CN104992149A - Mixing line detection method, mixing line detection system, network video camera and monitoring system - Google Patents
Mixing line detection method, mixing line detection system, network video camera and monitoring system Download PDFInfo
- Publication number
- CN104992149A CN104992149A CN201510350017.4A CN201510350017A CN104992149A CN 104992149 A CN104992149 A CN 104992149A CN 201510350017 A CN201510350017 A CN 201510350017A CN 104992149 A CN104992149 A CN 104992149A
- Authority
- CN
- China
- Prior art keywords
- line
- region
- grad
- state
- region unit
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
Abstract
The invention provides a mixing line detection method. The method comprises performing a gray scale, a frame difference and a two value on two adjacent frames of video monitoring images, obtaining more than two region blocks intersected with a mixing line region, generating a dividing line of the region blocks according to a mixing line direction, calculating gradient values of all region blocks on two side edges of the diving line to obtain states of the region blocks, performing statistics of all the region blocks, and then obtaining a state of a target object corresponding to the region block. The invention further provides a mixing line detection system. The invention further provides a network video camera and a monitoring system, and execution efficiency is improved.
Description
Technical field
The present invention relates to one and mix line detecting method, system, web camera and supervisory system.
Background technology
Mixing that line detects is common intelligent early-warning function in video monitoring process, and this function by drawing a straight line on monitored picture as mixing line, and judges whether assigned direction exists illegal cross-lane.
Traditional line detection technique major part of mixing is method based on moving body track at present, and these class methods generally can be partitioned into prospect part by background modeling, and then follows the tracks of foreground object, finally judges that foreground object is by mixing the direction of line.
Traditional at present to mix the dependence of line detection technique to background modeling and track algorithm very high, thus generally there is following shortcoming:
1. the computation complexity of background modeling and track algorithm is high, and algorithm execution performance is limited.
2., owing to using background modeling, need to use mass data in advance, the time trains background model.
3. track algorithm needs the response process of a period of time for the object occurred, therefore mixes line and does not generally allow to be arranged on scene boundary.
4., in close shot scene (large dimension of object), general track algorithm cannot process large scale prospect, and causes following the tracks of unsuccessfully, mixes line measuring ability simultaneously and also cannot normally work.
Summary of the invention
The technical problem to be solved in the present invention, is to provide one to mix line detecting method, system, web camera and supervisory system, improves execution efficiency.
One of the present invention is achieved in that one mixes line detecting method, comprises the steps:
Step 1, adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, and obtain the two or more region unit crossing with mixing line region;
Step 2: according to mixing line direction, the dividing line of formation zone block;
Step 3: calculate the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Step 4: the state of adding up all region units, obtains the state of target object corresponding to region unit.
Further, in described step 1, " obtaining the two or more region unit crossing with mixing line region " is specially: zoning block profile point set, if point concentrates any point to mix Nei Ze judging area, line region block crossing with mixing line region.
Further, in described step 2, the generation method of the dividing line of region unit is: make two linear vertical in mixing line, afterwards by these two rectilinear movements, clamp target object both sides, respectively there is an intersection point both sides of two straight lines and target object, and the straight line connecting these two intersection points is dividing line.
Further, in described step 3, " calculate the Grad size of all region units in dividing line both sides of the edge; obtain region unit state " to be specially: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
Further, in described step 3, during the Grad of computation partition line two side areas block edge, with vertical and horizontal sobel operator, namely when dividing line slope is between [-1,1], use horizontal operator, otherwise use vertical operator.
Further, in described step 4, the method of " adding up the state of all region units; obtain the state of target object corresponding to region unit " is: the situation of adding up all region units, when region unit when more than 50% is judged as Positive or Negative state, then judges that target object passes through and mix line; Otherwise target object does not pass through mixes line.
The present invention's two is achieved in that one mixes line detection system, and it comprises with lower module:
Region unit acquisition module: for doing that gray scale, frame are poor, two-value by with the crossing video monitoring image in line region of mixing preset, obtain plural region unit;
Dividing line generation module: mix line direction, the dividing line of formation zone block for basis;
Region unit state acquisition module: for calculating the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Target object state acquisition module: for adding up the state of all region units, obtain the state of target object corresponding to region unit.
Further, it comprises with lower module:
Region unit acquisition module: gray scale, frame are poor for being done by adjacent two frame video monitoring images, two-value, and obtain the two or more region unit crossing with mixing line region;
Dividing line generation module: mix line direction for basis, make two linear vertical in mixing line, afterwards by these two rectilinear movements, clamp target object both sides, respectively there is an intersection point both sides of two straight lines and target object, and the straight line connecting these two intersection points is dividing line;
Region unit state acquisition module: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
Target object state acquisition module: for adding up the situation of all region units, when the region unit when more than 50% is judged as Positive or Negative state, then judge that target object passes through and mix line; Otherwise target object does not pass through mixes line.
The present invention's three is achieved in that a kind of web camera, and it comprises described mixes line detection system.
The present invention's four is achieved in that a kind of supervisory system, and it comprises described mixes line detection system.
Tool of the present invention has the following advantages: one of the present invention mixes line detecting method and system, does not rely on traditional background modeling and prospect track algorithm; Only need to use front and back two two field pictures, because the edge of front frame object is in frame difference result, the response along movement direction of object side is very large, and utilize this principle can realize mixing line and detect, algorithm is simple, execution efficiency is high; All can normally work under scene boundary or close shot scene.
Accompanying drawing explanation
The present invention is further illustrated in conjunction with the embodiments with reference to the accompanying drawings.
Fig. 1 is the inventive method flowchart.
Fig. 2 is the process flow diagram of the embodiment of the present invention one.
Fig. 3 is the schematic diagram one of the embodiment of the present invention two.
Fig. 4 is the schematic diagram two of the embodiment of the present invention two.
Fig. 5 is the schematic diagram one of the embodiment of the present invention three.
Fig. 6 is the schematic diagram two of the embodiment of the present invention three.
Fig. 7 is the schematic diagram of the embodiment of the present invention four.
Embodiment
As shown in Figure 1, as shown in Figure 1, the present invention mixes line detecting method, comprises the steps:
Step 1, adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, and obtain the two or more region unit crossing with mixing line region;
Step 2: according to mixing line direction, the dividing line of formation zone block;
Step 3: calculate the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Step 4: the state of adding up all region units, obtains the state of target object corresponding to region unit.
Embodiment 1
As shown in Figure 2, the present invention mixes line detecting method, specifically comprises the steps:
Step 1, adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, and obtain the two or more region unit crossing with mixing line region;
Step 2: according to mixing line direction, the dividing line of formation zone block; Wherein, the generation method of the dividing line of region unit is: make two linear vertical in mixing line, afterwards by these two rectilinear movements, clamp target object both sides, respectively there is an intersection point both sides of two straight lines and target object, and the straight line connecting these two intersection points is dividing line.
Step 3: calculate the Grad size of all region units in dividing line both sides of the edge, obtain region unit state; The concrete operations of this step are: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
Step 4: the state of adding up all region units, obtains the state of target object corresponding to region unit.The concrete grammar of this step is: the situation of adding up all region units, when the region unit when more than 50% is judged as Positive or Negative state, then judges that target object passes through and mixes line; Otherwise, judge that target object does not pass through and mix line.When region unit when more than 50% is marked as Positive state, judges that target object forward passes through and mix line; When region unit when more than 50% is marked as Negative state, judges that target object negative sense passes through and mix line.
One of outstanding inventive point of the present invention is: utilize " edge of front frame object is in frame difference result; the response along movement direction of object side is very large " this principle, only need to use front and back two two field pictures can realize mixing line to detect, do not need to depend on traditional background modeling and prospect track algorithm; Algorithm is simple, execution efficiency is high; All can normally work under scene boundary or close shot scene.
The present invention mixes in line detecting method, " obtains the two or more region unit crossing with mixing line region " and is specially: zoning block profile point set in step 1, if point concentrates any point to mix Nei Ze judging area, line region block crossing with mixing line region.
The present invention mixes in line detecting method, in described step 3, during the Grad of computation partition line two side areas block edge, with vertical and horizontal sobel operator, namely when dividing line slope is between [-1,1], uses horizontal operator, otherwise uses vertical operator.
Embodiment 2, moves from left to right:
Shown in Fig. 3, step 1, setting mix line 1, and mix line 1 surrounding dotted line for mixing line region 2, object moves from left to right.Adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, obtain frame difference region unit 3, frame difference region unit 3 not yet enters mixes line 1 region.
As shown in Figure 4, step 2, basis mix line direction, the dividing line of delta frame difference region unit 3; Wherein, the generation method of the dividing line of frame difference region unit 3 is: making two linear vertical in mixing line, afterwards by these two rectilinear movements, clamping target object both sides, article two, respectively there is an intersection point both sides of straight line and target object, and the straight line connecting these two intersection points is dividing line.
Frame difference region unit 3 enters mixes line 1 region, the sobel Grad of frame difference region unit 3 both sides is calculated along dividing line, the intersection point in the lower left corner crossing with frame difference region unit 3 for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad at the region unit edge on the left of dividing line is defined as clockwise Grad, and the Grad at the region unit edge on the right side of dividing line defines counterclockwise Grad.Causing Grad very little because being in interior of articles texture position on the left of characteristic area block 1, on the right side of region unit, causing Grad very large because being in the edge of object.Now, gradient clockwise on the right side of left side is counterclockwise gradient <<, be judged as Negative, Negative region unit number accounting more than 50%, is judged to oppositely to pass through to mix line.
Embodiment 3
As shown in Figure 5, step 1, setting mix line 1, mix line 1 surrounding dotted line for mixing line region 2, and object is from right toward left movement.Adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, obtain frame difference region unit 3, frame difference region unit 3 not yet enters mixes line 1 region.
As shown in Figure 6, step 2, basis mix line direction, the dividing line of delta frame difference region unit 3; Wherein, the generation method of the dividing line of frame difference region unit 3 is: making two linear vertical in mixing line, afterwards by these two rectilinear movements, clamping target object both sides, article two, respectively there is an intersection point both sides of straight line and target object, and the straight line connecting these two intersection points is dividing line.
Frame difference region unit 3 enters mixes line 1 region, the sobel Grad of frame difference region unit 3 both sides is calculated along dividing line, the intersection point in the lower left corner crossing with frame difference region unit 3 for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad at the region unit edge on the left of dividing line is defined as clockwise Grad, and the Grad at the region unit edge on the right side of dividing line defines counterclockwise Grad.Causing Grad very little because being in interior of articles texture position on the right side of characteristic area block 1, on the left of region unit, causing Grad very large because being in the edge of object.Now, gradient clockwise on the right side of left side is counterclockwise gradient G reatT.GreaT.GT>, be judged as Positive, Positive region unit number accounting more than 50%, is judged to be that forward passes through and mixes line.
Embodiment 4
As Fig. 7, step 1, setting mix line 1, and mix line 1 surrounding dotted line for mixing line region 2, object moves from left to right.Adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, obtain frame difference region unit 3, frame difference region unit 3 not yet enters mixes line 1 region.
As shown in Figure 7, step 2, basis mix line direction, the dividing line of delta frame difference region unit 3; Wherein, the generation method of the dividing line of frame difference region unit 3 is: making two linear vertical in mixing line, afterwards by these two rectilinear movements, clamping target object both sides, article two, respectively there is an intersection point both sides of straight line and target object, and the straight line connecting these two intersection points is dividing line.
Frame difference region unit 3 enters mixes line region 2, and along the sobel Grad of block both sides, dividing line zoning, the upper and lower both sides of region unit cause Grad very little because being in interior of articles texture position.Now, most of region unit is judged as NULL (namely the counterclockwise gradient in downside and the clockwise gradient in upside are more or less the same), has respective regions block to be judged as Positive and Negative.NULL region unit number accounting more than 50%, is judged to not pass through and mixes line.
Present invention also offers one and mix line detection system, it comprises with lower module:
Region unit acquisition module: for doing that gray scale, frame are poor, two-value by with the crossing video monitoring image in line region of mixing preset, obtain plural region unit;
Dividing line generation module: mix line direction, the dividing line of formation zone block for basis;
Region unit state acquisition module: for calculating the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Target object state acquisition module: for adding up the state of all region units, obtain the state of target object corresponding to region unit.
Embodiment 5
Of the present inventionly mix line detection system, it specifically comprises with lower module:
Region unit acquisition module: gray scale, frame are poor for being done by adjacent two frame video monitoring images, two-value, and obtain the two or more region unit crossing with mixing line region;
Concrete operations are " to obtain the two or more region unit crossing with mixing line region ": zoning block profile point set, if point concentrates any point to mix Nei Ze judging area, line region block crossing with mixing line region.
Dividing line generation module: mix line direction for basis, make two linear vertical in mixing line, afterwards by these two rectilinear movements, clamp target object both sides, respectively there is an intersection point both sides of two straight lines and target object, and the straight line connecting these two intersection points is dividing line;
Region unit state acquisition module: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
Target object state acquisition module: for adding up the situation of all region units, when the region unit when more than 50% is marked as Positive or Negative state, then judge that target object passes through and mix line; Otherwise target object does not pass through mixes line.When region unit when more than 50% is marked as Positive state, judges that target object forward passes through and mix line; When region unit when more than 50% is marked as Negative state, judges that target object negative sense passes through and mix line.
The invention also discloses a kind of web camera, it comprises described mixes line detection system.
The invention also discloses a kind of supervisory system, it comprises described mixes line detection system.
Although the foregoing describe the specific embodiment of the present invention; but be familiar with those skilled in the art to be to be understood that; specific embodiment described by us is illustrative; instead of for the restriction to scope of the present invention; those of ordinary skill in the art, in the modification of the equivalence done according to spirit of the present invention and change, should be encompassed in scope that claim of the present invention protects.
Claims (10)
1. mix a line detecting method, it is characterized in that: comprise the steps:
Step 1, adjacent two frame video monitoring images are done gray scale, frame are poor, two-value, and obtain the two or more region unit crossing with mixing line region;
Step 2: according to mixing line direction, the dividing line of formation zone block;
Step 3: calculate the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Step 4: the state of adding up all region units, obtains the state of target object corresponding to region unit.
2. according to claim 1ly mix line detecting method, it is characterized in that: in described step 1, " obtain the two or more region unit crossing with mixing line region " to be specially: zoning block profile point set, if point concentrates any point to mix Nei Ze judging area, line region block crossing with mixing line region.
3. according to claim 1ly mix line detecting method, it is characterized in that:
In described step 2, the generation method of the dividing line of region unit is: making two linear vertical in mixing line, afterwards by these two rectilinear movements, clamping target object both sides, article two, respectively there is an intersection point both sides of straight line and target object, and the straight line connecting these two intersection points is dividing line.
4. according to claim 1ly mix line detecting method, it is characterized in that: in described step 3,
" calculate the Grad size of all region units in dividing line both sides of the edge; obtain region unit state " to be specially: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
5. according to claim 4ly mix line detecting method, it is characterized in that: in described step 3, during the Grad of computation partition line two side areas block edge, with vertical and horizontal sobel operator, namely when dividing line slope is [-1,1] time between, use horizontal operator, otherwise use vertical operator.
6. according to claim 1ly mix line detecting method, it is characterized in that: in described step 4, the method of " adding up the state of all region units; obtain the state of target object corresponding to region unit " is: the situation of adding up all region units, when region unit when more than 50% is judged as Positive or Negative state, then judges that target object passes through and mix line; Otherwise target object does not pass through mixes line.
7. mix a line detection system, it is characterized in that: it comprises with lower module:
Region unit acquisition module: for doing that gray scale, frame are poor, two-value by with the crossing video monitoring image in line region of mixing preset, obtain plural region unit;
Dividing line generation module: mix line direction, the dividing line of formation zone block for basis;
Region unit state acquisition module: for calculating the Grad size of all region units in dividing line both sides of the edge, obtain region unit state;
Target object state acquisition module: for adding up the state of all region units, obtain the state of target object corresponding to region unit.
8. according to right 7, mix line detection system, it is characterized in that: it comprises with lower module:
Region unit acquisition module: gray scale, frame are poor for being done by adjacent two frame video monitoring images, two-value, and obtain the two or more region unit crossing with mixing line region;
Dividing line generation module: mix line direction for basis, make two linear vertical in mixing line, afterwards by these two rectilinear movements, clamp target object both sides, respectively there is an intersection point both sides of two straight lines and target object, and the straight line connecting these two intersection points is dividing line;
Region unit state acquisition module: the intersection point in the lower left corner crossing with region unit for dividing line is defined as starting point, another intersection point is terminal, according to the direction of starting point to terminal, the Grad of dividing line two side areas block edge is defined as clockwise Grad and counterclockwise Grad respectively, if Grad is greater than 2 times of counterclockwise Grad clockwise, determinating area bulk state is Negative; If Grad is greater than 2 times of clockwise Grad counterclockwise, determinating area bulk state is Positive; Other situation determinating area bulk states are Null.
Target object state acquisition module: for adding up the situation of all region units, when the region unit when more than 50% is judged as Positive or Negative state, then judge that target object passes through and mix line; Otherwise target object does not pass through mixes line.
9. a web camera, is characterized in that: it comprises mixes line detection system described in claim 7 or 8.
10. a supervisory system, is characterized in that: it comprises mixes line detection system described in claim 7 or 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510350017.4A CN104992149B (en) | 2015-06-24 | 2015-06-24 | Mix line detecting method, system, web camera and monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510350017.4A CN104992149B (en) | 2015-06-24 | 2015-06-24 | Mix line detecting method, system, web camera and monitoring system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104992149A true CN104992149A (en) | 2015-10-21 |
CN104992149B CN104992149B (en) | 2018-05-04 |
Family
ID=54303962
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510350017.4A Active CN104992149B (en) | 2015-06-24 | 2015-06-24 | Mix line detecting method, system, web camera and monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104992149B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106650599A (en) * | 2016-10-14 | 2017-05-10 | 北京智眸科技有限公司 | A method for setting sparse sampling frequency regionally and selecting sampling points in stereo matching |
CN113450522A (en) * | 2021-05-28 | 2021-09-28 | 浙江大华技术股份有限公司 | Video cable mixing intrusion detection method, electronic device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080137960A1 (en) * | 2006-12-08 | 2008-06-12 | Electronics And Telecommunications Research Insititute | Apparatus and method for detecting horizon in sea image |
CN103425960A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术(北京)有限公司 | Method for detecting fast-moving objects in video |
CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
-
2015
- 2015-06-24 CN CN201510350017.4A patent/CN104992149B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080137960A1 (en) * | 2006-12-08 | 2008-06-12 | Electronics And Telecommunications Research Insititute | Apparatus and method for detecting horizon in sea image |
CN103425960A (en) * | 2012-05-25 | 2013-12-04 | 信帧电子技术(北京)有限公司 | Method for detecting fast-moving objects in video |
CN104021570A (en) * | 2014-06-04 | 2014-09-03 | 电子科技大学 | Method for directional cross-border detection and mixing line detection in video |
Non-Patent Citations (1)
Title |
---|
林树涛等: "基于OMAP3730的智能监控技术设计与实现", 《现代电子技术》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106650599A (en) * | 2016-10-14 | 2017-05-10 | 北京智眸科技有限公司 | A method for setting sparse sampling frequency regionally and selecting sampling points in stereo matching |
CN113450522A (en) * | 2021-05-28 | 2021-09-28 | 浙江大华技术股份有限公司 | Video cable mixing intrusion detection method, electronic device and storage medium |
CN113450522B (en) * | 2021-05-28 | 2022-10-04 | 浙江大华技术股份有限公司 | Video cable mixing intrusion detection method, electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104992149B (en) | 2018-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9706188B2 (en) | Binocular camera resetting method and binocular camera resetting apparatus | |
CN105575125B (en) | A kind of wagon flow video detecting analysis system | |
CN107316312A (en) | A kind of video image occlusion detection method and system | |
CN101272451A (en) | Motion estimation method | |
CN104410855A (en) | Jitter detection method of monitoring video | |
CN105354857B (en) | A kind of track of vehicle matching process for thering is viaduct to block | |
CN110307791A (en) | Vehicle length and speed calculation method based on three-dimensional vehicle bounding box | |
CN105574891A (en) | Method and system for detecting moving object in image | |
CN104364796A (en) | Method and device for processing stereoscopic data | |
CN103458261A (en) | Video scene variation detection method based on stereoscopic vision | |
CN106530328A (en) | Method for detecting and smoothly following moving object based on video images | |
CN106097734A (en) | A kind of plane perception detection method controlled for crossing traffic signal and system | |
CN101894380A (en) | Method for tracing target object in panoramic video automatically | |
CN104992149A (en) | Mixing line detection method, mixing line detection system, network video camera and monitoring system | |
CN107509059A (en) | Camera lens occlusion detection method | |
CN104933418A (en) | Population size counting method of double cameras | |
CN102156989A (en) | Vehicle blocking detection and segmentation method in video frame | |
CN106295557A (en) | A kind of method and device of crowd density estimation | |
CN102169583B (en) | Vehicle shielding detection and segmentation method based on vehicle window positioning | |
CN103337064A (en) | Method for removing mismatching point in image stereo matching | |
CN104301699A (en) | Image processing method and device | |
CN102542267A (en) | Salient region detecting method combining spatial distribution and global contrast | |
CN101739553B (en) | Method for identifying target in parallax image | |
CN106157301A (en) | A kind of threshold value for Image Edge-Detection is from determining method and device | |
CN105631868A (en) | Depth information extraction method based on image classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 350108, No. 2, building 9, 7 hi tech Avenue, Fuzhou Town, Minhou County, Fujian, China Applicant after: Fujian star net joint information system Co., Ltd. Address before: 350000, No. 2, building 9, 7 hi tech Avenue, Fuzhou Town, Minhou County, Fujian, China Applicant before: Fujian Star-Net Security Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |