CN109446917A - A kind of vanishing Point Detection Method method based on cascade Hough transform - Google Patents
A kind of vanishing Point Detection Method method based on cascade Hough transform Download PDFInfo
- Publication number
- CN109446917A CN109446917A CN201811154229.5A CN201811154229A CN109446917A CN 109446917 A CN109446917 A CN 109446917A CN 201811154229 A CN201811154229 A CN 201811154229A CN 109446917 A CN109446917 A CN 109446917A
- Authority
- CN
- China
- Prior art keywords
- point
- vehicle
- obtains
- target
- image
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 34
- 229910003460 diamond Inorganic materials 0.000 claims abstract description 18
- 239000010432 diamond Substances 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 13
- 230000003287 optical effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 235000007164 Oryza sativa Nutrition 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 235000009566 rice Nutrition 0.000 claims description 3
- 240000007594 Oryza sativa Species 0.000 claims 1
- 230000009466 transformation Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052754 neon Inorganic materials 0.000 description 1
- GKAOGPIIYCISHV-UHFFFAOYSA-N neon atom Chemical compound [Ne] GKAOGPIIYCISHV-UHFFFAOYSA-N 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to intelligent transportation fields, and in particular to a kind of vanishing Point Detection Method method based on cascade Hough transform includes the following steps: step 1: acquisition road vehicle video obtains the vehicle target of each frame image；Step 2: carrying out Harris angle point grid, obtain the characteristic point on the vehicle target of each frame image；Step 3: obtaining straight line track；Step 4: straight line track being screened, the straight line track set after screening is denoted as L；Step 5: the straight path set L after screening is transformed into diamond shape hough space from image space by cascade Hough transform and is voted, the maximum point coordinate after being voted；Step 6: the coordinate of maximum point being transformed into image space, end point coordinate in image space is finally obtained, completes the detection of end point.Various weather conditions are suitable for using this method, the erroneous detection of end point under special weather is avoided, substantially increases the accuracy of vanishing Point Detection Method.
Description
Technical field
The invention belongs to intelligent transportation fields, and in particular to a kind of vanishing Point Detection Method method based on cascade Hough transform.
Background technique
End point is a kind of important feature under many scenes, is defined as parallel straight line and all disappears to infinite point
It is same, it is called end point in the perspective.It is according to certain features in actual scene in conjunction with certain algorithm come
It obtains, can be used as the related work of the machine vision such as camera calibration, scene rebuilding and scene edge cluster.To sum up, end point
As a kind of important basic data, important basis has been established to subsequent machine vision related work.
Vanishing Point Detection Method method under existing traffic scene detects the point that disappears generally according to lane line, this method by
It is less in lane line number, and lane line may cause vanishing Point Detection Method inaccuracy there are one fixed width, and in special day
Gas lane detection inaccuracy also results in the appearance that end point is difficult to test problems.
Summary of the invention
It is difficult to detect or detect the problem of inaccuracy for disappearing in above-mentioned existing vanishing Point Detection Method method, the present invention mentions
For a kind of vanishing Point Detection Method method based on cascade Hough transform.
To achieve the goals above, the present invention is realised by adopting the following technical scheme, specifically comprises the following steps:
Step 1: acquisition road vehicle video obtains the vehicle target of each frame image；
Step 2: Harris angle point grid being carried out to the vehicle target for each frame image that step 1 detection obtains, is obtained every
Characteristic point on the vehicle target of one frame image；
Step 3: the vehicle target of each frame image being obtained to step 1 and the vehicle mesh of each frame image that step 2 obtains
The characteristic point put on obtains straight line track；
Step 4: the straight line track obtained to step 3 is screened, and the straight line track set after screening is denoted as
L；
Step 5: the straight path set L after the screening obtained by cascade Hough transform to step 4 turns from image space
It changes in diamond shape hough space and votes, the maximum point coordinate after being voted；
Step 6: the coordinate for the maximum point that step 5 obtains being transformed into image space, is finally obtained in image space
End point coordinate completes the detection of end point.
Further, step 3 specifically comprises the following steps:
On the vehicle target for each frame image that step 1 obtains the image of each frame vehicle target and step 2 obtains
In characteristic point, using optical flow tracking algorithm, using the characteristic point of the image of adjacent two frames vehicle target and previous frame image as
Whether the input in optical flow tracking algorithm then exports the corresponding position for former frame characteristic point in a later frame and tracks into
Function；Initial characteristic point is the Harris angle point of fresh target, is tracked with this as the starting point, and the characteristic point inputted later is to have deposited
Ending point in track；After all inputs traverse the above process, the set of output is the straight line track traced into.
Further, step 4 includes following sub-step:
Step 41: the track of vehicle that step 3 obtains being screened, the tracing point in track of vehicle is enough, retains；
Step 42: least square fitting being carried out to the track of vehicle that step 41 retains, finishing screen selects straight line track
Set L.
Further, step 41 includes following sub-step:
Step 41: the track of vehicle that step 3 obtains being screened, the tracing point in the track of vehicle is more than 15
Then retain.
Further, step 5 includes following sub-step:
The straight path set L after screening obtained in step 4 is transformed into from image space by cascade Hough transform
In diamond shape hough space, after the gridding of diamond shape space, the track of vehicle straight line after conversion is subjected to cumulative ballot, voting results
Highest point is the maximum point in diamond shape space, obtains the coordinate of maximum point.
Further, step 1 includes following sub-step:
Step 11: acquiring road vehicle video, prospect is the vehicle of movement in video, and background is road area, non-rice habitats
Ground region and sky；
Step 12: to the collected road vehicle video of step 11, being detected by GMM gauss hybrid models each in video
The background of frame image；
Step 13: image difference is first passed through to each frame image background that step 12 obtains and obtains foreground moving object, then
By median filtering and closed operation, the vehicle target in the foreground moving object of each frame image is obtained.
Further, step 2 includes following sub-step:
The prospect for obtaining the vehicle target of each frame image to step 1 is classified, and is divided into tracked target and is newly gone out
Existing target, if the end node that present frame extracts in foreground target comprising current track is more than 3, then it is assumed that the prospect
Target is existing target, otherwise is target newly occur, new occurs extracting three Harris angle points, i.e. feature in target each
Point；Above-mentioned processing is carried out to each frame image, obtains the characteristic point on the vehicle target of each frame image.
The invention has the following advantages:
(1) present invention uses this novel straight line parameter method of cascade Hough transform, can be ingenious and efficiently
Unlimited image space is become into limited diamond shape space, gridding processing is carried out to the diamond shape space later and using the side of ballot
Method determines the position of final end point.Verified, this kind of method is more steady than the method for directly extracting end point in luv space
It is fixed and accurate.
(2) since the lane line number on road is limited, and lane line generally requires manual measurement, in severe day
It is extremely difficult to the accurately extraction of lane line in gas, therefore the present invention is by collecting sufficient amount of effective straight line track
And not against the measurement of lane line, it can largely avoid influencing brought by bad weather, while being not necessarily to manual measurement, mention
The high degree of automation.
(3) to the screening of track of vehicle, on the one hand guarantee more effective trajectory lines by rejecting short track, exclude short rail
On the other hand there is the bending rail overtaking other vehicles equal behaviors and occurring on road due to vehicle in the influence of exception track brought by mark
Mark is screened by track and is rejected, so that it is guaranteed that the accuracy of end point position detection.
Illustration and description in further detail are carried out to the solution of the present invention with reference to the accompanying drawings and detailed description.
Detailed description of the invention
Fig. 1 is image end point position view under A scene；
Fig. 2 is parameter space voting results schematic diagram under A scene；
Fig. 3 is the traffic scene schematic diagram in the embodiment of the present invention；
Fig. 4 is that the scene background in the embodiment of the present invention extracts result；
Fig. 5 is the background modeling in the embodiment of the present invention；
Fig. 6 is median filtering and closed operation processing result in the embodiment of the present invention；
Fig. 7 is the exclusion result of the non-vehicle target in the embodiment of the present invention；
Fig. 8 is the track of the optical flow tracking in the embodiment of the present invention；
Fig. 9 is the space cascade Hough transform in the embodiment of the present invention；
Figure 10 is the corresponding relationship of hough space under cartesian coordinate system and parallel coordinate system in the embodiment of the present invention；
Figure 11 is parameter space voting results schematic diagram under B scene；
Figure 12 is image end point position view under B scene.
Specific embodiment
The following provides a specific embodiment of the present invention, it should be noted that the invention is not limited to implement in detail below
Example, all equivalent transformations made on the basis of the technical solutions of the present application each fall within protection scope of the present invention.
A kind of vanishing Point Detection Method method based on cascade Hough transform, comprising the following steps:
Step 1: acquisition road vehicle video obtains the vehicle target of each frame image；
Step 2: Harris angle point grid being carried out to the vehicle target for each frame image that step 1 detection obtains, is obtained every
Characteristic point on the vehicle target of one frame image；
Step 3: the vehicle target of each frame image being obtained to step 1 and the vehicle mesh of each frame image that step 2 obtains
The characteristic point put on obtains straight line track；
Step 4: the straight line track obtained to step 3 is screened, and the straight line track set after screening is denoted as
L；
Step 5: the straight path set L after the screening obtained by cascade Hough transform to step 4 turns from image space
It changes in diamond shape hough space and votes, the maximum point coordinate after being voted；
Step 6: the coordinate for the maximum point that step 5 obtains being transformed into image space, is finally obtained in image space
End point coordinate completes the detection of end point.
The invention proposes the vanishing Point Detection Method methods based on cascade Hough transform, are regarded using the monitoring under traffic scene
Frequently, target prospect is obtained using GMM algorithm, vehicle target is tracked with light rigid-liquid coupled system, track is sieved later
Choosing, then voted by the thought of cascade Hough transform the track after screening, so that it is determined that the end point on road.The party
Method is suitable for various weather conditions, avoids the erroneous detection of end point under special weather, substantially increases the accurate of vanishing Point Detection Method
Property.
Step 1 specifically includes following sub-step:
Step 11: choosing somewhere scene, camera is erected at by road, camera is enabled to obtain a certain range on lane
Interior vehicle acquires road vehicle video, and for scene as shown in figure 3, prospect is the vehicle of movement in video, background is roadway area
Domain, non-rice habitats ground region and sky；
Step 12: to the collected road vehicle video of step 11, being detected by GMM gauss hybrid models each in video
The background of frame image, background extracting result are as shown in Figure 4；
GMM algorithm is the classical solution of this classical problem of background modeling, the background modeling algorithm key to be solved
Problem is differentiation background pixel and foreground pixel, the resolving ideas of Gauss model (MM) are to describe certain using Gaussian statistics model
Pixel Distribution value at pixel P, before the pixel value covering of moving foreground object, using a period T to pixel value at P
Then distributive observation calculates the Gauss model for describing the position pixel Distribution value.When the Gauss model of position each in image
It all calculates, then just background model is claimed to be established, this period T is known as modeling the time.MM can establish background model
Basic assumption be modeling the time in, background pixel occur time occupy the majority.Differentiation for prospect and background, if newly
Pixel value at covering P meets the Gaussian Profile of the position, then being exactly background pixel, otherwise is exactly foreground pixel.However have
A kind of special background is not static but is moving, but moving presentation reciprocation cycle has certain regularity, such as: flashing
Neon light and shaking leaf.GMM algorithm aiming at such issues that propose, MM is to describe picture with a Gauss model
Element distribution, and GMM is described with multiple Gauss models.
Advantage: the algorithm is more preferable compared to the effect that the other methods such as frame difference method detect image background, while consuming
Time does not also increase.
Step 13: image difference is first passed through to each frame image background that step 12 obtains and obtains foreground moving object, then
By median filtering and closed operation, the vehicle target in the foreground moving object of each frame image is obtained.
In the case where obtaining background, foreground moving object can be obtained by image difference, but the knot of direct differential
Fruit still has many interference pixels, therefore, removes part interference pixel to image background, as shown in Figure 5；Again from foreground pixel block
The prospect for removing these non-vehicle targets in shape obtains vehicle target, as shown in Figure 6.
Step 2 includes following sub-step:
The core concept of Harris Corner Detection is that window is all very violent along any direction grey scale change in a certain position,
Then think that the position includes angle point, in order to enable the extraction efficiency of Harris angle point is higher, using only to vehicle target progress angle
Point detection, it is high-efficient that such efficiency obviously compares entire image progress Harris Corner Detection.
The prospect for obtaining the vehicle target of each frame image to step 1 is classified, and is divided into tracked target and is newly gone out
Existing target, if the end node that present frame extracts in foreground target comprising current track is more than 3, then it is assumed that the prospect
Target is existing target, otherwise is target newly occur, new occurs extracting three Harris angle points, i.e. characteristic point in target each
And the starting point as new track, as shown in Figure 7.
Step 3 specifically comprises the following steps:
Light stream is reflection of the instantaneous velocity of space motion object on imaging plane, is existed using pixel in image sequence
The correlation between variation and consecutive frame in time-domain finds previous frame with corresponding relationship existing between present frame, from
And calculate a kind of method of the motion information of object between consecutive frame.
On the vehicle target for each frame image that step 1 obtains the image of each frame vehicle target and step 2 obtains
In characteristic point, using optical flow tracking algorithm, using the characteristic point of the image of adjacent two frames vehicle target and previous frame image as
Whether the input in optical flow tracking algorithm then exports the corresponding position for former frame characteristic point in a later frame and tracks into
Function；Initial characteristic point is the Harris angle point of fresh target, is tracked with this as the starting point, and the characteristic point inputted later is to have deposited
Ending point in track；After all inputs traverse the above process, the set of output is the straight line track traced into, such as
Shown in Fig. 8.
Step 4 includes following sub-step:
Step 41: the track of vehicle that step 3 obtains being screened, the tracing point in track of vehicle is enough, retains；
Step 42: least square fitting being carried out to the track of vehicle that step 41 retains, finishing screen selects straight line track
Set L.
Preferably, the tracing point is more than 15.
Step 5 specifically comprises the following steps:
The straight path set L after screening obtained in step 4 is transformed into from image space by cascade Hough transform
In diamond shape hough space, using Hough vote thought, after the gridding of diamond shape space, by the track of vehicle straight line after conversion into
The cumulative ballot of row, finally obtains the maximum point in diamond shape space, voting results are as shown in figs. 2 and 11.
For traditional Hough transformation, transformation the result is that line becomes a little or point becomes line, and the problem of to be solved
It is the problem of a kind of line becomes line.In addition, original image is too big for Hough transformation, computer realization can waste time and
End point cannot achieve at or approximately at the case where infinity.Therefore using cascade Hough change thought, thus avoid it is above-mentioned because
This of element is a kind of transformation of line to line, and the parametrization of this straight line can be by the Image space transformation of original infinity to limited
Diamond shape space.
Hough transformation continuous twice by line to point again from point to line is referred to as cascade Hough transform.It first introduces herein parallel
Coordinate system, parallel coordinate system indicates a series of reference axis being parallel to each other of each component of high dimensional data, to solve to pass
The problem of cartesian cartesian coordinate system of system three-dimensional above data beyond expression of words.Below by cartesian coordinate system and parallel coordinates
System is to derive cascade Hough transform:
In derivation process, the reference axis under parallel coordinate system is indicated using subscript p, indicates that Descartes sits using subscript c
Reference axis in mark system.In order to facilitate connection cartesian coordinate system and parallel coordinate system, two coordinate systems are superimposed, are such as schemed
Shown in 9.Data in square brackets indicate a point, are expressed as [x, y, w] with homogeneous coordinates, and the data in round parentheses indicate one
Straight line, such as (a, b, c).
By xcAnd ycIn point and straight line transform to coordinate distance between axles be d xpAnd ypIn, available formula (1):
Transformation results are as shown in Figure 10.It is similar with converting above, second of transformation such as Fig. 9 is carried out, by ucAnd vcIn point and
Line transforms to the u that coordinate distance between axles is DpAnd vpIn:
Next by the position of-d by ypReference axis overturning is-ypReference axis ,-ypWith xpBetween space be known as the space T, xp
With ypBetween space be known as the space S.With reference to formula (1) and formula (2), the conversion of the Points And lines in the space T is obtained:
The Four processes of T transformation and S-transformation are connected, obtain a point transformation being the complete of the point in hough space
The process of whole cascade Hough transform:
By the above cascaded transformation, any point in cartesian coordinate system is all switched in limited diamond shape space,
The conversion of infinite space to the confined space is realized, and quadrant has corresponding pass in cartesian coordinate system lower quadrant and diamond shape space
System, as shown in Figure 10.
End point result using the detection of cascade Hough transform algorithm is verified, lane line at end point and near field scape
Line whether fit with lane lines most of in scene, as shown in figs. 1 and 12, if fitting if think detection compared with subject to
Really, on the contrary then error is larger.
Claims (7)
1. a kind of vanishing Point Detection Method method based on cascade Hough transform, method includes the following steps:
Step 1: acquisition road vehicle video obtains the vehicle target of each frame image；
Step 2: Harris angle point grid being carried out to the vehicle target for each frame image that step 1 detection obtains, obtains each frame
Characteristic point on the vehicle target of image；
It is characterized by:
Step 3: on the vehicle target for each frame image that step 1 obtains the vehicle target of each frame image and step 2 obtains
Characteristic point, obtain straight line track；
Step 4: the straight line track obtained to step 3 is screened, and the straight line track set after screening is denoted as L；
Step 5: the straight path set L after the screening obtained by cascade Hough transform to step 4 is transformed into from image space
It votes in diamond shape hough space, the maximum point coordinate after being voted；
Step 6: the coordinate for the maximum point that step 5 obtains being transformed into image space, finally obtains in image space and disappears
Point coordinate, completes the detection of end point.
2. the vanishing Point Detection Method method based on cascade Hough transform as described in claim 1, which is characterized in that step 3 is specific
Include the following steps:
Feature on the vehicle target for each frame image that step 1 obtains the image of each frame vehicle target and step 2 obtains
In point, using optical flow tracking algorithm, using the characteristic point of the image of adjacent two frames vehicle target and previous frame image as light stream
Input in track algorithm then exports the corresponding position for former frame characteristic point in a later frame and whether tracks success；Just
The characteristic point of beginning is the Harris angle point of fresh target, is tracked with this as the starting point, and the characteristic point inputted later is existing rail
The ending point of mark；After all inputs traverse the above process, the set of output is the straight line track traced into.
3. the vanishing Point Detection Method method based on cascade Hough transform as described in claim 1, which is characterized in that step 4 is specific
Include the following steps:
Step 41: the track of vehicle that step 3 obtains being screened, the tracing point in track of vehicle is enough, retains；
Step 42: least square fitting being carried out to the track of vehicle that step 41 retains, finishing screen selects straight line track set
L。
4. the vanishing Point Detection Method method based on cascade Hough transform as claimed in claim 3, which is characterized in that step 41 includes
Following sub-step:
Step 41: the track of vehicle that step 3 obtains being screened, the tracing point in the track of vehicle, which is more than 15, then to be protected
It stays.
5. the vanishing Point Detection Method method based on cascade Hough transform as described in claim 1, which is characterized in that step 5 includes
Following sub-step:
The straight path set L after screening obtained in step 4 is transformed into diamond shape from image space by cascade Hough transform
In hough space, after the gridding of diamond shape space, the track of vehicle straight line after conversion is subjected to cumulative ballot, voting results highest
Point be maximum point in diamond shape space, obtain the coordinate of maximum point.
6. the vanishing Point Detection Method method based on cascade Hough transform as described in claim 1, which is characterized in that step 1 includes
Following sub-step:
Step 11: acquiring road vehicle video, prospect is the vehicle of movement in video, and background is the ground of road area, non-rice habitats
Face region and sky；
Step 12: to the collected road vehicle video of step 11, detecting each frame figure in video by GMM gauss hybrid models
The background of picture；
Step 13: image difference being first passed through to each frame image background that step 12 obtains and obtains foreground moving object, then is passed through
Median filtering and closed operation obtain the vehicle target in the foreground moving object of each frame image.
7. the vanishing Point Detection Method method based on cascade Hough transform as described in claim 1, which is characterized in that step 2 includes
Following sub-step:
The prospect for obtaining the vehicle target of each frame image to step 1 is classified, and is divided into tracked target and mesh newly occurs
Mark, if the end node that present frame extracts in foreground target comprising current track is more than 3, then it is assumed that the foreground target
It is existing target, otherwise is target newly occur new occur extracting three Harris angle points, i.e. characteristic point in target each；It is right
Each frame image carries out above-mentioned processing, obtains the characteristic point on the vehicle target of each frame image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811154229.5A CN109446917B (en) | 2018-09-30 | 2018-09-30 | Vanishing point detection method based on cascading Hough transform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811154229.5A CN109446917B (en) | 2018-09-30 | 2018-09-30 | Vanishing point detection method based on cascading Hough transform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109446917A true CN109446917A (en) | 2019-03-08 |
| CN109446917B CN109446917B (en) | 2022-08-30 |
Family
ID=65546108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811154229.5A Expired - Fee Related CN109446917B (en) | 2018-09-30 | 2018-09-30 | Vanishing point detection method based on cascading Hough transform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446917B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222667A (en) * | 2019-06-17 | 2019-09-10 | 南京大学 | A kind of open route traffic participant collecting method based on computer vision |
| CN110675362A (en) * | 2019-08-16 | 2020-01-10 | 长安大学 | Method for acquiring horizon under monitoring environment of curved road |
| CN110909620A (en) * | 2019-10-30 | 2020-03-24 | 北京迈格威科技有限公司 | Vehicle detection method and device, electronic equipment and storage medium |
| CN111401248A (en) * | 2020-03-17 | 2020-07-10 | 北京百度网讯科技有限公司 | Sky area identification method and device, electronic equipment and storage medium |
| CN111798431A (en) * | 2020-07-06 | 2020-10-20 | 苏州市职业大学 | Real-time vanishing point detection method, device, equipment and storage medium |
| CN112132869A (en) * | 2020-11-02 | 2020-12-25 | 中远海运科技股份有限公司 | Vehicle target track tracking method and device |
| CN112598665A (en) * | 2020-12-31 | 2021-04-02 | 北京深睿博联科技有限责任公司 | Method and device for detecting vanishing points and vanishing lines of Manhattan scene |
| CN113781562A (en) * | 2021-09-13 | 2021-12-10 | 山东大学 | Lane line virtual and real registration and self-vehicle positioning method based on road model |
| CN116682209A (en) * | 2023-06-15 | 2023-09-01 | 南昌交通学院 | Automatic vending machine inventory management method and system based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101608924A (en) * | 2009-05-20 | 2009-12-23 | 电子科技大学 | A kind of method for detecting lane lines based on gray scale estimation and cascade Hough transform |
| CN103871079A (en) * | 2014-03-18 | 2014-06-18 | 南京金智视讯技术有限公司 | Vehicle tracking method based on machine learning and optical flow |
| CN106101485A (en) * | 2016-06-02 | 2016-11-09 | 中国科学技术大学 | A kind of prospect track decision method based on feedback and device |
| CN107067755A (en) * | 2017-04-28 | 2017-08-18 | 深圳市唯特视科技有限公司 | A kind of method for calibrating traffic monitoring camera automatically based on computer vision |
| CN107977664A (en) * | 2017-12-08 | 2018-05-01 | 重庆大学 | A kind of road vanishing Point Detection Method method based on single image |
-
2018
- 2018-09-30 CN CN201811154229.5A patent/CN109446917B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101608924A (en) * | 2009-05-20 | 2009-12-23 | 电子科技大学 | A kind of method for detecting lane lines based on gray scale estimation and cascade Hough transform |
| CN103871079A (en) * | 2014-03-18 | 2014-06-18 | 南京金智视讯技术有限公司 | Vehicle tracking method based on machine learning and optical flow |
| CN106101485A (en) * | 2016-06-02 | 2016-11-09 | 中国科学技术大学 | A kind of prospect track decision method based on feedback and device |
| CN107067755A (en) * | 2017-04-28 | 2017-08-18 | 深圳市唯特视科技有限公司 | A kind of method for calibrating traffic monitoring camera automatically based on computer vision |
| CN107977664A (en) * | 2017-12-08 | 2018-05-01 | 重庆大学 | A kind of road vanishing Point Detection Method method based on single image |
Non-Patent Citations (3)
| Title |
|---|
| MARKETA DUBSKA: ""Point and line parameterizations using parallel coordinates for hough transform"", 《BRNO UNIVERSITY OF TECHNOLOGY DOCTORAL THESIS》 * |
| MARKETA DUBSKA: ""Real projective plane mapping for detection of orthogonal vanishing points"", 《DUBSKA》 * |
| 张茜婷: ""车辆特征点3D参数估计及聚类算法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222667A (en) * | 2019-06-17 | 2019-09-10 | 南京大学 | A kind of open route traffic participant collecting method based on computer vision |
| CN110675362B (en) * | 2019-08-16 | 2022-10-28 | 长安大学 | Method for acquiring horizon under curved road monitoring environment |
| CN110675362A (en) * | 2019-08-16 | 2020-01-10 | 长安大学 | Method for acquiring horizon under monitoring environment of curved road |
| CN110909620A (en) * | 2019-10-30 | 2020-03-24 | 北京迈格威科技有限公司 | Vehicle detection method and device, electronic equipment and storage medium |
| CN111401248A (en) * | 2020-03-17 | 2020-07-10 | 北京百度网讯科技有限公司 | Sky area identification method and device, electronic equipment and storage medium |
| CN111401248B (en) * | 2020-03-17 | 2023-08-15 | 阿波罗智联(北京)科技有限公司 | Sky area identification method and device, electronic equipment and storage medium |
| CN111798431A (en) * | 2020-07-06 | 2020-10-20 | 苏州市职业大学 | Real-time vanishing point detection method, device, equipment and storage medium |
| CN111798431B (en) * | 2020-07-06 | 2023-09-15 | 苏州市职业大学 | Real-time vanishing point detection method, device, equipment and storage medium |
| CN112132869A (en) * | 2020-11-02 | 2020-12-25 | 中远海运科技股份有限公司 | Vehicle target track tracking method and device |
| CN112132869B (en) * | 2020-11-02 | 2024-07-19 | 中远海运科技股份有限公司 | Vehicle target track tracking method and device |
| CN112598665A (en) * | 2020-12-31 | 2021-04-02 | 北京深睿博联科技有限责任公司 | Method and device for detecting vanishing points and vanishing lines of Manhattan scene |
| CN112598665B (en) * | 2020-12-31 | 2022-05-06 | 北京深睿博联科技有限责任公司 | Method and device for detecting vanishing points and vanishing lines of Manhattan scene |
| CN113781562A (en) * | 2021-09-13 | 2021-12-10 | 山东大学 | Lane line virtual and real registration and self-vehicle positioning method based on road model |
| CN113781562B (en) * | 2021-09-13 | 2023-08-04 | 山东大学 | Lane line virtual-real registration and self-vehicle positioning method based on road model |
| CN116682209A (en) * | 2023-06-15 | 2023-09-01 | 南昌交通学院 | Automatic vending machine inventory management method and system based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109446917B (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446917A (en) | A kind of vanishing Point Detection Method method based on cascade Hough transform | |
| CN112883819B (en) | Multi-target tracking method, device, system and computer readable storage medium | |
| CN103077384B (en) | A kind of method and system of vehicle-logo location identification | |
| CN101950426B (en) | Vehicle relay tracking method in multi-camera scene | |
| CN103546726B (en) | Method for automatically discovering illegal land use | |
| CN111079556A (en) | Multi-temporal unmanned aerial vehicle video image change area detection and classification method | |
| CN108038415B (en) | Unmanned aerial vehicle automatic detection and tracking method based on machine vision | |
| DE102015206178A1 (en) | A video tracking-based method for automatically ranking vehicles in drive through applications | |
| CN106128121B (en) | Vehicle queue length fast algorithm of detecting based on Local Features Analysis | |
| CN109341580A (en) | Method for tracing, system and the device of profile of steel rail | |
| CN101847265A (en) | Method for extracting moving objects and partitioning multiple objects used in bus passenger flow statistical system | |
| CN109544635B (en) | Camera automatic calibration method based on enumeration heuristic | |
| CN107248174A (en) | A kind of method for tracking target based on TLD algorithms | |
| CN103646257A (en) | Video monitoring image-based pedestrian detecting and counting method | |
| CN105160649A (en) | Multi-target tracking method and system based on kernel function unsupervised clustering | |
| CN106228570A (en) | A kind of Truth data determines method and apparatus | |
| Selver et al. | Camera based driver support system for rail extraction using 2-D Gabor wavelet decompositions and morphological analysis | |
| CN106803262A (en) | The method that car speed is independently resolved using binocular vision | |
| CN107944354A (en) | A kind of vehicle checking method based on deep learning | |
| CN103295221A (en) | Water surface target motion detecting method simulating compound eye visual mechanism and polarization imaging | |
| CN109919832A (en) | One kind being used for unpiloted traffic image joining method | |
| CN110134148A (en) | A kind of transmission line of electricity helicopter make an inspection tour in tracking along transmission line of electricity | |
| CN103578121A (en) | Motion detection method based on shared Gaussian model in disturbed motion environment | |
| CN105741317B (en) | Infrared motion target detection method based on time-space domain significance analysis and rarefaction representation | |
| CN114137512B (en) | Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220830 |