CN107092908B - Automatic identification method based on plane embossed characters on train bogie - Google Patents
Automatic identification method based on plane embossed characters on train bogie Download PDFInfo
- Publication number
- CN107092908B CN107092908B CN201710439795.XA CN201710439795A CN107092908B CN 107092908 B CN107092908 B CN 107092908B CN 201710439795 A CN201710439795 A CN 201710439795A CN 107092908 B CN107092908 B CN 107092908B
- Authority
- CN
- China
- Prior art keywords
- character
- character image
- industrial camera
- module
- plane
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/145—Illumination specially adapted for pattern recognition, e.g. using gratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention discloses an automatic identification method based on plane embossed characters on a train bogie. The technical scheme adopted by the invention for solving the technical problems is as follows: the method comprises the following steps that 2 identical LED lamps are respectively installed on rotary supports of 2 identical piston rods, when the 2 LED lamps simultaneously irradiate a plane embossed character area of a train bogie, reflected light rays generated in the character background area cannot effectively enter a CMOS industrial camera, only part of diffuse reflection light rays enter the CMOS industrial camera, and meanwhile, due to the fact that the plane embossed characters have height difference, the reflected light rays generated by the character height just enter the CMOS industrial camera, so that the contrast ratio of a character outline and the character background outline is improved in the CMOS industrial camera, and a character image is formed; the CMOS industrial camera collects the character image signals and transmits the character image signals to the industrial personal computer for processing, and the industrial personal computer transmits the character image signals to the LED display screen for displaying after processing.
Description
Technical Field
The invention relates to an automatic identification method based on plane embossed characters on a train bogie.
Background
Characters on a train bogie are embossed characters, and workers have long adopted manual recognition for recognizing such characters, namely, the characters are registered by a pen while being observed by human eyes. This manual identification method is not only inefficient, but also easily identifies the wrong character.
The embossed characters on the train bogie are concave-convex characters, and have the following characteristics: the character is convex or concave and is a three-dimensional character; the material of the embossed characters is the same as that of the background, and no color difference exists; the embossed characters are imaged through reflection difference; the size of characters is generally small. Obviously, the existing character recognition method can not effectively recognize the embossed characters on the train bogie, so that a scientific, accurate, rapid and automatic recognition method needs to be developed, and the following problems are mainly solved:
(1) automaticity: the plane impression character on the train bogie can be automatically identified, and errors caused by manual identification are eliminated.
(2) The accuracy is as follows: the plane embossed characters on the train bogie can be accurately identified.
(3) Ease of use: the operation is simple, and the character display interface is visual.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an automatic identification method based on plane embossed characters on a train bogie, and the identification method can accurately identify the plane embossed characters on the train bogie.
The technical scheme adopted by the invention for solving the technical problems is as follows: in order to overcome the error brought by the manual identification of the plane embossed characters of the existing train bogie, the invention is based on the principle that 2 identical LED lamps are respectively arranged on 2 identical rotary supports of piston rods, when the 2 LED lamps simultaneously irradiate the plane embossed character area of the train bogie, the reflected light generated in the character background area can not effectively enter a CMOS industrial camera, only part of diffuse reflected light enters the CMOS industrial camera, and meanwhile, because the plane embossed characters have height difference, the reflected light generated by the character height just enters the CMOS industrial camera, thereby improving the contrast ratio of the character outline and the character background outline in the CMOS industrial camera and forming a character image; the CMOS industrial camera collects the character image signals and transmits the character image signals to the industrial personal computer for processing, and the industrial personal computer transmits the character image signals to the LED display screen for displaying after processing.
Compared with the prior art, the invention has the beneficial effects that:
(1) the method can continuously and effectively automatically identify the plane embossed characters on the train bogie in real time on site at high efficiency, and eliminates errors caused by manual identification.
(2) The biggest difference between the invention and the prior art is that 2 LED lamps are adopted to generate a low-angle lighting mode, so that the contrast between the flat embossed character outline collected by the camera and the character background outline is large, and the finally identified character image is more vivid.
(3) The invention has simple identification principle, high efficiency and visual display interface which is easy to observe.
Drawings
The structure of the invention is schematically shown in fig. 1 and fig. 2.
Reference numerals: the device comprises a CMOS industrial camera [1], a shell [2], a plane stamping character [3] on a train bogie, an LED lamp [4], a rotary support [5], a piston rod [6], a rod body [7], a rotary button [8], a screw [9], a support rod [10], a handle [11], an LED display screen [12], an industrial personal computer [13] provided with character and image processing software, a PCI slot [14] and an image acquisition card [15 ].
Detailed Description
The invention is described in further detail below with reference to the following figures and detailed description:
as shown in figures 1 and 2, the invention comprises a CMOS industrial camera [1], a shell [2], 2 LED lamps [4], 2 rod structures, a support rod [10], an LED display screen [12], an industrial personal computer [13] provided with character image processing software and an image acquisition card [15 ].
Embodiment 1, a plane impression character automatic identification method based on train bogie, the identification method is realized by character recognition instrument, the character recognition instrument is composed of CMOS industrial camera [1], shell [2], 2 LED lamps [4], 2 rod structure, support rod [10], LED display screen [12], industrial computer [13] with character image processing software, image acquisition card [15 ]; the LED lamp comprises a shell, 2 LED lamps, a lamp holder and a lamp holder, wherein the 2 LED lamps are respectively arranged on 2 same rod piece structures, and the 2; the rod piece structure is connected with the shell through a screw [9], one end of the supporting rod is fixed on the shell, and the other end of the supporting rod is connected with the rod piece body [7] and used for supporting the rod piece structure; the shell is provided with 2 symmetrical handles [11], a CMOS industrial camera is arranged in the shell, and the end part of the shell is connected with the LED display screen.
Embodiment 2, a method for automatically recognizing flat embossed characters based on a train bogie, wherein: the rod piece structure comprises a rotary support [5], a piston rod [6], a rod piece body [7] and a rotary button [8], wherein a hydraulic structure is arranged in the rod piece body, and the change of the hydraulic structure in the rod piece body can be controlled by controlling the rotation of the rotary button so as to further control the extension and retraction of the piston rod; the rotary support is used for mounting the LED lamp, the rotation of the LED lamp in a plane where the center of the piston rod is located can be realized, the rotation angle is 0-180 degrees, the included angle between the LED lamp and the character background plane is a variable inclination angle, and the inclination angle is 20-45 degrees; the purpose of the 2 bar structure arrangement is to enable the 2 LED lights to produce a low angle illumination pattern at the flat embossed characters on the train bogie, the incident angle between the incident light generated by the illumination mode and the character background area is small, so that the reflected light generated by the character background area can not effectively enter the CMOS industrial camera [1] for imaging, only part of the diffuse reflected light enters the CMOS industrial camera, and because the height difference exists between the plane embossed characters on the train bogie and the character background area, when the low-angle light emitted by the LED lamp irradiates the characters, the reflected light generated by the height difference will enter the CMOS industrial camera more, and thus, the contrast between the character area and the character background area can be improved when imaging is carried out in the CMOS industrial camera, and the more vivid embossed plane character image on the train bogie can be obtained finally.
Embodiment 4, a method for automatic recognition of flat embossed characters based on a train bogie, wherein: the CMOS industrial camera [1] is internally provided with a wireless transmitting module, and is used for shooting a plane embossed character image of the train bogie and transmitting a character image signal acquired by the CMOS industrial camera to a wireless receiving module through the wireless transmitting module.
Embodiment 5, a method for automatic recognition of flat embossed characters based on a train bogie, wherein: the industrial personal computer [13] is internally provided with a wireless receiving module which is used for receiving character image signals sent by the wireless transmitting module. The image acquisition card [15] is installed in a PCI slot [14] of the industrial personal computer, and has the function of acquiring the train bogie plane embossed character image information received by the wireless receiving module and inputting the information into the industrial personal computer in the form of digital images for processing the character images.
The character image enhancement module adopts a gray level conversion enhancement method to expand the contrast of the character image, so that the image is clearer. Converting the gray value f (x, y) of each pixel (x, y) in the input character image into a gray value g (x, y) output through a mapping function T, namely:
g(x,y)＝T[f(x,y)]
assuming that the gray-scale value range of f (x, y) is mostly in the interval [ a, b ], and it is desired that the gray-scale value of g (x, y) is extended to [ c, d ], and M is the maximum gray-scale value in the original image, the following formula can be used to implement:
the character image segmentation module adopts a Canny operator edge extraction method firstly and then carries out binarization.
Since most of the information of the character image is concentrated in the character edge part, it is necessary to process the character image by a method based on Canny operator edge extraction. The basic principle of Canny operator edge extraction is as follows:
step 1: selecting one-dimensional Gaussian function
And carrying out smooth denoising on the character image f (x, y).
Step 2: calculating the magnitude of the gradient
Gradient direction theta [ i, j ]]＝arctan(Py[i,j]/Px[i,j])
Wherein P isx[i,j]＝(I[i,j+1]-I[i,j]+I[i+1,j+1]-I[i+1,j])/2
Py[i,j]＝(I[i,j]-I[i+1,j]+I[i,j+1]-I[i+1,j+1])/2。
And step 3: and carrying out non-maximum suppression on the gradient amplitude, namely refining the gradient amplitude map.
And 4, step 4: after the non-maximum value suppression is carried out on the gradient amplitude, 2 high and low threshold values are adopted for the sub-images classified by the gradient histogram, wherein the character edge is determined to be larger than the high threshold value, and the character edge is not determined to be smaller than the low threshold value. If the detection result is between the two thresholds, then the neighboring pixels to the pixel have no edge pixels that exceed the high threshold, if any, it is an edge, otherwise it is not.
The binarization method of the characters comprises the steps of firstly detecting edge characteristics of an image by using a Canny edge detection operator, and then realizing binarization processing of different pixel points according to the spatial position relation of the edge pixel points. If the image point is a boundary pixel point, a local threshold value method is adopted to determine a threshold value, and if the image point is a non-boundary pixel point, an iteration method is adopted to determine an optimal global threshold value method to carry out binarization processing.
The character image tilt correction module firstly adopts Radon transformation to carry out horizontal tilt correction, and the main steps comprise: (1) performing edge detection on the image by using a Canny operator, projecting the image after the edge detection on the image at 0-180 degrees by using Radon transformation, and calculating to obtain an angle theta when the sum of projected non-zero values reaches a maximum value; (2) according to the Radon transformation principle, a horizontal inclination angle is obtained by subtracting theta from 90 degrees, theta is taken as a rotation angle, and the image is horizontally rotated by taking the central point of the image as an origin. Quick reuseThe character image is subjected to vertical inclination angle detection by a Radon transformation method to obtain theta1And theta2. If theta1-θ2If | is less than T, then
And vertically correcting the character by theta; if theta1-θ2If the value is greater than T, adopting a rotating projection method to detect the vertical inclination angle and vertically correct the character image, and finally obtaining a corrected image.
The character image segmentation module adopts a single character segmentation method based on maximum variance, the change of the gradient value of a character area is obviously larger than that of a background area due to the influence of fluctuation of character strokes, and the gradient characteristics of an image are utilized to segment an embossed character area first and then perform column segmentation. The line segmentation step is to adopt gradient operator G ═ 101]Solving a gradient image of the image in the horizontal direction, calculating the variance of each row of the gradient image, performing thresholding processing on the variance, and obtaining the boundary of each row through a thresholding result so as to realize row segmentation; column segmentation is performed by using vertical gradient operator G ═ 101]TAnd solving a gradient image of the image in the vertical value direction, calculating the variance of each column of the gradient image, thresholding the variance, and obtaining the boundary of each column through a thresholding result, thereby realizing column segmentation.
The character image normalization module performs embossed character normalization processing by adopting a method based on bilinear interpolation, wherein g (x) in the bilinear interpolation0，y0) The gray values of (m, n) adjacent four network points (i +1, j +1), (i +1, j), (i, j) are determined according to the following formula: g (x)0，y0) In the formula of f (i, j) (1-a) (1-b) + f (i, j +1) b (1-a) + f (i +1, j) a (1-b) + f (i +1, j +1) ab, i, j is a non-negative integer, a is m-i, and b is n-j.
The character image feature extraction module is a method for extracting features of embossed characters based on gray images by utilizing a Gabor filter, firstly, the Gabor filter extracts local stroke features of the characters, and the purpose is to establish an invariant Gabor feature. If I (x, y) represents the initial image of the character and I (x, y) represents the image output after the Gabor filter processing, then
The character image recognition module adopts a three-layer BP neural network method for recognition and comprises an input layer, a hidden layer and an output layer; the input vector is X ═ X1，x2，x3，，…xr)TThe hidden layer output vector is O ═ O1,o2…oc)TFor the output layer, there is ok＝f(netk)，netk＝∑wjkojWherein k is 1,2,3, … c; j ═ 1,2,3, …, c; for the hidden layer, there is ok＝f(netj)，netj＝∑vijxiWherein k is 1,2,3, … c; 1,2,3, …, j 1,2,3, …, s; transformation function
Or is
And f (x) is continuous and conductive.
Embodiment 7, a method for automatic recognition of flat embossed characters based on a train bogie, wherein: the industrial personal computer is provided with a wireless transmitting module 2, and the module can transmit the processed character image signals to a wireless receiving module 2.
Embodiment 8, a method for automatic recognition of flat embossed characters based on a train bogie, wherein: the LED display screen [12] is provided with a wireless receiving module 2, can receive character image signals transmitted by the wireless transmitting module 2, and displays the character image signals on the LED display screen.
The working method of the invention is as follows:
before identifying the plane embossed characters on the train bogie, preparation is made, an operator firstly aligns the front end of the CMOS industrial camera with the plane embossed characters [3] on the train bogie and keeps a proper distance (30-50 cm), then rotates a rotary button downwards to increase the hydraulic pressure in the rod piece body, a piston rod extends outwards, and then adjusts a rotary support to enable an LED lamp and a character background plane to form a low angle which is generally between 20 degrees and 45 degrees. The CMOS industrial camera is provided with a wireless transmitting module inside, and the digital image signals are transmitted into a wireless receiving module by the wireless transmitting module. The wireless receiving module is arranged in the industrial personal computer, the image acquisition card is arranged in a PCI slot of the industrial personal computer, and after the wireless receiving module receives the character image signal, the image acquisition card acquires character image information and inputs the character image information into the industrial personal computer for character image processing. After the processing is finished, the processed character image signals are transmitted to the wireless receiving module 2 through the internal wireless transmitting module 2 of the industrial personal computer, the wireless receiving module 2 is arranged in the LED display screen, and finally, the character image information is displayed through the LED display screen.
The invention has wide universality and can automatically and quickly identify the plane embossed characters on the train bogie.
The invention has been described above with reference to the accompanying drawings, it is obvious that the invention is not limited to the above-described embodiments, and it is within the scope of the invention to use the method concept and solution of the invention in various modifications or to apply it directly to other applications without modification.
Claims (2)
1. A plane impression character automatic identification method based on train bogie, the identification method is realized by character identification instrument, the character identification instrument is composed of CMOS industrial camera [1], shell [2], 2 LED lamps [4], 2 rod structure, support rod [10], LED display screen [12], industrial computer [13] with character image processing software, image acquisition card [15 ]; the LED lamp comprises a shell, 2 LED lamps, a lamp holder and a lamp holder, wherein the 2 LED lamps are respectively arranged on 2 same rod piece structures, and the 2; the rod piece structure is connected with the shell through a screw [9], one end of the supporting rod is fixed on the shell, and the other end of the supporting rod is connected with the rod piece body [7] and used for supporting the rod piece structure; 2 symmetrical handles [11] are arranged on the shell, a CMOS industrial camera is arranged in the shell, and the end part of the shell is connected with the LED display screen;
the CMOS industrial camera [1] is internally provided with a wireless transmitting module, the CMOS industrial camera shoots a plane embossed character image of a train bogie, then character image signals acquired by the CMOS industrial camera are input into an industrial personal computer [13] through the wireless transmitting module, the industrial personal computer [13] comprises seven character image processing modules, namely a character image enhancing module, a character image dividing module, a character image inclination correcting module, a character image dividing module, a character image normalizing module, a character image characteristic extracting module and a character image identifying module, the industrial personal computer receives the character image signals output by the image acquisition card [15], then the character image signals are sequentially input into the modules for processing, and the processed character image signals are transmitted to an LED display screen [12] for display.
2. The automatic identification method based on the plane embossed characters on the train bogie as claimed in claim 1, wherein: the rod piece structure comprises a rotary support [5], a piston rod [6], a rod piece body [7] and a rotary button [8], wherein a hydraulic structure is arranged in the rod piece body, and the change of the hydraulic structure in the rod piece body can be controlled by controlling the rotation of the rotary button so as to further control the extension and retraction of the piston rod; the rotary support is used for mounting the LED lamp, so that the rotation of the LED lamp in the plane where the center of the piston rod is located can be realized, and the included angle between the LED lamp and the character background plane is a variable inclined angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710439795.XA CN107092908B (en) | 2017-06-12 | 2017-06-12 | Automatic identification method based on plane embossed characters on train bogie |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710439795.XA CN107092908B (en) | 2017-06-12 | 2017-06-12 | Automatic identification method based on plane embossed characters on train bogie |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107092908A CN107092908A (en) | 2017-08-25 |
| CN107092908B true CN107092908B (en) | 2020-01-07 |
Family
ID=59640658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710439795.XA Expired - Fee Related CN107092908B (en) | 2017-06-12 | 2017-06-12 | Automatic identification method based on plane embossed characters on train bogie |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107092908B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112070678B (en) * | 2020-08-10 | 2023-04-11 | 华东交通大学 | Batch Western blot membrane strip inclination correction and segmentation method and system |
| CN117523543B (en) * | 2024-01-08 | 2024-03-19 | 成都大学 | Metal stamping character recognition method based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663386A (en) * | 2012-03-27 | 2012-09-12 | 江南大学 | Online detection method of mechanical-bearing annular-distributed pressed character |
| CN203760430U (en) * | 2013-11-22 | 2014-08-06 | 中航（重庆）微电子有限公司 | Automatic identification system for marking numbers on the wafers |
| CN204256752U (en) * | 2014-11-28 | 2015-04-08 | 北京中远通科技有限公司 | A kind of stereo identification character automatic identification equipment |
| CN207051928U (en) * | 2017-06-12 | 2018-02-27 | 华东交通大学 | A kind of plane pressed characters automatic identification equipment based on train bogie |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8942420B2 (en) * | 2012-10-18 | 2015-01-27 | Qualcomm Incorporated | Detecting embossed characters on form factor |
-
2017
- 2017-06-12 CN CN201710439795.XA patent/CN107092908B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663386A (en) * | 2012-03-27 | 2012-09-12 | 江南大学 | Online detection method of mechanical-bearing annular-distributed pressed character |
| CN203760430U (en) * | 2013-11-22 | 2014-08-06 | 中航（重庆）微电子有限公司 | Automatic identification system for marking numbers on the wafers |
| CN204256752U (en) * | 2014-11-28 | 2015-04-08 | 北京中远通科技有限公司 | A kind of stereo identification character automatic identification equipment |
| CN207051928U (en) * | 2017-06-12 | 2018-02-27 | 华东交通大学 | A kind of plane pressed characters automatic identification equipment based on train bogie |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107092908A (en) | 2017-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN105869160B (en) | The method and system of three-dimensional modeling and holographic display are realized using Kinect | |
| CN111080724A (en) | Infrared and visible light fusion method | |
| CN105147311B (en) | For the visualization device sub-scanning localization method and system in CT system | |
| JP2019514123A5 (en) | ||
| CN104075965B (en) | A kind of micro-image grain graininess measuring method based on watershed segmentation | |
| CN106228513A (en) | A kind of Computerized image processing system | |
| JP2013089252A (en) | Video processing method and device | |
| CN103971126A (en) | Method and device for identifying traffic signs | |
| CN104361314A (en) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion | |
| CN103218605A (en) | Quick eye locating method based on integral projection and edge detection | |
| CN102860814B (en) | OCT (Optical Coherence Tomography) synthetic fundus image optic disc center positioning method and equipment | |
| CN103852060A (en) | Visible light image distance measuring method based on monocular vision | |
| CN109191520B (en) | Plant leaf area measuring method and system based on color calibration | |
| CN109978940A (en) | A kind of SAB air bag size vision measuring method | |
| CN107092908B (en) | Automatic identification method based on plane embossed characters on train bogie | |
| CN105957116B (en) | A kind of design and coding/decoding method of the dynamic coding point based on frequency | |
| CN103914829B (en) | Method for detecting edge of noisy image | |
| CN111157532A (en) | Visual detection device and method for scratches of mobile phone shell | |
| US9204130B2 (en) | Method and system for creating a three dimensional representation of an object | |
| CN109889799B (en) | Monocular structure light depth perception method and device based on RGBIR camera | |
| CN111105493A (en) | Human hand three-dimensional acquisition method based on multi-view stereoscopic vision | |
| CN105758337B (en) | A method of obtaining angle between lens plane and image sensor plane | |
| Petrovai et al. | Obstacle detection using stereovision for Android-based mobile devices |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200107 Termination date: 20200612 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |