CN103927526A - Vehicle detecting method based on Gauss difference multi-scale edge fusion - Google Patents
Vehicle detecting method based on Gauss difference multi-scale edge fusion Download PDFInfo
- Publication number
- CN103927526A CN103927526A CN201410181851.0A CN201410181851A CN103927526A CN 103927526 A CN103927526 A CN 103927526A CN 201410181851 A CN201410181851 A CN 201410181851A CN 103927526 A CN103927526 A CN 103927526A
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- difference
- gaussian
- scale
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a vehicle detecting method based on Gauss difference multi-scale edge fusion. The method includes the steps that Gauss scale transformation is performed on images to obtain four Gauss images in adjacent scales; according to the four Gauss images in the adjacent scales, the difference operation is performed between the images in the adjacent scales to obtain three Gauss difference images different in scale, edge detection is performed on the obtained three Gauss difference images through a Sobel operator, then edge fusion with the scale upward searching is performed to remove a lot of background edges while edge information of a vehicle is obtained as much as possible, and expansion, closed operation, hole filling and other series of morphological operation are performed on the fused edge images to obtain a connected domain image representing the vehicle; an outside rectangle of the position where the vehicle is located is determined in the original image according to the position information of a connected domain to detect the vehicle. The images in multiple scales are processed, so that algorithm complexity is reduced, operation amount is reduced, efficiency of vehicle detection is effectively improved, and a good detection result is obtained.
Description
Technical field
The invention belongs to video detection field, be specifically related to a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge.
Background technology
Moving object detection is a gordian technique of computer vision and image model identification.Vehicle detection technology based on vision is the study hotspot of intelligent transportation image processing, has a wide range of applications at intelligent transportation field, and as vehicle DAS (Driver Assistant System), traffic parameter statistical system etc.
Vehicle checking method based on computer vision is broadly divided into three classes: based on model, based on neural network learning, based on the method for feature.Thereby the detection method based on model is mated with the auto model of setting up in advance in Computer Database the candidate's vehicle region detecting detect vehicle, but the shortcoming of the method is to place one's entire reliance upon all variety classes vehicles are carried out to Geometric Modeling, this is to be difficult to realize.
Based on study detection method by using sample to train neural network, carry out vehicle identification with the network that trains, the method is through being usually used in verifying the testing result of additive method.The local feature that method based on feature is passed through to detect vehicle is as symmetrical parts (wheel, head lamp, taillight etc.), edge and shade etc., thus positioned vehicle.The advantage of the method be with vehicle under most of environment all recognizable feature detect vehicle, the be applicable to sleet sky vehicle detection problem at night even.By the impact of problems such as detecting the method that wheel realizes vehicle detection and be easily subject to Vehicle Driving Cycle attitude, block, and method by detecting car light is also disturbed by street lamp and urban lighting in night scene, affects testing result.And vehicle checking method based on rim detection (comprise vehicle shadow detect) is because the existence of background edge (as lane line, railing, trees etc.) causes the inaccurate of testing result, therefore, how to detect to greatest extent vehicle edge and suppress figure viewed from behind edge simultaneously, become the key issue that improves the method Detection accuracy.
Summary of the invention
The object of the invention is to overcome the problems of the prior art, a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge is provided, and the method has reduced algorithm complex, has reduced calculated amount, obtain good testing result, effectively improved detection efficiency.
To achieve these goals, the present invention takes following technical solution to be achieved:
Step 1, gathers certain road section traffic volume video, to the piece image gray processing in video and carry out gaussian pyramid multi-scale transform, utilizes the gaussian kernel of four adjacent scale parameters and image to carry out convolution algorithm, obtains the Gaussian image G of four adjacent yardsticks
l, wherein l represents four adjacent yardsticks, l=1,2,3,4;
Step 2, to the Gaussian image G of these four adjacent yardsticks
lcarry out adjacent scalogram as calculus of differences, obtain the difference of Gaussian image D of three adjacent yardsticks
l, the yardstick of three these difference images of panel height is respectively: σ, 2 × σ, 2 × 2 × σ; Wherein l=1,2,3, σ is smoothing parameter;
Step 3, this difference image of three panel heights D that step 2 is obtained
ladopt Sobel operator to carry out rim detection, calculate the gradient magnitude of each pixel on level, vertical both direction in difference image, and threshold value T is set
1, retain gradient magnitude and be greater than T
1pixel, this pixel is marginal point to establish its gray-scale value be 255, otherwise is made as 0, obtains the rim detection binary map E of corresponding three adjacent yardsticks
l, wherein l=1,2,3;
Step 4, to three width two-value outline map E of corresponding three different scales
lcarry out multi-scale edge fusion, wherein, l=1,2,3, concrete steps are:
(1) under four adjacent yardstick l, search for the difference of Gaussian image D of three adjacent yardsticks
ledge image E
lin each edge pixel, because the edge dislocation between adjacent yardstick is no more than 1, the difference Gaussian image D that is l-1 at yardstick
l-1edge image in to search for corresponding area be 3 × 3 region, all marginal points that occur in this region are all labeled as marginal point, obtain candidate's edge image;
(2) l=l-1; If l>1 jumps to step (1), otherwise execution step (3);
(3) when l=1, edge image E
lit is the edge image after merging;
Step 5, the edge image after the fusion that step 4 is obtained adopts expansion template to carry out morphology processing, setting threshold T
2, connect pel spacing and be less than threshold value T
2marginal point or line, obtain continuous boundary; Carry out again closing operation of mathematical morphology, make hole and the crack of edge image up, the edge image that obtains being further closed; Fill the interior void filling of enclosed region finally by crossing image, form complete connected region;
Step 6, carries out mark to connected region, calculates the area of each connected region, and area threshold T is set
3, reject area and be less than area threshold T
3connected domain; The coordinate of determining the minimum boundary rectangle of each connected domain according to connected domain coordinate finally shows in original-gray image, completes the detection to vehicle.
Described step 1 mesoscale determines jointly by smoothing parameter σ and smoothing parameter k, and k is determined by parameter s, and k=2^ (1/S), S+3=N, wherein N is the Gauss's picture number in the every one deck of gaussian pyramid, gets N=4, S=1, σ=0.5, k=2, four adjacent yardsticks are respectively σ, k σ, 2k σ, 3k σ.
In described step 3, the template of Sobel operator horizontal direction is (1,0,1;-2,0,2;-1,0,1), vertical direction template is (1 ,-2 ,-1; 0,0,0; 1,2,1), threshold value T
1obtained by maximum variance between clusters.
In described step 5, bulging die board size is 3 × 3, and form closed operation template size is 8 × 8, T
2span is 1～8, and taking pixel as unit.
In described step 6, the setting up procedure of area threshold is: the area to the n of a mark connected domain sorts, using largest connected territory area 1/4 as area threshold.
Compared with prior art, the beneficial effect that the present invention has: the invention discloses a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge, first utilize gaussian kernel and the image of four adjacent scale parameters to carry out convolution algorithm, obtain the Gaussian image of four adjacent yardsticks.Then the Gaussian image of these four adjacent yardsticks is carried out to difference, obtain the difference of Gaussian image of three adjacent yardsticks and adopt Sobel operator to carry out rim detection to it.Then the edge image that detects the three width different scales that obtain is carried out to the Fusion Edges that yardstick is upwards searched for, obtain vehicle edge information as much as possible and remove a large amount of background edge simultaneously.Again to the edge image merging expand, a series of morphological operations such as closed operation, hole filling, obtain representing the connected domain image of vehicle.Finally in original image, determine the extraneous rectangle of vehicle position according to the positional information of connected domain, realize vehicle detection.The present invention processes the multi-scale image of non-sampling, has avoided the marginal information disappearance that image interpolation arithmetic causes or has occurred pseudo-edge; Adopt method that multi-scale edge image upwards searches for fusion Background suppression edge in obtaining more multiple edge information.The method has reduced algorithm complex, has reduced calculated amount, can effectively improve the efficiency of vehicle detection, obtains good testing result.
Brief description of the drawings
Fig. 1 is gray level image to be detected;
Fig. 2～4 are difference of Gaussian images of three adjacent yardsticks;
Fig. 5 is Sobel operator template;
Fig. 6 is the edge detection results under yardstick 1;
Fig. 7 is the edge image after merging;
Fig. 8 is the connected domain image that morphology closed operation obtains;
Fig. 9 is the complete connected domain image obtaining after hole is filled;
Figure 10 is the connected domain image that represents vehicle;
Figure 11 is rainy day vehicle detection result.
Figure 12 is fine day vehicle detection result.
Figure 13 is the vehicle detecting algorithm process schematic diagram that difference of Gaussian multi-scale edge merges.
Embodiment
The present invention provides a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge, one width size is carried out to rim detection for W × H vehicle image under multiple dimensioned, marginal position information after Multiscale Fusion is determined vehicle location, thereby realizes vehicle detection.
Below in conjunction with accompanying drawing, the present invention is described in detail, and referring to Figure 13, method of the present invention is concrete adopts following step to realize:
Step 1, gathers certain road section traffic volume video, gathers the vehicle image I that a width size is 517 × 363 in video, and its gray processing is obtained to gray scale figure, then carries out gaussian pyramid multi-scale transform.Utilize four gaussian kernel G and the image I of adjacent scale parameter to carry out convolution algorithm, obtain the non-sampling Gaussian image G of four adjacent yardsticks
l(l=1,2,3,4), wherein l represents four adjacent yardsticks.
Yardstick is determined jointly by smoothing parameter σ and smoothing parameter k, and smoothing parameter k is determined by parameter s.K=2^ (1/S), S+3=N, wherein N is the Gauss's picture number (according to Lowe paper) in the every one deck of gaussian pyramid, in the present invention, get N=4, S=1, σ=0.5, k=2, gets σ=0.5, S=1, k=2, four adjacent yardsticks are respectively σ, k σ, 2k σ, 3k σ, i.e. σ, 2 × σ, 2 × 2 × σ, 3 × 2 × σ.
Step 2, identical without the size of down-sampling to this four width, the Gaussian image G that yardstick is different
l(l=1,2,3,4) carry out adjacent scalogram as calculus of differences, obtain the difference of Gaussian image D of three adjacent yardsticks
l, wherein, l=1,2,3 and the yardstick of three these difference images of panel height be respectively: σ, 2 × σ, 2 × 2 × σ.
Step 3, this difference image of three panel heights D that step 2 is obtained
ladopt respectively Sobel operator to carry out rim detection.Sobel operator, by calculating the gradient magnitude of each pixel on level, vertical both direction in difference image, adopts maximum between-cluster variance (OTSU) method that threshold value T is set
1, retain gradient magnitude and be greater than T
1pixel be marginal point and be set to 1, otherwise be set to 0, obtain the edge detection graph E of corresponding three different scales
l(l=1,2,3).
The template of Sobel operator horizontal direction is (1,0,1;-2,0,2;-1,0,1), vertical direction template is (1 ,-2 ,-1; 0,0,0; 1,2,1).
Step 4, to three width edge-detected image E
l(l=1,2,3) carry out multi-scale edge fusion, and step is:
(1) under yardstick l, search for difference Gaussian image D
ledge image E
lin each edge pixel, because the edge dislocation between adjacent yardstick is no more than 1, the difference Gaussian image D that is l-1 at yardstick
l-1edge image in to search for corresponding area be 3 × 3 region, all marginal points that occur in this region are all labeled as marginal point, obtain candidate's edge image;
(2) l=l-1; If l>1 jumps to step (1), otherwise execution step (3);
(3) when l=1, edge image E
lbe the edge image obtaining after fusion.
Step 5, the edge image that step 4 is obtained adopts expansion template to carry out morphology processing, is called lines and expands processing, connects pel spacing and is less than threshold value T
2marginal point or line, obtain continuous boundary.Carry out again closing operation of mathematical morphology, make hole and the crack of edge image up, the edge image that obtains being further closed.Finally by crossing image filling, the interior void of enclosed region is filled, form complete connected region.
Wherein, bulging die board size is 3 × 3, and form closed operation template size is 8 × 8, T
2=1～8 (taking pixels as unit).
Step 6, carries out mark and calculates the area of each connected region connected region, and area threshold T is set
3, be less than area threshold T
3connected domain be considered as background area and disallowable.The coordinate of determining the minimum boundary rectangle of each connected domain according to connected domain coordinate finally shows in original-gray image, completes the detection to vehicle.
Wherein, area threshold T
3setting: the area to the N of a mark connected domain sorts, get largest connected territory area 1/4 as area threshold.
Below provide specific embodiments of the invention, it should be noted that the present invention is not limited to following specific embodiment, every equal conversion of doing on the application's scheme basis all falls into protection scope of the present invention.
Embodiment:
The gray processing that gathers a width size and be 517 × 363 rainy day traffic images obtains gray-scale map, as shown in Figure 1, choose scale parameter σ=0.5, k=2, be respectively σ, 2 × σ, 2 × 2 × σ with yardstick, four gaussian kernel of 3 × 2 × σ are carried out convolution algorithm with gray-scale map respectively, obtain the non-sampling Gaussian Blur image of four adjacent yardsticks.
Size without the down-sampling Gaussian Blur image identical and that yardstick is different of four adjacent yardsticks is carried out adjacent yardstick calculus of differences and is obtained the difference of Gaussian image of three adjacent yardsticks, be that yardstick 1 obtains with the Gaussian image difference of yardstick 2 the Gaussian difference component that yardstick is, figure yardstick 2 obtains with the Gaussian image difference of yardstick 3 difference diagram that yardstick is, yardstick 3 obtains with the Gaussian image difference of yardstick 4 difference diagram that yardstick is.Gaussian difference component is as shown in Fig. 2～4.
Utilize horizontal direction template (1,0,1 as shown in Figure 5;-2,0,2;-1,0,1), vertical direction template (1 ,-2 ,-1; 0,0,0; 1,2,1) Sobel operator carries out rim detection to this difference diagram of three panel heights, obtains the edge detection graph of three adjacent yardsticks, and the outline map of yardstick 1 as shown in Figure 6.Centered by each marginal point in yardstick 3 outline maps, in the outline map of yardstick 2, its 3 × 3 neighborhood is searched for, retained the marginal point in neighborhood, to search end, the outline map after being merged for the first time.To each marginal point in this outline map, in the outline map that is 1 at yardstick, proceed above-mentioned same operation, obtain final Fusion Edges image, as shown in Figure 7.
Get T
2=3, edge fused images is carried out morphological dilations with 3 × 3 templates, then carries out closing operation of mathematical morphology with 8 × 8 templates, obtains the connected domain of edge closure, as shown in Figure 8.Fig. 8 is carried out to image filling, make the hole in connected domain up, obtain complete connected domain image (as shown in Figure 9).
Fig. 9 is carried out to connected component labeling (mark result is 16), calculate the area of each connected domain and sort by descending order, taking largest connected territory area 1/4 as threshold value (in this example as 2300), reject the connected domain that area is less than threshold value, the connected domain image (as shown in figure 10) obtaining is considered as vehicle position.In Fig. 1, relevant position draws connected domain boundary rectangle, obtains rainy day vehicle detection result, as shown in figure 11.The testing result of Figure 12 for adopting processing of the present invention to obtain to another scene (fine day).
Can find out from Figure 11 and 12, carry out according to the method described above vehicle detection, realize good testing result.This example shows, the solution of the present invention algorithm is simple, has reduced calculated amount, has realized good vehicle detection simultaneously.
The invention discloses a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge, first utilize the gaussian kernel of four adjacent scale parameters and image to carry out convolution algorithm, obtain the Gaussian image of four adjacent yardsticks.Then the Gaussian image of these four adjacent yardsticks is carried out to difference, obtain the difference of Gaussian image of three adjacent yardsticks and adopt Sobel operator to carry out rim detection to it.Then the edge image that detects three adjacent yardsticks that obtain is carried out to the Fusion Edges that yardstick is upwards searched for, obtain vehicle edge information as much as possible and remove a large amount of background edge simultaneously.Again to the edge image merging expand, a series of morphological operations such as closed operation, hole filling, obtain representing the connected domain image of vehicle.Finally in original image, determine the extraneous rectangle of vehicle position according to the positional information of connected domain, realize vehicle detection.The present invention processes the multi-scale image of non-sampling, has avoided the marginal information disappearance that image interpolation arithmetic causes or has occurred pseudo-edge; Adopt method that multi-scale edge image upwards searches for fusion Background suppression edge in obtaining more multiple edge information.The method has reduced algorithm complex, has reduced calculated amount, can effectively improve the efficiency of vehicle detection, obtains good testing result.
Claims (5)
1. the vehicle checking method merging based on difference of Gaussian multi-scale edge, is characterized in that, comprises the following steps:
Step 1, gather certain road section traffic volume video, the piece image gray processing in video is obtained to original-gray image, then carry out gaussian pyramid multi-scale transform, utilize gaussian kernel and the image of four adjacent scale parameters to carry out convolution algorithm, obtain the Gaussian image G of four adjacent yardsticks
l, wherein l represents four adjacent yardsticks, l=1,2,3,4;
Step 2, to the Gaussian image G of these four adjacent yardsticks
lcarry out adjacent scalogram as calculus of differences, obtain the difference of Gaussian image D of three adjacent yardsticks
l, the yardstick of three these difference images of panel height is respectively: σ, 2 × σ, 2 × 2 × σ; Wherein l=1,2,3, σ is smoothing parameter;
Step 3, this difference image of three panel heights D that step 2 is obtained
ladopt Sobel operator to carry out rim detection, calculate the gradient magnitude of each pixel on level, vertical both direction in difference image, and threshold value T is set
1, retain gradient magnitude and be greater than threshold value T
1pixel, this pixel is marginal point to establish its gray-scale value be 255, otherwise is made as 0, obtains the rim detection binary map E of corresponding three adjacent yardsticks
l, wherein l=1,2,3;
Step 4, to three width two-value outline map E of corresponding three different scales
lcarry out multi-scale edge fusion, wherein, l=1,2,3, concrete steps are:
(1) under four adjacent yardstick l, search for the difference of Gaussian image D of three adjacent yardsticks
ledge image E
lin each edge pixel, because the edge dislocation between adjacent yardstick is no more than 1, the difference Gaussian image D that is l-1 at yardstick
l-1edge image in to search for corresponding area be 3 × 3 region, all marginal points that occur in this region are all labeled as marginal point, obtain candidate's edge image;
(2) l=l-1; If l>1 jumps to step (1), otherwise execution step (3);
(3) when l=1, edge image E
lit is the edge image after merging;
Step 5, the edge image after the fusion that step 4 is obtained adopts expansion template to carry out morphology processing, setting threshold T
2, connect pel spacing and be less than threshold value T
2marginal point or line, obtain continuous boundary; Carry out again closing operation of mathematical morphology, make hole and the crack of edge image up, the edge image that obtains being further closed; Fill the interior void filling of enclosed region finally by crossing image, form complete connected region;
Step 6, carries out mark to connected region, calculates the area of each connected region, and area threshold T is set
3, reject area and be less than area threshold T
3connected domain; The coordinate of determining the minimum boundary rectangle of each connected domain according to connected domain coordinate finally shows in original-gray image, completes the detection to vehicle.
2. a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge according to claim 1, is characterized in that, described step 1 mesoscale is determined jointly by smoothing parameter σ and smoothing parameter k, k is determined by parameter s, and k=2^ (1/S), S+3=N, wherein N is the Gauss's picture number in the every one deck of gaussian pyramid, gets N=4, S=1, σ=0.5, k=2, four adjacent yardsticks are respectively σ, k σ, 2k σ, 3k σ.
3. a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge according to claim 1, is characterized in that, in described step 3, the template of Sobel operator horizontal direction is (1,0,1;-2,0,2;-1,0,1), vertical direction template is (1 ,-2 ,-1; 0,0,0; 1,2,1), threshold value T
1obtained by maximum variance between clusters.
4. a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge according to claim 1, is characterized in that, in described step 5, bulging die board size is 3 × 3, and form closed operation template size is 8 × 8, T
2span is 1～8, and taking pixel as unit.
5. a kind of vehicle checking method merging based on difference of Gaussian multi-scale edge according to claim 1, it is characterized in that, in described step 6, the setting up procedure of area threshold is: the area to the n of a mark connected domain sorts, using largest connected territory area 1/4 as area threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410181851.0A CN103927526B (en) | 2014-04-30 | 2014-04-30 | Vehicle detecting method based on Gauss difference multi-scale edge fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410181851.0A CN103927526B (en) | 2014-04-30 | 2014-04-30 | Vehicle detecting method based on Gauss difference multi-scale edge fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103927526A true CN103927526A (en) | 2014-07-16 |
| CN103927526B CN103927526B (en) | 2017-02-15 |
Family
ID=51145742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410181851.0A Active CN103927526B (en) | 2014-04-30 | 2014-04-30 | Vehicle detecting method based on Gauss difference multi-scale edge fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103927526B (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598906A (en) * | 2015-03-04 | 2015-05-06 | 西安工业大学 | External-profile detection method and device for vehicles |
| CN105956532A (en) * | 2016-04-25 | 2016-09-21 | 大连理工大学 | Traffic scene classification method based on multi-scale convolution neural network |
| CN107240111A (en) * | 2017-06-14 | 2017-10-10 | 郑州天迈科技股份有限公司 | Edge connection segmentation passenger flow statistical method |
| CN107492110A (en) * | 2017-07-31 | 2017-12-19 | 腾讯科技（深圳）有限公司 | A kind of method for detecting image edge, device and storage medium |
| CN107730521A (en) * | 2017-04-29 | 2018-02-23 | 安徽慧视金瞳科技有限公司 | The quick determination method of roof edge in a kind of image |
| CN108596931A (en) * | 2018-05-11 | 2018-09-28 | 浙江大学 | A kind of noise robustness hub edge detection algorithm based on Canny operators |
| CN108629781A (en) * | 2018-04-24 | 2018-10-09 | 成都品果科技有限公司 | A kind of hair method for drafting |
| CN108830169A (en) * | 2018-05-24 | 2018-11-16 | 中国农业大学 | The detection method and system of aerator working condition |
| CN108957530A (en) * | 2018-05-23 | 2018-12-07 | 电子科技大学 | A kind of crack automatic testing method based on Acceleration Algorithm in Seismic Coherence Cube slice |
| CN109242884A (en) * | 2018-08-14 | 2019-01-18 | 西安电子科技大学 | Remote sensing video target tracking method based on JCFNet network |
| CN109389617A (en) * | 2018-08-27 | 2019-02-26 | 深圳大学 | A kind of motion estimate based on piece heterogeneous system and method for tracing and system |
| CN109543487A (en) * | 2018-11-22 | 2019-03-29 | 福州图腾易讯信息技术有限公司 | A kind of automatic sensing triggering method and its system based on bar edges segmentation |
| CN109559299A (en) * | 2018-11-19 | 2019-04-02 | 常州大学 | A kind of separation method of double fruit overlapping fruits |
| CN109741406A (en) * | 2019-01-03 | 2019-05-10 | 广州广电银通金融电子科技有限公司 | A kind of body color recognition methods under monitoring scene |
| CN109784322A (en) * | 2019-01-04 | 2019-05-21 | 平安科技（深圳）有限公司 | A kind of recognition methods of vin code, equipment and medium based on image procossing |
| CN109886312A (en) * | 2019-01-28 | 2019-06-14 | 同济大学 | A kind of bridge wheel of vehicle detection method based on multilayer feature fused neural network model |
| CN111324145A (en) * | 2020-02-28 | 2020-06-23 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111353446A (en) * | 2020-03-05 | 2020-06-30 | 广智微芯(扬州)有限公司 | Lane line detection method and system |
| CN111626304A (en) * | 2020-05-20 | 2020-09-04 | 中国科学院新疆理化技术研究所 | Color feature extraction method based on machine vision and application thereof |
| CN111915496A (en) * | 2019-05-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Image processing method, device and storage medium |
| CN112329677A (en) * | 2020-11-12 | 2021-02-05 | 北京环境特性研究所 | Remote sensing image river target detection method and device based on feature fusion |
| CN112520524A (en) * | 2021-01-13 | 2021-03-19 | 大连理工大学 | Intelligent elevator control interaction device and control method based on gesture recognition technology |
| CN112819843A (en) * | 2021-01-20 | 2021-05-18 | 上海大学 | Method and system for extracting power line at night |
| CN113269800A (en) * | 2021-05-25 | 2021-08-17 | 华能海南发电股份有限公司澄迈光伏电站 | Infrared image segmentation method for solar photovoltaic module |
| CN114494318A (en) * | 2022-02-17 | 2022-05-13 | 天津市眼科医院 | Method for extracting cornea contour from cornea dynamic deformation video based on Otsu algorithm |
| CN114972276A (en) * | 2022-06-05 | 2022-08-30 | 长沙烽铭智能科技有限公司 | Automatic driving distance judgment algorithm for vehicle |
| CN115775250A (en) * | 2023-02-13 | 2023-03-10 | 惠州威尔高电子有限公司 | Golden finger circuit board defect rapid detection system based on digital image analysis |
| CN118628495A (en) * | 2024-08-13 | 2024-09-10 | 广州优箔良材科技有限公司 | Method for monitoring abnormal cutting of foil based on machine vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520894A (en) * | 2009-02-18 | 2009-09-02 | 上海大学 | Method for extracting significant object based on region significance |
| US20100266183A1 (en) * | 2007-12-10 | 2010-10-21 | Agfa Healthcare Nv | Method of Generating a Multiscale Contrast Enhanced IMage |
| CN102289806A (en) * | 2011-06-21 | 2011-12-21 | 北京航空航天大学 | Method for measuring image definition by utilizing multi-scale morphological characteristics |
| CN103714538A (en) * | 2013-12-20 | 2014-04-09 | 中联重科股份有限公司 | Road edge detection method and device and vehicle |
-
2014
- 2014-04-30 CN CN201410181851.0A patent/CN103927526B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100266183A1 (en) * | 2007-12-10 | 2010-10-21 | Agfa Healthcare Nv | Method of Generating a Multiscale Contrast Enhanced IMage |
| CN101520894A (en) * | 2009-02-18 | 2009-09-02 | 上海大学 | Method for extracting significant object based on region significance |
| CN102289806A (en) * | 2011-06-21 | 2011-12-21 | 北京航空航天大学 | Method for measuring image definition by utilizing multi-scale morphological characteristics |
| CN103714538A (en) * | 2013-12-20 | 2014-04-09 | 中联重科股份有限公司 | Road edge detection method and device and vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 刘立: "基于多尺度特征的图像匹配与目标定位研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598906B (en) * | 2015-03-04 | 2017-08-22 | 西安工业大学 | Vehicle outline detection method and its device |
| CN104598906A (en) * | 2015-03-04 | 2015-05-06 | 西安工业大学 | External-profile detection method and device for vehicles |
| CN105956532B (en) * | 2016-04-25 | 2019-05-21 | 大连理工大学 | A kind of traffic scene classification method based on multiple dimensioned convolutional neural networks |
| CN105956532A (en) * | 2016-04-25 | 2016-09-21 | 大连理工大学 | Traffic scene classification method based on multi-scale convolution neural network |
| CN107730521A (en) * | 2017-04-29 | 2018-02-23 | 安徽慧视金瞳科技有限公司 | The quick determination method of roof edge in a kind of image |
| CN107730521B (en) * | 2017-04-29 | 2020-11-03 | 安徽慧视金瞳科技有限公司 | Method for rapidly detecting ridge type edge in image |
| CN107240111A (en) * | 2017-06-14 | 2017-10-10 | 郑州天迈科技股份有限公司 | Edge connection segmentation passenger flow statistical method |
| CN107492110A (en) * | 2017-07-31 | 2017-12-19 | 腾讯科技（深圳）有限公司 | A kind of method for detecting image edge, device and storage medium |
| CN108629781B (en) * | 2018-04-24 | 2022-04-22 | 成都品果科技有限公司 | Hair drawing method |
| CN108629781A (en) * | 2018-04-24 | 2018-10-09 | 成都品果科技有限公司 | A kind of hair method for drafting |
| CN108596931A (en) * | 2018-05-11 | 2018-09-28 | 浙江大学 | A kind of noise robustness hub edge detection algorithm based on Canny operators |
| CN108957530A (en) * | 2018-05-23 | 2018-12-07 | 电子科技大学 | A kind of crack automatic testing method based on Acceleration Algorithm in Seismic Coherence Cube slice |
| CN108957530B (en) * | 2018-05-23 | 2019-08-23 | 电子科技大学 | A kind of crack automatic testing method based on Acceleration Algorithm in Seismic Coherence Cube slice |
| CN108830169A (en) * | 2018-05-24 | 2018-11-16 | 中国农业大学 | The detection method and system of aerator working condition |
| CN108830169B (en) * | 2018-05-24 | 2020-10-09 | 中国农业大学 | Method and system for detecting working state of aerator |
| CN109242884B (en) * | 2018-08-14 | 2020-11-20 | 西安电子科技大学 | Remote sensing video target tracking method based on JCFNet network |
| CN109242884A (en) * | 2018-08-14 | 2019-01-18 | 西安电子科技大学 | Remote sensing video target tracking method based on JCFNet network |
| CN109389617A (en) * | 2018-08-27 | 2019-02-26 | 深圳大学 | A kind of motion estimate based on piece heterogeneous system and method for tracing and system |
| CN109559299A (en) * | 2018-11-19 | 2019-04-02 | 常州大学 | A kind of separation method of double fruit overlapping fruits |
| CN109559299B (en) * | 2018-11-19 | 2023-07-25 | 常州大学 | Method for separating double-fruit overlapped fruits |
| CN109543487B (en) * | 2018-11-22 | 2022-04-01 | 福州图腾易讯信息技术有限公司 | Automatic induction triggering method and system based on bar code edge segmentation |
| CN109543487A (en) * | 2018-11-22 | 2019-03-29 | 福州图腾易讯信息技术有限公司 | A kind of automatic sensing triggering method and its system based on bar edges segmentation |
| CN109741406A (en) * | 2019-01-03 | 2019-05-10 | 广州广电银通金融电子科技有限公司 | A kind of body color recognition methods under monitoring scene |
| CN109784322A (en) * | 2019-01-04 | 2019-05-21 | 平安科技（深圳）有限公司 | A kind of recognition methods of vin code, equipment and medium based on image procossing |
| CN109886312B (en) * | 2019-01-28 | 2023-06-06 | 同济大学 | Bridge vehicle wheel detection method based on multilayer feature fusion neural network model |
| CN109886312A (en) * | 2019-01-28 | 2019-06-14 | 同济大学 | A kind of bridge wheel of vehicle detection method based on multilayer feature fused neural network model |
| CN111915496A (en) * | 2019-05-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Image processing method, device and storage medium |
| CN111915496B (en) * | 2019-05-08 | 2024-04-23 | 北京字节跳动网络技术有限公司 | Image processing method, device and storage medium |
| CN111324145B (en) * | 2020-02-28 | 2022-08-16 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111324145A (en) * | 2020-02-28 | 2020-06-23 | 厦门理工学院 | Unmanned aerial vehicle autonomous landing method, device, equipment and storage medium |
| CN111353446A (en) * | 2020-03-05 | 2020-06-30 | 广智微芯(扬州)有限公司 | Lane line detection method and system |
| CN111626304A (en) * | 2020-05-20 | 2020-09-04 | 中国科学院新疆理化技术研究所 | Color feature extraction method based on machine vision and application thereof |
| CN111626304B (en) * | 2020-05-20 | 2023-08-04 | 中国科学院新疆理化技术研究所 | Color feature extraction method based on machine vision and application thereof |
| CN112329677B (en) * | 2020-11-12 | 2024-02-02 | 北京环境特性研究所 | Remote sensing image river channel target detection method and device based on feature fusion |
| CN112329677A (en) * | 2020-11-12 | 2021-02-05 | 北京环境特性研究所 | Remote sensing image river target detection method and device based on feature fusion |
| CN112520524A (en) * | 2021-01-13 | 2021-03-19 | 大连理工大学 | Intelligent elevator control interaction device and control method based on gesture recognition technology |
| CN112819843A (en) * | 2021-01-20 | 2021-05-18 | 上海大学 | Method and system for extracting power line at night |
| CN113269800A (en) * | 2021-05-25 | 2021-08-17 | 华能海南发电股份有限公司澄迈光伏电站 | Infrared image segmentation method for solar photovoltaic module |
| CN114494318A (en) * | 2022-02-17 | 2022-05-13 | 天津市眼科医院 | Method for extracting cornea contour from cornea dynamic deformation video based on Otsu algorithm |
| CN114972276A (en) * | 2022-06-05 | 2022-08-30 | 长沙烽铭智能科技有限公司 | Automatic driving distance judgment algorithm for vehicle |
| CN115775250A (en) * | 2023-02-13 | 2023-03-10 | 惠州威尔高电子有限公司 | Golden finger circuit board defect rapid detection system based on digital image analysis |
| CN118628495A (en) * | 2024-08-13 | 2024-09-10 | 广州优箔良材科技有限公司 | Method for monitoring abnormal cutting of foil based on machine vision |
| CN118628495B (en) * | 2024-08-13 | 2024-11-05 | 广州优箔良材科技有限公司 | Method for monitoring abnormal cutting of foil based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103927526B (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103927526B (en) | Vehicle detecting method based on Gauss difference multi-scale edge fusion | |
| CN107507167B (en) | Cargo tray detection method and system based on point cloud plane contour matching | |
| Gong et al. | The recognition and tracking of traffic lights based on color segmentation and camshift for intelligent vehicles | |
| CN106951879B (en) | Multi-feature fusion vehicle detection method based on camera and millimeter wave radar | |
| CN103559791B (en) | A kind of vehicle checking method merging radar and ccd video camera signal | |
| CN102509098B (en) | Fisheye image vehicle identification method | |
| Hautière et al. | Real-time disparity contrast combination for onboard estimation of the visibility distance | |
| Gomez et al. | Traffic lights detection and state estimation using hidden markov models | |
| Huang et al. | Vehicle detection and inter-vehicle distance estimation using single-lens video camera on urban/suburb roads | |
| CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
| CN105488454A (en) | Monocular vision based front vehicle detection and ranging method | |
| EP2549457A1 (en) | Vehicle-mounting vehicle-surroundings recognition apparatus and vehicle-mounting vehicle-surroundings recognition system | |
| CN102419820A (en) | Method for rapidly detecting automobile logo in video and image | |
| WO2015147764A1 (en) | A method for vehicle recognition, measurement of relative speed and distance with a single camera | |
| Liu et al. | ROI perspective transform based road marking detection and recognition | |
| CN107256633B (en) | Vehicle type classification method based on monocular camera three-dimensional estimation | |
| CN109190483B (en) | Lane line detection method based on vision | |
| CN103942560A (en) | High-resolution video vehicle detection method in intelligent traffic monitoring system | |
| CN104700072A (en) | Lane line historical frame recognition method | |
| CN107909047A (en) | A kind of automobile and its lane detection method and system of application | |
| CN113837094A (en) | Road condition rapid analysis method based on full-color high-resolution remote sensing image | |
| CN105069441A (en) | Moving vehicle detection method based on background updating and particle swarm optimization algorithm | |
| CN105426868A (en) | Lane detection method based on adaptive region of interest | |
| Arshad et al. | Lane detection with moving vehicles using color information | |
| CN105512641A (en) | Method for using laser radar scanning method to calibrate dynamic pedestrians and vehicles in video in snowing or raining state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |