | Lg伊诺特有限公司 | Camera module and mobile terminal having the same |
| CN101114039A (en) * | 2006-07-28 | 2008-01-30 | 鸿富锦精密工业（深圳）有限公司 | Lens module |
| US20090201360A1 (en) * | 2008-02-08 | 2009-08-13 | Google Inc. | Dichroic Cut Filter for Wide-Angle Imaging |
| CN101520420A (en) * | 2009-04-03 | 2009-09-02 | 中国政法大学 | Middle and far infrared camera |
| CN102768074A (en) * | 2012-07-25 | 2012-11-07 | 北京华铁能信科技有限公司 | Multi-lattice detector for photons with intermediate and far infrared wavelengths |
| CN103024251A (en) * | 2011-09-23 | 2013-04-03 | 三星电机株式会社 | Camera module |
-
2014
- 2014-05-15 CN CN201410205232.0A patent/CN103973952A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101047783A (en) * | 2006-03-31 | 2007-10-03 | 鸿富锦精密工业（深圳）有限公司 | Micro-camera device |
| CN101072299A (en) * | 2006-05-11 | 2007-11-14 | Lg伊诺特有限公司 | Camera module and mobile terminal having the same |
| CN101114039A (en) * | 2006-07-28 | 2008-01-30 | 鸿富锦精密工业（深圳）有限公司 | Lens module |
| US20090201360A1 (en) * | 2008-02-08 | 2009-08-13 | Google Inc. | Dichroic Cut Filter for Wide-Angle Imaging |
| CN101520420A (en) * | 2009-04-03 | 2009-09-02 | 中国政法大学 | Middle and far infrared camera |
| CN103024251A (en) * | 2011-09-23 | 2013-04-03 | 三星电机株式会社 | Camera module |
| CN102768074A (en) * | 2012-07-25 | 2012-11-07 | 北京华铁能信科技有限公司 | Multi-lattice detector for photons with intermediate and far infrared wavelengths |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105919746A (en) * | 2016-05-24 | 2016-09-07 | 杨春燕 | Nursing bed with multi-angle adjusting function and blood purification function |
| CN105919745A (en) * | 2016-05-24 | 2016-09-07 | 许兰兰 | Sickbed for internal medicine department |
| CN105943273A (en) * | 2016-05-24 | 2016-09-21 | 李勇 | Cloud computing system |
| CN105943274A (en) * | 2016-05-24 | 2016-09-21 | 李红军 | A clinical nursing ward bed |
| CN107582272A (en) * | 2016-05-24 | 2018-01-16 | 许兰兰 | A kind of internal medicine operation bed |
| CN107563321A (en) * | 2017-08-28 | 2018-01-09 | 无锡北斗星通信息科技有限公司 | A kind of human body target real-time analysis method |
| CN107563321B (en) * | 2017-08-28 | 2018-07-13 | 深圳市奥丝卡生物科技有限公司 | A kind of human body target real-time analysis method |
| CN108470166A (en) * | 2018-04-04 | 2018-08-31 | 北京天目智联科技有限公司 | A kind of biological characteristic 3D 4 D datas recognition methods and system based on laser scanning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103973952A (en) | Four-dimensional human body recognition device | |
| JP5545016B2 (en) | Imaging device | |
| TWI666935B (en) | A mini thermography for enhance nir captures images | |
| US8836793B1 (en) | True color night vision (TCNV) fusion | |
| WO2017059774A1 (en) | Methods and systems for fusion display of thermal infrared and visible image | |
| CN103926199B (en) | Hazardous material detection method | |
| US20170111557A1 (en) | Camera assembly with filter providing different effective entrance pupil sizes based on light type | |
| CN107407855B (en) | Vehicle-mounted camera | |
| CN205068435U (en) | Camera subassembly and have its mobile device | |
| KR20110125172A (en) | Image processing apparatus, image processing method, and program | |
| CN103412407A (en) | Multi-spectrum image collecting system | |
| CN106415239A (en) | A mobile microscopy device being able to take images in different wavelengths (multispectral) | |
| CN203164522U (en) | Multispectral image acquisition system | |
| MX366073B (en) | Method for identifying objects in a subject's ear. | |
| CN104080663A (en) | Detection of rain drops on a plate by means of a camera and illumination | |
| CN105428376A (en) | Single-chip image sensor having visible light and UV-light detection function and detection method thereof | |
| CN104092987A (en) | Bimodal dual-feedback self-adaptation target tracking system and method and control circuit | |
| JP6321289B2 (en) | Apparatus and method for acquiring iris image outside and inside | |
| KR102047255B1 (en) | An automatic observation method using whole-sky image | |
| CN102564580A (en) | Device for improving sensitivity of image sensor and applying forming light | |
| Kim et al. | Hyperspectral image-based night-time fire detection using NKNBD | |
| US10848691B2 (en) | System for observing nocturnal activities and temperature variation of a living target during daytime | |
| KR20220004740A (en) | Systems and methods for object recognition under natural and/or artificial light | |
| CN205539731U (en) | Biological imaging device under water | |
| CN202617286U (en) | Image acquisition apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140806 |
|
| RJ01 | Rejection of invention patent application after publication |