CN108805847A - Detection suitable for ship and tracking - Google Patents
Detection suitable for ship and tracking Download PDFInfo
- Publication number
- CN108805847A CN108805847A CN201810392842.4A CN201810392842A CN108805847A CN 108805847 A CN108805847 A CN 108805847A CN 201810392842 A CN201810392842 A CN 201810392842A CN 108805847 A CN108805847 A CN 108805847A
- Authority
- CN
- China
- Prior art keywords
- ship
- detection
- boundary
- tracking
- waterfront
- 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- Withdrawn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
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 230000000877 morphologic effect Effects 0.000 claims abstract description 11
- 238000005260 corrosion Methods 0.000 claims description 9
- 230000007797 corrosion Effects 0.000 claims description 9
- 238000005498 polishing Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 10
- 230000000694 effects Effects 0.000 abstract description 3
- 230000000386 athletic effect Effects 0.000 abstract 1
- 238000000034 method Methods 0.000 description 12
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
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)
Abstract
The invention discloses a kind of detection suitable for ship and trackings comprising following steps：(1) use Canny operator combination waterfront boundary profile information extractions without the waterfront boundary line in the case of ship the video sequence of input；(2) motion history figure is extracted；(3) Morphological scale-space is carried out to the water-surface areas in motion history figure；And (4) rebuild ship profile boundary rectangle；The present invention detaches the riverbank region of Interference Detection by extracting waterfront boundary line, eliminate deck movements object effects, reasonable utilization Morphological scale-space eliminates the non-athletic target jamming of the water surface, in conjunction with profile boundary rectangle rebuild completion because speed excessively slowly caused by the movement locus that lacks, realize the accurate of ship under complicated port environment and detect and real-time tracking.
Description
Technical field
The present invention relates to moving object detection fields, are in more detail related to a kind of detection suitable for ship and track side
Method.
Background technology
Moving object detection is to come out interested Acquiring motion area in image sequence, for subsequently carry out target with
Track.Current existing domestic and international application can be divided into the moving target detecting method of ship detecting and tracking according to detection medium：
Satellite image, four major class of radar image, infrared image and sequence of video images.It can be divided into according to application direction：Ship's fix,
Ship collision prevention early warning and ship flow monitoring three classes.Wherein, the ship based on satellite image, radar image and infrared image
Detection and tracking, the cost is relatively high, and professional person is needed to operate, and causes to be difficult to obtain in civil field extensively
Using.And the ship detecting based on sequence of video images and tracking, cost are relatively low, easy to operate, and obtained extensively in water transport project
General application.
But it is based on single or static mostly currently based on the ship moving object detection algorithm of sequence of video images
The frame differential method or background subtraction of background environment, the ship moved by the Differential Detection of present image and background image
Oceangoing ship, such method are easy to occur the case where caused flase drop by the interference of deck movements target.Therefore, for complicated harbour ring
Border and the ship detecting under complicated aquatic environment and tracking, traditional calculus of finite differences has been difficult to meet actual demand, and is based on
Then there is the problems such as ship identification library training difficulty is big, time-consuming, poor universality in the method for machine learning.
In conclusion there is an urgent need for a kind of new detections suitable for ship to solve the above problems with tracking for this field.
Invention content
It is an object of the present invention to provide a kind of detection suitable for ship and trackings, realize in complicated water
Real-time to ship target under face ring border, accurately detection and tracking.
It is another object of the present invention to provide a kind of detection suitable for ship and trackings, reduce monitor
The working strength of member realizes intelligent to the video monitoring of ship target.
Therefore, to achieve the goals above, the present invention provides a kind of detection suitable for ship and tracking comprising
Following steps：
(1) to the video sequence of input using Canny operator combination waterfront boundary profile information extractions without ship in the case of
Waterfront boundary line；
(2) motion history figure is extracted；
(3) Morphological scale-space is carried out to the water-surface areas in motion history figure, to eliminate in background non-targeted fortune on the water surface
Dynamic object；And
(4) ship profile boundary rectangle is rebuild.
According to a preferred embodiment of the invention, wherein including the following steps before the step (1)：Input video sequence
Row.
According to a preferred embodiment of the invention, include the following steps in the step (1)：
(11) essential information on waterfront boundary is detected by Canny operators；
(12) Morphological scale-space is carried out to discontinuous boundary information；
(13) lookup polishing is carried out to waterfront boundary profile；And
(14) primary to step (13) iteration to above-mentioned steps (11).
According to a preferred embodiment of the invention, the formula of extraction motion history figure is as follows wherein in step (2)：
Wherein, silhouette (x, y) > 0 indicates that the pixel at (x, y) moves, silhouette (x, y) < 0
Indicate that the pixel at (x, y) does not move, at the time of mhi (x, y) indicates that the point moves, duration is indicated more
The period of new pixel motion state obtains the pixel moved by inter-frame difference, and records each pixel hair
The time of raw movement is timestamp, constantly updates the movement moment value of pixel in image, the fortune of pixel is characterized with this
Dynamic state.
According to a preferred embodiment of the invention, include the following steps between the step (2) and the step (3)
(21)：Motion history figure is subjected to waterfront separation along waterfront boundary line, obtains the motion history figure for only including water-surface areas.
According to a preferred embodiment of the invention, wherein the step (3) includes the following steps：
(31) corrosion treatment is carried out to the water-surface areas in motion history figure；With
(32) closed operation processing is carried out to the motion history figure after corrosion.
According to a preferred embodiment of the invention, wherein the step (4) includes the following steps：
(41) contour detecting is carried out to every frame motion history figure；With
(42) extraction profile external world rectangle, is saved in array R.
Wherein, the step (42) includes the following steps:
(421) array R is ranked up according to wide and height, extracts the wide W and high H of largest contours；
(422) extraction ship tail portion coordinate P (x, y)；And
(423) according to the wide W of largest contours and high H, and the tail portion coordinate P (x, y) of ship current location is combined to rebuild ship
Oceangoing ship profile boundary rectangle.
It wherein,, will most by ship tail portion coordinate P (x, y) as the upper left point for rebuilding rectangle in the step (423)
The wide W and high H of big profile rebuild profile boundary rectangle r as the width and height for rebuilding rectangle, using Rectr=Rect (P, W, H),
The regions r are ship Current location area, to realize ship tracking.
The above and other purposes of the present invention, feature, advantage will in the following detailed description, attached drawing and appended
Claim it is further clear.
Description of the drawings
Fig. 1 is according to a preferred embodiment of the present invention suitable for the detection of ship and the flow signal of tracking
Figure；
Fig. 2 is according to a preferred embodiment of the present invention suitable for the detection of ship and the extraction waterfront of tracking
The flow diagram of boundary line step；
Fig. 3 is according to a preferred embodiment of the present invention suitable for the detection of ship and the reconstruction ship of tracking
The flow diagram of profile boundary rectangle step.
Specific implementation mode
In the following, in conjunction with attached drawing and specific implementation mode, invention is described further, it should be noted that in not phase
Under the premise of conflict, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
It is described below for disclosing the present invention so that those skilled in the art can realize the present invention.It is excellent in being described below
Embodiment is selected to be only used as illustrating, it may occur to persons skilled in the art that other obvious modifications.It defines in the following description
The present invention basic principle can be applied to other embodiments, deformation scheme, improvement project, equivalent program and do not carry on the back
Other technologies scheme from the spirit and scope of the present invention.
It will be understood by those skilled in the art that the present invention exposure in, term " longitudinal direction ", " transverse direction ", "upper",
The orientation or position of the instructions such as "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside"
Relationship is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of description of the present invention and simplification of the description, rather than
Indicate or imply that signified device or element must have a particular orientation, with specific azimuth configuration and operation, therefore above-mentioned
Term is not considered as limiting the invention.
It is understood that term " one " is interpreted as " at least one " or " one or more ", i.e., in one embodiment,
The quantity of one element can be one, and in a further embodiment, the quantity of the element can be multiple, and term " one " is no
It can be interpreted as the limitation to quantity.
Referring to Fig. 1 to Fig. 3 of attached drawing, the detection and tracking suitable for ship according to a preferred embodiment of the present invention
Method will be elucidated in following description, wherein the detection suitable for ship passes through extraction waterfront side with tracking
Boundary line detaches the riverbank region of Interference Detection, eliminates deck movements object effects, it is non-that reasonable utilization Morphological scale-space eliminates the water surface
Moving target interfere, in conjunction with profile boundary rectangle rebuild completion because speed excessively slowly caused by lack movement locus, realize complexity
The accurate detection of ship and real-time tracking under port environment.
As shown in Fig. 1 of attached drawing, the detection suitable for ship includes the following steps with tracking：
(1) to the video sequence of input using Canny operator combination waterfront boundary profile information extractions without ship in the case of
Waterfront boundary line；
(2) motion history figure is extracted；
(3) Morphological scale-space is carried out to the water-surface areas in motion history figure, to eliminate in background non-targeted fortune on the water surface
Dynamic object；And
(4) ship profile boundary rectangle is rebuild.
It will be readily appreciated by those skilled in the art that wherein including the following steps before the step (1)：Input video
Sequence.
Method provided by the present invention is mainly used for pulling in shore on the water surface detection and tracking of ship, therefore is carrying out ship inspection
The bad interference surveyed and need moving target on elimination riverbank before tracking.
As shown in Fig. 2 of attached drawing, specifically, including the following steps in the step (1)：
(11) essential information on waterfront boundary is detected by Canny operators；
(12) Morphological scale-space is carried out to discontinuous boundary information；
(13) lookup polishing is carried out to waterfront boundary profile；And
(14) primary to step (13) iteration to above-mentioned steps (11).
It is noted that Canny operators detection waterfront boundary line has very strong versatility, compared to Color-based clustering
Method, testing result will not be affected because of Changes in weather.The essential information on the waterfront boundary that the step (11) obtains
It is not continuous, is not enough to the line of demarcation of the calibration water surface and riverbank.Therefore need step (12) to discontinuous boundary information into
Row Morphological scale-space so that connection is tentatively realized in most of discontinuous region in figure.Further, riverbank information is not at this time still
Completely, it needs into row information polishing, the step (13) carries out lookup polishing to waterfront boundary profile, and contour area is larger black
It is filled with white in color region.Finally, primary to step (13) iteration according to above-mentioned steps (11), you can to eliminate on riverbank
Hollow sectors obtain complete riverbank.
More specifically, the formula of extraction motion history figure is as follows wherein in step (2)：
Wherein, silhouette (x, y) > 0 indicates that the pixel at (x, y) moves, silhouette (x, y) < 0
Indicate that the pixel at (x, y) does not move, at the time of mhi (x, y) indicates that the point moves, duration is indicated more
The period of new pixel motion state obtains the pixel moved by inter-frame difference, and records each pixel hair
The time of raw movement is timestamp, constantly updates the movement moment value of pixel in image, the fortune of pixel is characterized with this
Dynamic state.
It sees on the whole, motion history figure illustrates movement beginning and ending time and the motion process of pixel, such pixel
Point motion history figure is actually the movement locus figure of a width binaryzation.
Wherein, include the following steps (21) between the step (2) and the step (3)：By motion history figure along
Waterfront boundary line carries out waterfront separation, obtains the motion history figure for only including water-surface areas.
The motion history of acquisition and waterfront boundary, which are subtracted each other, can eliminate deck movements day mark to ship detecting and tracking
It influences.
Due to wave, the floating material on the closer waters surface of the focal length of camera in actual environment be clearly captured to regarding
In frequency, a part for background is constituted.And this part becomes interference noise in motion history figure, influences the effect of ship detecting
Fruit.For such situation, algorithm provided by the present invention carries out Morphological scale-space to motion history figure, and noise is eliminated with this.
Further, the step (3) includes the following steps：
(31) corrosion treatment is carried out to the water-surface areas in motion history figure；With
(32) closed operation processing is carried out to the motion history figure after corrosion.
The moving object of other small volumes such as wave, floating material on the water surface can form noise point, when water surface wave ratio
It will connect together with hull areas when more rapid, vessel area is caused flase drop occur, it is therefore desirable to carry out corrosion treatment, eliminate
These noise spots.After the corrosion treatment of background, part ship movement locus will appear cavity and missing, after this is all unfavorable for
The detection of continuous ship profile.Therefore, in order to eliminate these disturbing factors, continue to carry out closed operation to the historical movement figure after corrosion
The movement locus with completion ship is improved in processing with this.
Motion mask algorithm is proposed by MIT Media Labs, is a kind of moving object detection based on inter-frame difference
Algorithm.The algorithm inherits that frame differential method is insensitive to light, adapts to the advantages that various dynamic environment.In addition, by adopting
The movement locus of moving target is described with motion history figure, can overcome the shortcomings of to be unable to extracting object complete area.But it should
Algorithm also inherits the shortcomings that frame differential method is dependent on inter frame temporal gap size is chosen so that the algorithm is slow to movement velocity
Object it is insensitive.Therefore, when velocity to moving target is slower, it may appear that target trajectory lacks, and inaccurate target is fixed
It position will be so that tracking failure.
According to above-mentioned moving object detection algorithm to the insensitive characteristic of object at a slow speed, can obtain to draw a conclusion：Work as ship
When oceangoing ship does not slow down, movement locus is complete display；When ship pulls in shore, since speed is to be progressively smaller until ship
Stop, movement locus then will appear missing；Ship size variation unobvious in vessel area during actual deceleration.Therefore,
We can use the profile boundary rectangle of the movement locus under ship normal operation, in conjunction with the current position coordinates of ship,
To indicate the vessel area position under movement locus deletion condition.
As shown in Fig. 3 of attached drawing, wherein the step (4) includes the following steps：
(41) contour detecting is carried out to every frame motion history figure；With
(42) extraction profile external world rectangle, is saved in array R.
Wherein, the step (42) includes the following steps:
(421) array R is ranked up according to wide and height, extracts the wide W and high H of largest contours；
(422) extraction ship tail portion coordinate P (x, y)；And
(423) according to the wide W of largest contours and high H, and the tail portion coordinate P (x, y) of ship current location is combined to rebuild ship
Oceangoing ship profile boundary rectangle.
Specifically, when ship enters imaging area, since its speed is held essentially constant, so it is moved at this time
Track be it is complete reliable, being capable of accurate characterization vessel area.Meanwhile ship is not when completely into imaging area, ship
Region is gradually increased, and the movement locus with maximum boundary rectangle can accurately indicate vessel area range.Therefore, originally
The there is provided method of invention carries out contour detecting, the profile boundary rectangle that will be obtained first to the motion history figure that each frame obtains
It is saved in array R；Then, it to all rectangles in R, is sorted from big to small according to wide, high respectively；Finally obtained from array R
Take the wide W and high H of largest contours boundary rectangle.
When ship pulls in shore, fore first pulls in shore, and the tail portion of ship is since inertia is still moving, the motion history figure obtained at this time
Middle main movement track is the tail portion of ship, and ship tail portion coordinate P (x, y) is obtained so selecting.
In the step (423), by ship tail portion coordinate P (x, y) as the upper left point for rebuilding rectangle, by largest contours
Wide W and high H as the width and height for rebuilding rectangle, utilize Rectr=Rect (P, W, H) to rebuild where profile boundary rectangle r, r
Region is ship Current location area, to realize the tracking to ship.
It should be understood by those skilled in the art that the embodiment of the present invention shown in foregoing description and attached drawing is only used as illustrating
And it is not intended to limit the present invention.The purpose of the present invention has been fully and effectively achieved.The function and structural principle of the present invention exists
It shows and illustrates in embodiment, under without departing from the principle, embodiments of the present invention can have any deformation or modification.
Claims (9)
1. the detection suitable for ship and tracking, which is characterized in that include the following steps：
(1) use Canny operator combination waterfront boundary profile information extractions without the waterfront in the case of ship the video sequence of input
Boundary line；
(2) motion history figure is extracted；
(3) Morphological scale-space is carried out to the water-surface areas in motion history figure；And
(4) ship profile boundary rectangle is rebuild.
2. as described in claim 1 detection and tracking suitable for ship, which is characterized in that in the step (1)
Include the following steps：
(11) essential information on waterfront boundary is detected by Canny operators；
(12) Morphological scale-space is carried out to discontinuous boundary information；
(13) lookup polishing is carried out to waterfront boundary profile；And
(14) primary to step (13) iteration to above-mentioned steps (11).
3. as claimed in claim 2 detection and tracking suitable for ship, which is characterized in that carried in the step (2)
Take the formula of motion history figure as follows：
Wherein, silhouette (x, y) > 0 indicates that the pixel at (x, y) moves, and silhouette (x, y) < 0 is indicated
Pixel at (x, y) does not move, and at the time of mhi (x, y) indicates that the point moves, duration indicates update picture
The period of vegetarian refreshments motion state obtains the pixel moved by inter-frame difference, and records each pixel and transport
The dynamic time is timestamp, constantly updates the movement moment value of pixel in image, the movement shape of pixel is characterized with this
State.
4. as claimed in claim 3 detection and tracking suitable for ship, which is characterized in that in the step (2) and
Include the following steps (21) between the step (3)：Motion history figure is subjected to waterfront separation along waterfront boundary line.
5. as claimed in claim 4 detection and tracking suitable for ship, which is characterized in that the wherein described step (3)
Include the following steps：
(31) corrosion treatment is carried out to the water-surface areas in motion history figure；With
(32) closed operation processing is carried out to the motion history figure after corrosion.
6. as claimed in claim 5 detection and tracking suitable for ship, which is characterized in that the wherein described step (4)
Include the following steps：
(41) contour detecting is carried out to every frame motion history figure；With
(42) extraction profile external world rectangle, is saved in array R.
7. as claimed in claim 6 detection and tracking suitable for ship, which is characterized in that the wherein described step (42)
Include the following steps:
(421) array R is ranked up according to wide and height, extracts the wide W and high H of largest contours；
(422) extraction ship tail portion coordinate P (x, y)；And
(423) according to the wide W of largest contours and high H, and the tail portion coordinate P (x, y) of ship current location is combined to rebuild ship wheel
Wide boundary rectangle.
8. as claimed in claim 7 detection and tracking suitable for ship, which is characterized in that wherein in the step
(423) in, by ship tail portion coordinate P (x, y) as the upper left point for rebuilding rectangle, using the wide W of largest contours and high H as reconstruction
The width and height of rectangle, it is ship present bit to rebuild the regions profile boundary rectangle r, r using Rect r=Rect (P, W, H)
Set region.
9. the detection suitable for ship as described in any in claim 1 to 8 and tracking, which is characterized in that described
Include the following steps before step (1)：Input video sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810392842.4A CN108805847A (en) | 2018-04-27 | 2018-04-27 | Detection suitable for ship and tracking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810392842.4A CN108805847A (en) | 2018-04-27 | 2018-04-27 | Detection suitable for ship and tracking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108805847A true CN108805847A (en) | 2018-11-13 |
Family
ID=64093502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810392842.4A Withdrawn CN108805847A (en) | 2018-04-27 | 2018-04-27 | Detection suitable for ship and tracking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805847A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559333A (en) * | 2018-12-05 | 2019-04-02 | 中国科学院长春光学精密机械与物理研究所 | Track and record device |
| CN111752286A (en) * | 2020-03-09 | 2020-10-09 | 西南科技大学 | Automatic mooring method for small unmanned ship |
-
2018
- 2018-04-27 CN CN201810392842.4A patent/CN108805847A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109559333A (en) * | 2018-12-05 | 2019-04-02 | 中国科学院长春光学精密机械与物理研究所 | Track and record device |
| CN109559333B (en) * | 2018-12-05 | 2021-09-17 | 中国科学院长春光学精密机械与物理研究所 | Tracking recording device |
| CN111752286A (en) * | 2020-03-09 | 2020-10-09 | 西南科技大学 | Automatic mooring method for small unmanned ship |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409283A (en) | A kind of method, system and the storage medium of surface vessel tracking and monitoring | |
| Cucchiara et al. | Improving shadow suppression in moving object detection with HSV color information | |
| CN101872546B (en) | Video-based method for rapidly detecting transit vehicles | |
| CN107463890B (en) | A kind of Foregut fermenters and tracking based on monocular forward sight camera | |
| CN102968625B (en) | Ship distinguishing and tracking method based on trail | |
| Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
| TW201120806A (en) | Method of locating license plate of moving vehicle | |
| CN104408932A (en) | Drunk driving vehicle detection system based on video monitoring | |
| CN103198300B (en) | Parking event detection method based on double layers of backgrounds | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN113435336A (en) | Running intelligent timing system and method based on artificial intelligence | |
| CN108805847A (en) | Detection suitable for ship and tracking | |
| CN107194946A (en) | A kind of infrared obvious object detection method based on FPGA | |
| CN107038423A (en) | A kind of vehicle is detected and tracking in real time | |
| CN106934819A (en) | A kind of method of moving object segmentation precision in raising image | |
| Tian et al. | Road marking detection based on mask R-CNN instance segmentation model | |
| CN105913425A (en) | Self-adaptive oval blocking and wavelet transformation-based multi-pig contour extraction method | |
| Chen et al. | A novel AMS-DAT algorithm for moving vehicle detection in a satellite video | |
| CN107220982A (en) | It is a kind of to suppress the ship conspicuousness video detecting method that stern drags line | |
| Shi et al. | Obstacle type recognition in visual images via dilated convolutional neural network for unmanned surface vehicles | |
| CN107169412A (en) | Remote sensing image harbor-berthing ship detection method based on mixed model decision | |
| CN110473255A (en) | A kind of ship bollard localization method divided based on multi grid | |
| CN104267209A (en) | Method and system for expressway video speed measurement based on virtual coils | |
| CN103870795A (en) | Automatic detection method and device of video rolling subtitle | |
| Balisavira et al. | Real-time object detection by road plane segmentation technique for ADAS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181113 |
|
| WW01 | Invention patent application withdrawn after publication |