CN108563987A - A kind of intelligent mobile terminal - Google Patents
A kind of intelligent mobile terminal Download PDFInfo
- Publication number
- CN108563987A CN108563987A CN201810176220.8A CN201810176220A CN108563987A CN 108563987 A CN108563987 A CN 108563987A CN 201810176220 A CN201810176220 A CN 201810176220A CN 108563987 A CN108563987 A CN 108563987A
- Authority
- CN
- China
- Prior art keywords
- image
- segmentation
- processing module
- result
- mobile terminal
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of intelligent mobile terminals, including audio collecting device, Image Acquisition array, image processing module, picture recognition module and display module, the audio collecting device setting is on mobile terminals, noise level for detecting site environment, and testing result is sent to display module, it includes the first image capture device and the second image capture device that described image, which acquires array, described image processing module to the ambient image of output for being split processing, described image identification module is for being identified the ambient image after segmentation, and recognition result is sent to display module, the display module is for showing the noise measuring result and ambient image recognition result.Beneficial effects of the present invention are：A kind of intelligent mobile terminal is provided, the detection and identification of environmental noise and environment scene are realized.
Description
Technical field
The present invention relates to technical field of mobile terminals, and in particular to a kind of intelligent mobile terminal.
Background technology
Mobile terminal can meet a variety of demands of user whenever and wherever possible, with the development of mobile terminal, the demand of people
Also higher and higher, existing mobile terminal is unable to judge accurately the noise in residing environment and environment.
Vision is the primary sensing organ that human contact recognizes objective world, and the result that every statistical data is presented tells me
, it is by vision system that the mankind, which obtain in all approach of external information 60% or more, and vision obtains existence institute for the mankind
The various information needed are of great significance, it is the most important feeling of the mankind.In addition, one of human vision or thinking is basic
Tool, from the reception, transmission or even working process of information, until really being received all to be unable to do without vision system.Entire vision mistake
Journey is very complicated, but in this process, most important function --- distinguish that image but is highlighted out.When the mankind enter information
Dai Hou, various Image Acquisition tools also continuously emerge, these Image Acquisition tools none be not to causing visual stimulus
Visual information acquisition, computer in face of collect various types visual information to be done exactly it is carried out with which kind of method
Processing, during exploring processing method, computer vision is also just gradually formed as a subject.
Invention content
In view of the above-mentioned problems, the present invention is intended to provide a kind of intelligent mobile terminal.
The purpose of the present invention is realized using following technical scheme：
Provide a kind of intelligent mobile terminal, including audio collecting device, Image Acquisition array, image processing module, figure
As identification module and display module, the audio collecting device is arranged on mobile terminals, the noise for detecting site environment
Size, and testing result is sent to display module, it includes the first image capture device and the second figure that described image, which acquires array,
As collecting device, described first image collecting device is set to above mobile terminal, for the top scene to mobile terminal into
The acquisition of row image data is to obtain and export the ambient image at top, the second image capture device setting and mobile terminal
Lower section carries out the acquisition of image data to obtain and export the ambient image of bottom, institute for the lower section scene to mobile terminal
Image processing module is stated for being split processing to the ambient image of output, after described image identification module is used for segmentation
Ambient image is identified, and recognition result is sent to display module, and the display module is for showing the noise measuring
As a result with ambient image recognition result.
Beneficial effects of the present invention are：A kind of intelligent mobile terminal is provided, environmental noise and environment scene are realized
Detection and identification.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural schematic diagram of the present invention；
Reference numeral：
Audio collecting device 1, Image Acquisition array 2, image processing module 3, picture recognition module 4, display module 5.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of intelligent mobile terminal of the present embodiment, including audio collecting device 1, Image Acquisition array 2, figure
As processing module 3, picture recognition module 4 and display module 5, the audio collecting device 1 is arranged on mobile terminals, for examining
The noise level of site environment is surveyed, and testing result is sent to display module 5, it includes the first figure that described image, which acquires array 2,
As collecting device and the second image capture device, described first image collecting device is set to above mobile terminal, for moving
The top scene of dynamic terminal carries out the acquisition of image data to obtain and export the ambient image at top, second Image Acquisition
Equipment is arranged with below mobile terminal, and the acquisition of image data is carried out to obtain and export for the lower section scene to mobile terminal
The ambient image of bottom, described image processing module 3 are used to be split processing, described image identification to the ambient image of output
Recognition result is sent to display module 5, the display module 5 by module 4 for the ambient image after segmentation to be identified
For showing the noise measuring result and ambient image recognition result.
A kind of intelligent mobile terminal is present embodiments provided, the detection and identification of environmental noise and environment scene are realized.
Preferably, described image processing module 3 include first processing module, Second processing module, third processing module and
Segmentation evaluation module, the first processing module obtain a segmentation result for once being divided to image, and described second
Processing module is used to carry out secondary splitting to image, obtains secondary splitting as a result, the third processing module is used for according to primary
Segmentation result and secondary splitting result obtain the final segmentation result of image, and the segmentation evaluation module is used for third processing
The segmentation effect of module is evaluated.
The effective segmentation and the accurate evaluation to segmentation effect that this preferred embodiment realizes image.
Preferably, the first processing module obtains a segmentation result, specifically for once being divided to image
For：
Select a threshold value t1, image is divided into two set by its pixel grey scale, all pixels ash in each set
It spends the probability occurred and constitutes a chance event, define the first segmentation function of image：
In formula, H (t1) indicate image the first segmentation function, piIndicate that image pixel gray level grade is the probability of i-stage, L tables
The series of the gray scale of diagram picture；
The first segmentation function for maximizing image, obtains the optimal threshold T that image is once divided1, once divided according to image
Cut optimal threshold T1Obtain segmentation result F of image1(x, y), wherein (x, y) indicates pixel；
This preferred embodiment is split image using the first segmentation function, respectively due to the target and background in image
Gray value fluctuations are corresponded to than shallower region, as long as target and background divides correct, the value meeting of the first segmentation function
It is bigger；If threshold value selection is improper, it will can originally be not belonging to certain a kind of pixel and be divided into such, due between inhomogeneity
Pixel grey scale differs greatly, and the value of the first segmentation function can be caused to reduce；
Preferably, the Second processing module includes single treatment submodule, after-treatment submodule and handles three times sub
Module, the single treatment submodule are used for true according to gray matrix for establishing gray matrix, the after-treatment submodule
Fixed second segmentation function, the submodule of processing three times are used to obtain secondary splitting result according to the second segmentation function；
The single treatment submodule is for establishing gray matrix, specially：
The image for being L grades for gray scale defines the square formation that gray matrix Z is L × L：Z=[tij]L×L, wherein
In formula, M and N indicate that the line number of image and columns and j indicate pixel grey scale respectively, when f (m, n)=i and f (m+1,
N)=j when or f (m, n)=i and when f (m, n+1)=j, βmn=1, otherwise, βmn=0；
Calculate the transition probability matrix of gray scale i to j：
In formula, the gray scale of k and l expression pixels；
The after-treatment submodule according to gray matrix for determining the second segmentation function, specially：
The gray scale of gray matrix increases from 0 to L-1 from bottom to top, increases from left to right from 0 to L-1, chooses a threshold value
t2Gray matrix is divided into four regions, the gray matrix lower left corner is 1st area, and the lower right corner is 2nd area, and the upper right corner is 3rd area, and the upper left corner is
4th area, it is background to enable gray scale be less than the pixel of threshold value, and gray scale is target higher than the pixel of threshold value；
Define the second segmentation function：
In formula, E (t2) indicate the second segmentation function；
The submodule of processing three times is used to obtain secondary splitting according to the second segmentation function as a result, being specially：
The second segmentation function is maximized, the optimal threshold T of image secondary splitting is obtained2, best according to image secondary splitting
Threshold value T2Obtain image secondary splitting result F2(x, y), wherein (x, y) indicates pixel；
The third processing module, which is used to obtain image according to a segmentation result and secondary splitting result, finally divides knot
Fruit, specially：Final segmentation result is calculated using following formula：
F (x, y)=ρ1F1(x,y)+ρ2F2(x,y)
In formula, F (x, y) indicates the final segmentation result of image, ρ1、ρ2Indicate weight, ρ1+ρ2=1；
This preferred embodiment is split image using the second segmentation function, has fully considered neighborhood territory pixel, has embodied
The spatial positional information of pixel obtains more accurate secondary splitting as a result, by by a segmentation result and secondary splitting
As a result it is weighted fusion, obtains the more accurate final segmentation result of image.
Preferably, the segmentation evaluation module is for evaluating the segmentation effect of the third processing module, specifically
For：Define evaluation points：
In formula, P indicates evaluation points, M1Indicate the number of pixel segmentation errors, N1Indicate the number of pixel in image；It comments
The valence factor is smaller, indicates that segmentation effect is better.
This preferred embodiment segmentation evaluation module evaluates segmentation effect by evaluation points, ensure that image segmentation
Level is laid a good foundation for subsequent image identification.
Environment scene is detected using intelligent mobile terminal of the present invention, 5 scenes is chosen and is tested, respectively field
Scape 1, scene 2, scene 3, scene 4, scene 5, count scene Recognition accuracy rate and scene Recognition efficiency, compared with intelligence
Mobile terminal is compared, and generation has the beneficial effect that shown in table：
| Scene Recognition accuracy rate improves | Scene Recognition efficiency improves | |
| Scene 1 | 29% | 27% |
| Scene 2 | 27% | 26% |
| Scene 3 | 26% | 26% |
| Scene 4 | 25% | 24% |
| Scene 5 | 24% | 22% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (5)
1. a kind of intelligent mobile terminal, which is characterized in that including audio collecting device, Image Acquisition array, image processing module,
Picture recognition module and display module, the audio collecting device are arranged on mobile terminals, for detecting making an uproar for site environment
Sound size, and testing result is sent to display module, it includes the first image capture device and second that described image, which acquires array,
Image capture device, described first image collecting device are set to above mobile terminal, for the top scene to mobile terminal
The acquisition of image data is carried out to obtain and export the ambient image at top, the second image capture device setting and movement are eventually
End lower section carries out the acquisition of image data to obtain and export the ambient image of bottom for the lower section scene to mobile terminal,
Described image processing module is used to be split processing to the ambient image of output, after described image identification module is used for segmentation
Ambient image be identified, and recognition result is sent to display module, the display module is for showing the noise inspection
Survey result and ambient image recognition result.
2. intelligent mobile terminal according to claim 1, which is characterized in that described image processing module includes the first processing
Module, Second processing module, third processing module and segmentation evaluation module, the first processing module are used to carry out one to image
Secondary segmentation obtains a segmentation result, and the Second processing module is used to carry out secondary splitting to image, obtains secondary splitting knot
Fruit, the third processing module are used to obtain the final segmentation result of image, institute according to a segmentation result and secondary splitting result
Segmentation evaluation module is stated for evaluating the segmentation effect of the third processing module.
3. intelligent mobile terminal according to claim 2, which is characterized in that the first processing module be used for image into
The primary segmentation of row, obtains a segmentation result, specially：
Select a threshold value t1, image is divided into two set by its pixel grey scale, all pixels gray scale in each set occurs
Probability and constitute a chance event, define the first segmentation function of image：
In formula, H (t1) indicate image the first segmentation function, piIndicate that image pixel gray level grade is the probability of i-stage, L indicates figure
The series of the gray scale of picture；
The first segmentation function for maximizing image, obtains the optimal threshold T that image is once divided1, once divided according to image best
Threshold value T1Obtain segmentation result F of image1(x, y), wherein (x, y) indicates pixel.
4. intelligent mobile terminal according to claim 3, which is characterized in that the Second processing module includes single treatment
Submodule, after-treatment submodule and submodule is handled three times, the single treatment submodule is described for establishing gray matrix
After-treatment submodule is used to determine that the second segmentation function, the submodule of processing three times are used for according to second according to gray matrix
Segmentation function obtains secondary splitting result.
5. intelligent mobile terminal according to claim 4, which is characterized in that the single treatment submodule is for establishing ash
Matrix is spent, specially：
The image for being L grades for gray scale defines the square formation that gray matrix Z is L × L：Z=[tij]L×L, wherein
In formula, M and N indicate the line number and columns of image respectively, and i and j indicate pixel grey scale, as f (m, n)=i and f (m+1, n)
When=j or f (m, n)=i and when f (m, n+1)=j, βmn=1, otherwise, βmn=0；
Calculate the transition probability matrix of gray scale i to j：
In formula, the gray scale of k and l expression pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810176220.8A CN108563987A (en) | 2018-03-02 | 2018-03-02 | A kind of intelligent mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810176220.8A CN108563987A (en) | 2018-03-02 | 2018-03-02 | A kind of intelligent mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108563987A true CN108563987A (en) | 2018-09-21 |
Family
ID=63531462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810176220.8A Pending CN108563987A (en) | 2018-03-02 | 2018-03-02 | A kind of intelligent mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108563987A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343478A (en) * | 2020-09-30 | 2022-04-15 | 宁波方太厨具有限公司 | Scene recognition method of cleaning robot and cleaning robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419818A (en) * | 2011-10-28 | 2012-04-18 | 中国林业科学研究院资源信息研究所 | LiDAR (Light Detecting and Ranging) data single-tree extraction method with combination of morphological canopy control and watershed |
| CN105654501A (en) * | 2016-02-22 | 2016-06-08 | 北方工业大学 | Self-adaptive image segmentation method based on fuzzy threshold |
| CN106204592A (en) * | 2016-07-12 | 2016-12-07 | 东北大学 | A kind of image level collection dividing method based on local gray level cluster feature |
| CN107493381A (en) * | 2017-08-18 | 2017-12-19 | 李英 | Intelligent mobile terminal |
-
2018
- 2018-03-02 CN CN201810176220.8A patent/CN108563987A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419818A (en) * | 2011-10-28 | 2012-04-18 | 中国林业科学研究院资源信息研究所 | LiDAR (Light Detecting and Ranging) data single-tree extraction method with combination of morphological canopy control and watershed |
| CN105654501A (en) * | 2016-02-22 | 2016-06-08 | 北方工业大学 | Self-adaptive image segmentation method based on fuzzy threshold |
| CN106204592A (en) * | 2016-07-12 | 2016-12-07 | 东北大学 | A kind of image level collection dividing method based on local gray level cluster feature |
| CN107493381A (en) * | 2017-08-18 | 2017-12-19 | 李英 | Intelligent mobile terminal |
Non-Patent Citations (7)
| Title |
|---|
| 刘国英: "一种自适应多尺度分割结果融合新方法", 《安阳师范学院学报》 * |
| 朱秀昌: "《数字图像处理与图像信息》", 31 August 2016 * |
| 薛河儒等: "一种基于数学形态学及融合技术的彩色图像分割方法", 《中国图像图形学报》 * |
| 郑南宁: "《计算机视觉与模式识别》", 31 March 1998 * |
| 阳树洪: "灰度图像阈值分割的自适应和快速算法研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 阳树洪: "灰度图像阈值分割的自适应和快速算法研究", 《中国博士学位论文全文数据库》 * |
| 鱼滨: "《基于MATLAB和遗传算法的图像处理》", 31 October 2015 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114343478A (en) * | 2020-09-30 | 2022-04-15 | 宁波方太厨具有限公司 | Scene recognition method of cleaning robot and cleaning robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101216304B (en) | Systems and methods for object dimension estimation | |
| CN108009515B (en) | Power transmission line positioning and identifying method of unmanned aerial vehicle aerial image based on FCN | |
| CN108711148B (en) | Tire defect intelligent detection method based on deep learning | |
| CN107392965A (en) | A kind of distance-finding method being combined based on deep learning and binocular stereo vision | |
| CN105700525B (en) | Method is built based on Kinect sensor depth map robot working environment uncertainty map | |
| CN109784204A (en) | A kind of main carpopodium identification of stacking string class fruit for parallel robot and extracting method | |
| CN104134216B (en) | The laser point cloud autoegistration method described based on 16 dimensional features and system | |
| CN111899296B (en) | Log volume detection method and device based on computer vision | |
| CN103295239A (en) | Laser-point cloud data automatic registration method based on plane base images | |
| CN103310203B (en) | Pointer type instrument indication value automatic identifying method based on Internet of Things and machine vision | |
| CN110992325A (en) | Target counting method, device and equipment based on deep learning | |
| CN107808376A (en) | A kind of detection method of raising one's hand based on deep learning | |
| CN104463240B (en) | A kind of instrument localization method and device | |
| CN113239916B (en) | Expression recognition and classroom state evaluation method, device and medium | |
| CN113033315A (en) | Rare earth mining high-resolution image identification and positioning method | |
| CN114627502A (en) | Improved YOLOv 5-based target recognition detection method | |
| CN106407908A (en) | Training model generation method and human face detection method and device | |
| CN108563987A (en) | A kind of intelligent mobile terminal | |
| CN113378905B (en) | Small target detection method based on distribution distance | |
| CN107633201A (en) | A kind of answering card intelligent identification Method and system | |
| CN107748621A (en) | A kind of intelligent interaction robot | |
| CN114972335A (en) | Image classification method and device for industrial detection and computer equipment | |
| CN113554070B (en) | Bearing fault diagnosis method based on transition probability matrix and lightweight network | |
| CN113592773B (en) | Wireless acoustic imaging method and device for valve leakage monitoring | |
| CN114627468A (en) | Wheat field obstacle detection method based on generation of confrontation network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180921 |