CN109242824A - A kind of road surface intelligent checking system based on depth image - Google Patents
A kind of road surface intelligent checking system based on depth image Download PDFInfo
- Publication number
- CN109242824A CN109242824A CN201810825711.0A CN201810825711A CN109242824A CN 109242824 A CN109242824 A CN 109242824A CN 201810825711 A CN201810825711 A CN 201810825711A CN 109242824 A CN109242824 A CN 109242824A
- Authority
- CN
- China
- Prior art keywords
- image
- depth image
- depth
- road surface
- processing
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of road surface intelligent checking system based on depth image, comprising: image capture module is directed to the first image and the second image that same road surface to be detected takes for obtaining dual camera;Depth image obtains module, for carrying out matching primitives to the first image and the second image to obtain corresponding depth image;Depth image enhances module, for carrying out image enhancement processing to the depth image;Monitoring modular obtains unevenness, damaged information, and show unevenness, damaged information for being analyzed and processed to the depth image obtained after image enhancement processing.
Description
Technical field
The present invention relates to lane detection technology fields, and in particular to a kind of road surface intelligent measurement system based on depth image
System.
Background technique
Currently, road roughness detection device mainly has response class and two class of section class.Respond the detection of class surface evenness
Equipment and instrument structure is generally relatively simple, cheap, but can not directly acquire vertical section of road surface curve shape, and detected value does not have
Having time stability, and need to often be demarcated.Section class surface evenness detection device can directly acquire vertical section of road surface song
Wire shaped, but section class surface evenness detection device apparatus structure is complicated, it is expensive, and be mostly discrete detection, i.e.,
Several section values along longitudinal direction are taken to measure the flatness value on whole road height, reflection is with an approximation.In addition, mesh
Preceding non-flatness measurement device can only measure unevenness mostly;Or multiple measuring systems are integrated together, to measure simultaneously
Other highway pavement information such as breakage, track.But the information between each system is not shared, there are the wastings of resources, low efficiency
Under problem.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of road surface intelligent checking system based on depth image.
The purpose of the present invention is realized using following technical scheme:
Provide a kind of road surface intelligent checking system based on depth image, comprising:
Image capture module is directed to the first image and second that same road surface to be detected takes for obtaining dual camera
Image;
Depth image obtains module, corresponding to obtain for carrying out matching primitives to the first image and the second image
Depth image;
Depth image enhances module, for carrying out image enhancement processing to the depth image;
Monitoring modular obtains unevenness, breaks for being analyzed and processed to the depth image obtained after image enhancement processing
Damage information, and show unevenness, damaged information.
Preferably, the monitoring modular includes analysis and processing unit and display unit;The analysis and processing unit for pair
The depth image obtained after image enhancement processing is analyzed and processed to obtain unevenness, damaged information;The display unit is used
In the display unevenness, damaged information.
Preferably, described the depth image obtained after image enhancement processing to be analyzed and processed to obtain unevenness, break
Damage information, comprising:
The depth image obtained after enhancing processing is analyzed and handled, road surface three-dimensional data is obtained, forms point cloud battle array
Column simulate the three-D profile on road surface, obtain unevenness, damaged information.
The invention has the benefit that by obtaining depth image, and depth image is analyzed and processed, realize road
The detection of the multinomial information of road surface such as face unevenness, breakage, and unevenness, damaged information are shown by display unit, it can be realized not
Information sharing between homologous ray.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the 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 representation of the road surface intelligent checking system based on depth image of an illustrative embodiment of the invention
Block diagram;
Fig. 2 is the structural schematic block diagram of the monitoring modular of an illustrative embodiment of the invention;
Fig. 3 is the structural schematic block diagram of the depth image enhancing module of an illustrative embodiment of the invention.
Appended drawing reference:
Image capture module 2, depth image obtain module 4, depth image enhancing module 6, monitoring modular 8, first and divide
Unit 60, the second cutting unit 61, first processing units 62, the second processing unit 63, third processing unit 64, analysis processing are single
First 80, display unit 82.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, the embodiment of the invention provides a kind of road surface intelligent checking system based on depth image, comprising:
Image capture module 2, the first image taken for same road surface to be detected for obtaining dual camera and the
Two images;
Depth image obtains module 4, for carrying out matching primitives to the first image and the second image to be corresponded to
Depth image;
Depth image enhances module 6, for carrying out image enhancement processing to the depth image;
Monitoring modular 8, for being analyzed and processed to the depth image obtained after image enhancement processing, acquisition unevenness,
Damaged information, and show unevenness, damaged information.
In one embodiment, as shown in Fig. 2, the monitoring modular 8 includes analysis and processing unit 80 and display unit
82;The analysis and processing unit 80 is for being analyzed and processed to obtain injustice the depth image obtained after image enhancement processing
Degree, damaged information;The display unit 82 is for showing the unevenness, damaged information.In a kind of mode that can be realized,
It is described the depth image obtained after image enhancement processing to be analyzed and processed to obtain unevenness, damaged information, comprising: to increasing
The depth image obtained after the reason of strength is analyzed and is handled, and road surface three-dimensional data is obtained, and is formed point cloud array, is simulated road surface
Three-D profile, obtain unevenness, damaged information.
The above embodiment of the present invention is analyzed and processed depth image by obtaining depth image, realizes road surface
The detection of the multinomial information of road surface such as unevenness, breakage, and unevenness, damaged information are shown by display unit, it can be realized difference
Information sharing between system.
In a kind of optional mode, as shown in figure 3, depth image enhancing module 6 includes:
First cutting unit 60, for being split to the first image to obtain first object image block and the first Background
As block, it is also used to be split the second image to obtain the second target image block and the second background image block;
Second cutting unit 61 obtains target depth image block and background is deep for being split to the depth image
Spend image block;
First processing units 62, for smoothly being located respectively to the first object image block and the first background image block
Combination first image that obtains that treated after reason, be also used to second target image block and the second background image block respectively into
Combination second image that obtains that treated after row smoothing processing;
The second processing unit 63, for treated described in, the first image joins the target depth image block
Close bilateral filtering processing;
Third processing unit 64, for treated to joint bilateral filtering is carried out using treated second image
Depth image block is filtered to obtain described image enhancing treated depth image.
In a kind of mode that can be realized, the first image and the second image are counted using binocular ranging algorithm
Calculation obtains depth image.
Dual camera is a kind of camera group of two cameras composition for simulating eyes imaging, can utilize dual camera
Photo is shot to obtain the depth of view information of two images respectively, generates depth image, however the depth image generated can exist carefully
The not high problem of section enhancing precision.First using treated, the first image carries out depth image block to combine bilateral filter the present embodiment
Wave processing, then to carrying out joint bilateral filtering treated, depth image block is filtered using treated second image
Processing, by way of double-smoothing, the precision for advantageously allowing the details enhancing of depth image is higher, so that depth map
Picture depth is more complete, and image quality more preferably, for the detection of subsequent road pavement provides preferably depth image.
In a kind of mode that can be realized, Steerable filter is all used to first object image block and the second target image block
It is smoothed.In the mode that one kind can be implemented, the first background image block and the second background image block are all used and led
It is smoothed to filtering.
In the mode that one kind can be implemented, the depth image is split, comprising:
(1) first obtained depth image is detected using edge detection algorithm and divides to obtain target depth figure
As block and background depth image block, the target depth image block includes pavement image to be detected;
(2) average depth value of each pixel in the first target depth image block acquiredMaximum depth value Pmax
With minimum depth value Pmin, using the average depth value as pixel depth threshold value;
(3) second or more obtained depth image is split by the way of Threshold segmentation, specifically:
1) depth frame for i-th depth image that reading is calculated, the 2 of i, line position of going forward side by side operates to obtain described i-th
The depth value of each pixel of depth image;
2) depth value of each pixel is compared with the pixel depth threshold value, if the depth value of pixel s meet it is following
Formula then keeps the depth value of pixel s constant, and the depth value of pixel y is otherwise set to 0:
In formula, P0(s) depth value for being pixel s, z are preset regulation coefficient;
3) the corresponding image block of pixel that depth value is 0 is classified as background depth image block, by the corresponding figure of other pixels
As block is classified as target depth image block.
The present embodiment is split processing to first depth image being calculated using edge detection algorithm, and utilizes
Threshold segmentation method is split processing to subsequent depth image, solves pavement image to be detected from depth image
The problem of background separation comes out reduces interference of the background to depth image, while greatly reducing operand;Wherein this implementation
Example applies in subsequent Threshold segmentation according to the depth values data that processing obtains each pixel in first target depth image block,
Using the average value of the depth values data as the pixel depth threshold value of Threshold segmentation, relative to the mode of subjective threshold value, energy
Enough effectively improve image segmentation precision.
In a kind of mode that can be realized, using treated first image to the target depth image block into
Row joint bilateral filtering processing, wherein improving joint bilateral filtering handles formula are as follows:
In formula, P (y) is the depth value that the pixel y in smooth pretreated depth image is carried out to the depth image,
P0It (y) is the depth value of the pixel y before smoothly pre-process to the depth image;P0(yi) it is to the depth
Image carries out the depth value of the pixel yi before smoothly pretreatment, yi∈Nh(y), Nh(y) by center radius of y to be the part of h
Neighborhood;f(yi, y) be joint two-sided filter when not improving weight coefficient, kaIt is poor for the criterion distance based on Gaussian function,
kbPoor, the k for the luminance standard based on Gaussian functiona、kbSpecific value set by expert.
Joint two-sided filter is a kind of to be filtered using high quality reference signal to low quality object signal
Two-sided filter handles image by combining two-sided filter, enables to low-quality signal in high-quality signal
Flat site keeps smooth, and is consistent low-quality signal and high-quality signal in edge details, wherein combining bilateral
The weight coefficient of filter is provided by the product of airspace smooth function and codomain smooth function.
The present embodiment improves the filtering processing formula of joint two-sided filter, in original joint two-sided filter
Exponential function relevant to depth image pixel is increased on the basis of weight coefficient, with weaken on different depth level pixel it
Between correlation.The depth image is smoothly pre-processed using improved joint two-sided filter, advantageously allows depth
The depth value for spending pixel between same depth layer in image is more smooth, thus before remaining the marginal information of depth image
It puts raising and smooth pretreated effect is carried out to depth image, so that filtered image surface is more smooth, edge is changed
It is kind, closer to road surface true form, preferably depth image basis is provided for the subsequent analysis to road surface to be detected.
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 explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of road surface intelligent checking system based on depth image, characterized in that include:
Image capture module is directed to the first image and the second figure that same road surface to be detected takes for obtaining dual camera
Picture;
Depth image obtains module, for carrying out matching primitives to the first image and the second image to obtain corresponding depth
Image;
Depth image enhances module, for carrying out image enhancement processing to the depth image;
Monitoring modular obtains unevenness, damaged letter for being analyzed and processed to the depth image obtained after image enhancement processing
Breath, and show unevenness, damaged information.
2. a kind of road surface intelligent checking system based on depth image according to claim 1, characterized in that the monitoring
Module includes analysis and processing unit and display unit;The analysis and processing unit is used for the depth obtained after image enhancement processing
Image is analyzed and processed to obtain unevenness, damaged information;The display unit is for showing the unevenness, damaged letter
Breath.
3. a kind of road surface intelligent checking system based on depth image according to claim 2, characterized in that described pair of figure
The depth image obtained after image intensifying processing is analyzed and processed to obtain unevenness, damaged information, comprising:
The depth image obtained after enhancing processing is analyzed and handled, road surface three-dimensional data is obtained, forms point cloud array, mould
The three-D profile on road surface is drawn up, unevenness, damaged information are obtained.
4. a kind of road surface intelligent checking system based on depth image according to claim 1, characterized in that the depth
Image enhancement module includes:
First cutting unit, for being split to the first image to obtain first object image block and the first background image block,
It is also used to be split the second image to obtain the second target image block and the second background image block;
Second cutting unit obtains target depth image block and background depth image for being split to the depth image
Block;
First processing units, for being smoothed rear group respectively to the first object image block and the first background image block
Conjunction obtains that treated the first image, is also used to carry out smoothly second target image block and the second background image block respectively
Combination second image that obtains that treated after processing;
The second processing unit, for treated that the first image combine to the target depth image block is bilateral using described
Filtering processing;
Third processing unit, for using treated second image to carrying out joint bilateral filtering treated depth map
As block is filtered to obtain described image enhancing treated depth image.
5. a kind of road surface intelligent checking system based on depth image according to claim 1, characterized in that described
One image and the second image using binocular ranging algorithm carry out that corresponding depth image is calculated.
6. a kind of road surface intelligent checking system based on depth image according to claim 4, characterized in that described in use
Treated, and the first image carries out the processing of joint bilateral filtering to the target depth image block, wherein improving joint bilateral filtering
Handle formula are as follows:
In formula, P (y) is the depth value that the pixel y in smooth pretreated depth image is carried out to the depth image, P0(y)
For the depth value of the pixel y before smoothly pre-process to the depth image;P0(yi) be to the depth image into
Pixel y before the smooth pretreatment of rowiDepth value, yi∈Nh(y), Nh(y) by center radius of y to be the local neighborhood of h;f
(yi, y) be joint two-sided filter when not improving weight coefficient, kaPoor, the k for the criterion distance based on Gaussian functionbFor base
Poor, the k in the luminance standard of Gaussian functiona、kbSpecific value set by expert.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810825711.0A CN109242824A (en) | 2018-07-25 | 2018-07-25 | A kind of road surface intelligent checking system based on depth image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810825711.0A CN109242824A (en) | 2018-07-25 | 2018-07-25 | A kind of road surface intelligent checking system based on depth image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109242824A true CN109242824A (en) | 2019-01-18 |
Family
ID=65072328
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810825711.0A Withdrawn CN109242824A (en) | 2018-07-25 | 2018-07-25 | A kind of road surface intelligent checking system based on depth image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109242824A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110222557A (en) * | 2019-04-22 | 2019-09-10 | 北京旷视科技有限公司 | Real-time detection method, device, system and the storage medium of road conditions |
CN115058947A (en) * | 2022-05-12 | 2022-09-16 | 安徽中青检验检测有限公司 | Roadbed pavement flatness detection device and method |
-
2018
- 2018-07-25 CN CN201810825711.0A patent/CN109242824A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110222557A (en) * | 2019-04-22 | 2019-09-10 | 北京旷视科技有限公司 | Real-time detection method, device, system and the storage medium of road conditions |
CN110222557B (en) * | 2019-04-22 | 2021-09-21 | 北京旷视科技有限公司 | Real-time road condition detection method, device and system and storage medium |
CN115058947A (en) * | 2022-05-12 | 2022-09-16 | 安徽中青检验检测有限公司 | Roadbed pavement flatness detection device and method |
CN115058947B (en) * | 2022-05-12 | 2024-02-09 | 安徽中青检验检测有限公司 | Roadbed and pavement flatness detection device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102013210153B4 (en) | Techniques for producing robust stereo images | |
CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
CN108764071B (en) | Real face detection method and device based on infrared and visible light images | |
CN107369159B (en) | Threshold segmentation method based on multi-factor two-dimensional gray level histogram | |
CN102682446B (en) | Adaptive combined two-sided filter is used to generate equipment and the method for dense depth map | |
Vaudrey et al. | Differences between stereo and motion behaviour on synthetic and real-world stereo sequences | |
CN102006425B (en) | Method for splicing video in real time based on multiple cameras | |
CN104850850B (en) | A kind of binocular stereo vision image characteristic extracting method of combination shape and color | |
CN104408724B (en) | Froth flotation level monitoring and operating mode's switch method and system based on depth information | |
CN104597057B (en) | A kind of column Diode facets defect detecting device based on machine vision | |
CN109636732A (en) | A kind of empty restorative procedure and image processing apparatus of depth image | |
CN104048969A (en) | Tunnel defect recognition method | |
CN102903098A (en) | Depth estimation method based on image definition difference | |
CN107687819A (en) | A kind of optical losses sub-pixel extraction of quick high accuracy | |
CN105719250A (en) | Image inpainting method based on simple background, system and shooting camera | |
CN104517095A (en) | Head division method based on depth image | |
CN113744315B (en) | Semi-direct vision odometer based on binocular vision | |
CN109840463A (en) | A kind of Lane detection method and apparatus | |
CN204039886U (en) | A kind of pavement damage crack detection system based on multiple stage camera stereoscopic shooting | |
CN111383257A (en) | Method and device for determining loading and unloading rate of carriage | |
CN109242824A (en) | A kind of road surface intelligent checking system based on depth image | |
CN101887579B (en) | Underwater image restoration method based on scattering model | |
CN111681275B (en) | Double-feature-fused semi-global stereo matching method | |
CN113554646A (en) | Intelligent urban road pavement detection method and system based on computer vision | |
CN112465778A (en) | Underwater fish shoal observation device and method |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190118 |
|
WW01 | Invention patent application withdrawn after publication |