CN104410771B - A kind of mobile detection method and system - Google Patents
A kind of mobile detection method and system Download PDFInfo
- Publication number
- CN104410771B CN104410771B CN201410740363.9A CN201410740363A CN104410771B CN 104410771 B CN104410771 B CN 104410771B CN 201410740363 A CN201410740363 A CN 201410740363A CN 104410771 B CN104410771 B CN 104410771B
- Authority
- CN
- China
- Prior art keywords
- moving object
- frame
- continuous transition
- transition
- frames
- 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.)
- Active
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to mobile detection field, a kind of mobile detection method and system are provided.The following steps are included: obtaining the continuous transition frame between key frame during multimedia-data procession；It is respectively compared the size of First Transition frame and other continuous transition frames in continuous transition frame, if being all larger than preset mobile detection threshold value, extracts parsing motion vector, according to Dynamic Control Strategy, obtains the dynamic result of moving object.Present invention discloses according to the size variation between continuous transition frame, parsing motion vector is extracted, to describe the motion conditions of moving object.
Description
Technical field
The invention belongs to mobile detection field more particularly to a kind of mobile detection method and systems.
Background technique
The prior art provides a kind of adaptive global motion estimating method, including camera real-time image acquisition；It extracts
The i-th frame image in input image sequence when i≤5, calculates offset of the i+1 frame image relative to the i-th frame image, according to
Offset real-time rendering i+1 frame image corresponds to the camera motion track at moment；When i > 5, with Kalman filtering algorithm,
Prediction obtains offset of the i-th frame image relative to the (i-1)-th frame image, according to prediction drift amount, obtains the i-th frame image and i-th-
The overlapping region of 1 frame image, calculates the set of characteristic points of overlapping region, then calculates respectively each characteristic point in set
Four dimensional vector of feature point description subclass is obtained, and then obtains the matching pair of overlapping region feature point description and is obtained according to matching pair
Offset to the i-th frame image relative to the (i-1)-th frame image, real-time rendering the i-th frame image correspond to the camera moving rail at moment
Mark.
Above scheme does not disclose according to transition frames the motion conditions for describing moving object.
Summary of the invention
The present invention provides a kind of mobile detection method and system, to solve the above problems.
The present invention provides a kind of mobile detection method.The above method the following steps are included:
During multimedia-data procession, the continuous transition frame between key frame is obtained；
It is respectively compared the size of First Transition frame and other continuous transition frames in continuous transition frame, if being all larger than preset shifting
Dynamic detecting threshold value, then extract parsing motion vector, according to Dynamic Control Strategy, obtain the dynamic result of moving object.
The present invention also provides a kind of moving sensing systems, including obtain module, strategic control module；The acquisition module with
The strategic control module is connected；
The acquisition module, for during multimedia-data procession, obtaining the continuous transition frame between key frame simultaneously
The transition frames are sent to the strategic control module；
The strategic control module, for being respectively compared First Transition frame and other continuous transition frames in continuous transition frame
Size extracts parsing motion vector if being all larger than preset mobile detection threshold value, according to Dynamic Control Strategy, obtains movement
The dynamic result of object.
Parsing movement is extracted present invention discloses according to the size variation between continuous transition frame compared to prior art
Vector, to describe the motion conditions of moving object.
In addition, passing through following scheme: obtaining the big of First Transition frame and other continuous transition frames in continuous transition frame respectively
Small absolute value of the difference counts the quantity of the continuous transition frame and according to even if being all larger than preset mobile detection threshold value
Continuous transition number of frames and the calculating dynamic parameter table of comparisons, obtain the dynamic result of moving object, so that calculating the feelings of moving object
Condition is more accurate.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 show the mobile detection method flow chart of the embodiment of the present invention 1；
Fig. 2 show the moving sensing system structure chart of the embodiment of the present invention 2.
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
Fig. 1 show the mobile detection method flow chart of the embodiment of the present invention 1, comprising the following steps:
Step 101: during multimedia-data procession, obtaining the continuous transition frame between key frame；
Wherein, multi-medium data refers to video data；The transition frames refer to P frame；Treatment process refers to compression process.
Step 102: the size of First Transition frame and other continuous transition frames in continuous transition frame is respectively compared, if being all larger than
Preset mobile detection threshold value, then extract parsing motion vector, according to Dynamic Control Strategy, obtains the dynamic knot of moving object
Fruit；Wherein, the key frame refers to I frame.
Wherein, First Transition frame refer to before occur transition frames average value, the transition frames occurred below again with front
Average value compare.
Wherein, the dynamic result of moving object includes: the motion profile of moving object, the speed of moving object, moving object
The shape of body.
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if
Greater than preset mobile detection threshold value, then counts the quantity of the continuous transition frame and moved according to continuous transition number of frames and calculating
State parameter lookup table obtains the dynamic result of moving object.
Continuous transition number of frames and the calculating dynamic parameter table of comparisons
| Continuous transition number of frames | Calculate the dynamic parameter of moving object |
| Greater than the first preset value | Calculate the motion profile of moving object |
| Greater than the second preset value | Calculate speed, the motion profile of moving object |
| Greater than third preset value | Calculate shape, the speed, motion profile of moving object |
Table 1
Wherein, first preset value < the second preset value < third preset value, the first preset value, the second preset value, third are pre-
If value is set according to the actual situation, such as: the first preset value be the 2, second preset value be 4, third preset value is 6, this reality
It applies example and does not limit protection scope.
According to table 1: if the quantity of the continuous transition frame of statistics is greater than the first preset value, calculating moving object
Motion profile；If more than the second preset value, then movement velocity, the motion profile of moving object are calculated；It is default if more than third
Value, then calculate shape of movement, movement velocity, the motion profile of moving object.
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if
Greater than preset mobile detection threshold value, then the quantity of the continuous transition frame is counted, if the number of the continuous transition frame of statistics
Amount is greater than the first preset value, then calculates the process of the motion profile of moving object are as follows:
Moving object is extracted respectively for each transition frames according to the continuous transition frame between the key frame of acquisition
The motion vector of body, and further determine that the movement position of the moving object, to obtain the motion profile of moving object.
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if
Greater than preset mobile detection threshold value, then the quantity of the continuous transition frame is counted, if more than the second preset value, then calculates movement
The process of the movement velocity of object are as follows:
Moving object is extracted respectively for each transition frames according to the continuous transition frame between the key frame of acquisition
The motion vector of body, and further determine that the movement position of the moving object；
According to the position of moving object, picture size, moving object size in each transition frames of acquisition, obtain
Take the displacement of moving object in each transition frames；
According to the displacement of acquisition and code rate, the speed of the moving object is obtained.
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if
Greater than preset mobile detection threshold value, then the quantity of the continuous transition frame is counted, if more than third preset value, then calculates movement
The process of the shape of movement of object are as follows:
According to the profile that moving object in each transition frames of acquisition changes, moving object shape is obtained.
Citing is described in detail below:
Camera obtains automobile image and to be compressed driving on the road, obtain 3 transition frames (IPPPI, first
3) transition frames P quantity between I frame and the 2nd I frame is
If mobile detection threshold value be 100, the first preset value be the 2, second preset value be 4, third preset value is 6；If the first P
The size of frame be 800 bytes (if the first P frame before occur the i.e. previous P frame (size is 1000 bytes) of 2 transition frames P, the first two
P frame (size is 600 bytes), then First Transition frame P size is equal to the average value of the sum of previous P frame sign and the first two P frame sign
That is 800=(1000+600)/2), the size of the 2nd P frame be 950 bytes, the size of the 3rd P frame is 1000 bytes, then the first P frame
Magnitude difference absolute value with the 2nd P frame is 150, and the magnitude difference absolute value of the first P frame and the 3rd P frame is 200, they are big
In mobile detection threshold value 100, and consecutive variations P number of frames is greater than the first preset value 2, then combines table 1 it is found that needing to calculate fortune
The motion profile of animal body.
Calculate the process of the motion profile of moving object are as follows:
For transition frames P frame, the motion vector of automobile is extracted respectively, and further determines that the movement position of automobile, from
And obtain the motion profile of automobile.
If obtaining 5 transition frames, (5) IPPPPPI, the transition number of frames between the first I frame and the 2nd I frame are
If the size of the first P frame is 800 bytes, the size of the 2nd P frame is 1000 bytes, the 3rd P frame sign is 920 words
Section, the 4th P frame sign be 950 bytes, the 5th P frame sign be 940 bytes, then second and third, four, five P frames it is big with the first P frame
Small difference is both greater than mobile detection threshold value 100, and consecutive variations P number of frames is greater than the second preset value 4, then combine table 1 it is found that
Calculate speed, the motion profile of moving object.
For above-mentioned five transition frames P, the motion vector for parsing automobile is extracted respectively, and further determine that the fortune of automobile
Dynamic position；
According to the position of automobile, picture size, automobile size in five transition frames of acquisition, each transition frames are obtained
The displacement of middle moving object；
According to the displacement of acquisition and code rate, the speed of automobile is obtained.
Fig. 2 show the moving sensing system structure chart of the embodiment of the present invention 2, including obtains module, strategic control module；
The acquisition module is connected with the strategic control module；
The acquisition module, for during multimedia-data procession, obtaining the continuous transition frame between key frame simultaneously
The transition frames are sent to the strategic control module；
The strategic control module, for being respectively compared First Transition frame and other continuous transition frames in continuous transition frame
Size extracts parsing motion vector if being all larger than preset mobile detection threshold value, according to Dynamic Control Strategy, obtains movement
The dynamic result of object.
Parsing movement is extracted present invention discloses according to the size variation between continuous transition frame compared to prior art
Vector, to describe the motion conditions of moving object.
In addition, passing through following scheme: obtaining the big of First Transition frame and other continuous transition frames in continuous transition frame respectively
Small absolute value of the difference counts the quantity of the continuous transition frame and according to even if being all larger than preset mobile detection threshold value
Continuous transition number of frames and the calculating dynamic parameter table of comparisons, obtain the dynamic result of moving object, so that calculating the feelings of moving object
Condition is more accurate.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of mobile detection method, which comprises the following steps:
During multimedia-data procession, the continuous transition frame between key frame is obtained；
It is respectively compared the size of First Transition frame and other continuous transition frames in continuous transition frame, is detectd if being all larger than preset movement
Threshold value is surveyed, then extracts parsing motion vector, according to Dynamic Control Strategy, obtains the dynamic result of moving object；
First Transition frame refer to before occur transition frames average value, the transition frames occurred below again with the average value of front ratio
Compared with；
It is respectively compared the size of First Transition frame and other continuous transition frames in continuous transition frame, is detectd if being all larger than preset movement
Threshold value is surveyed, then extracts parsing motion vector, according to Dynamic Control Strategy, obtains the process of the dynamic result of moving object are as follows:
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if being all larger than
Preset mobile detection threshold value then counts the quantity of the continuous transition frame and is joined according to continuous transition number of frames and calculating dynamic
The number table of comparisons, obtains the dynamic result of moving object.
2. according to the method described in claim 1, it is characterized by: if the quantity of the continuous transition frame of statistics is greater than first
Preset value then calculates the motion profile of moving object；If more than the second preset value, then movement velocity, the fortune of moving object are calculated
Dynamic rail mark；If more than third preset value, then shape of movement, movement velocity, the motion profile of moving object are calculated.
3. according to the method described in claim 2, it is characterized by: if the quantity of the continuous transition frame of statistics is greater than first
Preset value then calculates the process of the motion profile of moving object are as follows:
Moving object is extracted respectively for each transition frames according to the continuous transition frame between the key frame of acquisition
Motion vector, and further determine that the movement position of the moving object, to obtain the motion profile of moving object.
4. according to the method described in claim 2, it is characterized by: then calculating the fortune of moving object if more than the second preset value
The process of dynamic speed are as follows:
Moving object is extracted respectively for each transition frames according to the continuous transition frame between the key frame of acquisition
Motion vector, and further determine that the movement position of the moving object；
According to the position of moving object, picture size, moving object size in each transition frames of acquisition, obtain every
The displacement of moving object in a transition frames；
According to the displacement of acquisition and code rate, the speed of the moving object is obtained.
5. according to the method described in claim 2, it is characterized by: then calculating the fortune of moving object if more than third preset value
The process of dynamic shape are as follows:
According to the profile that moving object in each transition frames of acquisition changes, moving object shape is obtained.
6. according to the method described in claim 1, it is characterized by: the dynamic result of moving object includes: the fortune of moving object
Dynamic rail mark, the speed of moving object, the shape of moving object.
7. according to the method described in claim 1, it is characterized by: the transition frames refer to P frame；The key frame refers to I frame.
8. a kind of moving sensing system, which is characterized in that including obtaining module, strategic control module；The acquisition module and institute
Strategic control module is stated to be connected；
The acquisition module obtains the continuous transition frame between key frame and by institute for during multimedia-data procession
It states transition frames and is sent to the strategic control module；
The strategic control module, for being respectively compared the big of First Transition frame and other continuous transition frames in continuous transition frame
It is small, if being all larger than preset mobile detection threshold value, parsing motion vector is extracted, according to Dynamic Control Strategy, obtains moving object
The dynamic result of body；
First Transition frame refer to before occur transition frames average value, the transition frames occurred below again with the average value of front ratio
Compared with；
It is respectively compared the size of First Transition frame and other continuous transition frames in continuous transition frame, is detectd if being all larger than preset movement
Threshold value is surveyed, then extracts parsing motion vector, according to Dynamic Control Strategy, obtains the process of the dynamic result of moving object are as follows:
The absolute value of the difference for obtaining the size of First Transition frame and other continuous transition frames in continuous transition frame respectively, if being all larger than
Preset mobile detection threshold value then counts the quantity of the continuous transition frame and is joined according to continuous transition number of frames and calculating dynamic
The number table of comparisons, obtains the dynamic result of moving object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740363.9A CN104410771B (en) | 2014-12-06 | 2014-12-06 | A kind of mobile detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740363.9A CN104410771B (en) | 2014-12-06 | 2014-12-06 | A kind of mobile detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104410771A CN104410771A (en) | 2015-03-11 |
| CN104410771B true CN104410771B (en) | 2019-08-30 |
Family
ID=52648363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410740363.9A Active CN104410771B (en) | 2014-12-06 | 2014-12-06 | A kind of mobile detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104410771B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101090498A (en) * | 2007-07-19 | 2007-12-19 | 华为技术有限公司 | Device and method for motion detection of image |
| CN101119480A (en) * | 2007-09-13 | 2008-02-06 | 中兴通讯股份有限公司 | Method for detecting video shelter in network video monitoring |
| US20080316174A1 (en) * | 2007-05-31 | 2008-12-25 | Stmicroelectronics Sa | Motion estimation with adaptation of the correlation block size |
| CN102395030A (en) * | 2011-11-18 | 2012-03-28 | 杭州海康威视数字技术股份有限公司 | Motion analysis method based on video compression code stream, code stream conversion method and apparatus thereof |
-
2014
- 2014-12-06 CN CN201410740363.9A patent/CN104410771B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080316174A1 (en) * | 2007-05-31 | 2008-12-25 | Stmicroelectronics Sa | Motion estimation with adaptation of the correlation block size |
| CN101090498A (en) * | 2007-07-19 | 2007-12-19 | 华为技术有限公司 | Device and method for motion detection of image |
| CN101119480A (en) * | 2007-09-13 | 2008-02-06 | 中兴通讯股份有限公司 | Method for detecting video shelter in network video monitoring |
| CN102395030A (en) * | 2011-11-18 | 2012-03-28 | 杭州海康威视数字技术股份有限公司 | Motion analysis method based on video compression code stream, code stream conversion method and apparatus thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104410771A (en) | 2015-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102202164B (en) | Motion-estimation-based road video stabilization method | |
| CN102722982B (en) | Based on wagon flow and the motion state detection method thereof of background and inter-frame difference algorithm | |
| Arróspide et al. | Homography-based ground plane detection using a single on-board camera | |
| CN105261037A (en) | Moving object detection method capable of automatically adapting to complex scenes | |
| CN104575003B (en) | A kind of vehicle speed detection method based on traffic surveillance videos | |
| WO2014077928A3 (en) | Video and lidar target detection and tracking system | |
| WO2008070319A3 (en) | Electronic traffic monitor | |
| CN106530328B (en) | A method of it is followed based on video image to moving object detection and smoothly | |
| JP2015115955A (en) | Video synopsis method and apparatus | |
| CN103729857B (en) | Moving target detecting method under mobile camera based on second compensation | |
| CN108022249A (en) | A kind of remote sensing video satellite moving vehicle target region of interest extraction method | |
| CN106559605A (en) | Digital video digital image stabilization method based on improved block matching algorithm | |
| CN104899894A (en) | Method for tracking moving object by using multiple cameras | |
| CN106887010A (en) | Ground moving target detection method based on high-rise scene information | |
| CN104123733B (en) | A kind of method of motion detection and reduction error rate based on Block- matching | |
| CN106558224A (en) | A kind of traffic intelligent monitoring and managing method based on computer vision | |
| CN107527370A (en) | A kind of method for tracking target based on camshift | |
| WO2018164575A8 (en) | Method of detecting moving objects from a temporal sequence of images | |
| CN103093480A (en) | Particle filtering video image tracking method based on dual model | |
| CN104410771B (en) | A kind of mobile detection method and system | |
| US20150125037A1 (en) | Heuristic motion detection methods and systems for interactive applications | |
| CN106056630B (en) | Occlusion area detection method based on image sequence light stream and triangle gridding | |
| EP3447722A1 (en) | Two-dimensional image depth-of-field generating method and device | |
| EP3232403A3 (en) | Fast multi-spectral image registration by modeling platform motion | |
| CN106485697A (en) | A kind of roadbed subsidence based on binocular vision and foreign matter detecting method |
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: 200233 Shanghai city Xuhui District Tianzhou Road No. 99 building 13 room 401A Applicant after: QUECTEL WIRELESS SOLUTIONS CO., LTD. Address before: 200233 Shanghai city Xuhui District Tianzhou Road No. 99 building 13 room 401A Applicant before: Shanghai Quectel Communication Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder |
Address after: 200233 room 193, 2f, No. 25-1, Hongcao Road, Xuhui District, Shanghai Patentee after: QUECTEL WIRELESS SOLUTIONS Co.,Ltd. Address before: 200233 Shanghai city Xuhui District Tianzhou Road No. 99 building 13 room 401A Patentee before: QUECTEL WIRELESS SOLUTIONS Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |