CN106407887B - Method and device for acquiring search step length of candidate frame - Google Patents
Method and device for acquiring search step length of candidate frame Download PDFInfo
- Publication number
- CN106407887B CN106407887B CN201610716184.0A CN201610716184A CN106407887B CN 106407887 B CN106407887 B CN 106407887B CN 201610716184 A CN201610716184 A CN 201610716184A CN 106407887 B CN106407887 B CN 106407887B
- Authority
- CN
- China
- Prior art keywords
- partition
- original
- search
- step length
- determining
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for acquiring the search step length of a candidate frame, which relates to the field of target detection in computer vision and pattern recognition, and can determine the search step length of a target candidate frame in a video to be detected by establishing a Poisson distribution model. The method comprises the steps of obtaining an image to be searched; acquiring image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition; determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition; and determining the candidate frame searching step length in each original partition according to the partition type. The technical scheme provided by the embodiment of the invention can be suitable for target detection processes such as pedestrian detection, vehicle detection and the like in scenes such as static monitoring videos, vehicle monitoring videos and the like.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the field of target detection in computer vision and pattern recognition, in particular to a method and a device for acquiring a candidate frame search step length.
[ background of the invention ]
With the rapid development and wide application of computer image processing technology, the demand for object detection technology is also gradually rising. Object detection has become a fundamental problem in the field of computer vision and pattern recognition, and determination of candidate box search steps for detecting objects is an important preliminary task in object recognition classification. The current method for generating a candidate target frame is generally a sliding window search method, and when the target search is performed in the sliding window search method, the candidate frame is stepped by a fixed length in the whole scanning window.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
according to the existing target searching method, in the process of searching a target, a candidate frame is stepped by a fixed length in the whole scanning window, missing detection may occur in the step searching by the fixed length in the areas with different numbers of searched targets, and the searching result is not globally optimal.
[ summary of the invention ]
In view of this, embodiments of the present invention provide a method and an apparatus for obtaining a candidate frame search step, which can determine the candidate frame search step according to frequency and density information of a search target appearing in a region.
In one aspect, an embodiment of the present invention provides a method for obtaining a candidate frame search step size, where the method includes:
acquiring an image to be searched;
acquiring image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition;
determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition;
and determining the candidate frame searching step length in each original partition according to the partition type.
On the other hand, an embodiment of the present invention provides an apparatus for obtaining a candidate frame search step size, where the apparatus includes:
the device comprises a first acquisition unit, a second acquisition unit and a search unit, wherein the first acquisition unit is used for acquiring an image to be searched;
the second acquisition unit is used for acquiring the image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition;
the first determining unit is used for determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition;
and the second determining unit is used for determining the candidate frame searching step length in each original partition according to the partition type.
According to the method and the device for acquiring the candidate frame search step length, the Poisson model is established in a partitioning mode, the position information of the specific search target obtained through continuous learning and updating is obtained, the candidate frame search step length of each area in each frame of image can be adjusted, the number of target candidate frames is restricted, and therefore the search target is detected aiming at different areas. The method and the device improve the detection effect and can obtain higher detection rate.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a flowchart of a method for obtaining a candidate box search step according to an embodiment of the present invention;
fig. 2 is a flowchart of another method for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 3 is a flowchart of another method for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 4 is a flowchart of another method for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 5 is a block diagram of an apparatus for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 6 is a block diagram of another apparatus for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 7 is a block diagram of another apparatus for obtaining a candidate frame search step according to an embodiment of the present invention;
fig. 8 is a block diagram of another apparatus for obtaining a candidate frame search step according to an embodiment of the present invention.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The word "if," as used herein, may be interpreted as "when or" in response to determining "or" in response to detecting, "depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
The embodiment of the invention provides a method for acquiring a candidate frame search step length, which can be applied to the process of detecting targets such as pedestrian detection, vehicle detection and the like in scenes such as static surveillance video, vehicle surveillance video and the like, and as shown in fig. 1, the method comprises the following steps:
101. and acquiring an image to be searched.
The images to be searched refer to all images to be detected in the target detection process.
102. And acquiring image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition.
It should be noted that, in the embodiment of the present invention, for scene monitoring such as a static monitoring video and a vehicle-mounted monitoring video, the frequency and the distribution density of a search target appearing in a certain area in an image obey poisson distribution.
Wherein, the original partitions refer to the areas obtained by partitioning the detection area.
The image information of each original partition comprises frequency information of appearance of a search target in each block area and density information of distribution of the search targets.
The search target refers to an object to be detected in a target detection process, such as a person, a vehicle, an object and the like.
The Poisson distribution function is based on a function established by a mathematical Poisson model and is suitable for describing the occurrence frequency of random events in unit time.
103. And determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition.
And the partition type is determined by the number of the search targets in the original partition.
The number of the search targets refers to the number of the distribution of the search targets in unit time, and is related to the frequency information of the occurrence of the search targets and the density information of the distribution.
104. And determining the candidate frame searching step length in each original partition according to the partition type.
According to the method for acquiring the candidate frame search step length, the Poisson model is established in a partitioning mode, the position information of the specific target is obtained through continuous learning and updating, the candidate frame search step length of each area in each frame of image can be adjusted, the number of target candidate frames is restricted, and therefore the target is detected according to different areas. The method improves the detection effect and can obtain higher detection rate.
Further, in combination with the foregoing method flows, in another possible implementation manner of the embodiment of the present invention, for the step 103, an implementation of determining the partition type of each original partition according to the image information and the poisson distribution function of each original partition provides the following specific flows, as shown in fig. 2, including:
201. and determining the number of the search targets in each original partition according to the image information and the Poisson distribution function of each original partition.
In the embodiment of the present invention, the frequency of the occurrence of the random event in the time domain refers to the frequency of the occurrence of the search target in each original partition, and the distribution density of the random event in the space domain refers to the density of the distribution of the search target.
The Poisson distribution function is trained in the process of detecting the search target, and frequency information of the search target appearing in each block area and distribution density information of the search target are dynamically acquired in the learning process.
When the search target is detected, each frame of image to be searched is detected, the Poisson distribution function is changed into discrete distribution, the time is determined, and the number of the search targets is the density of the distribution of the search targets in unit time.
202. And when the number of the search targets is within a first threshold range, determining the partition type of the original partition with the number of the search targets within the first threshold range as a target sparse distribution area.
The first threshold range refers to a number range in which the number of search targets is smaller, and is recorded as [ L min ].
Wherein L is an integer greater than 0.
Wherein L min is an integer greater than L.
203. And when the number of the search targets is within a second threshold range, determining the partition type of the original partition with the number of the search targets within the second threshold range as a target middle distribution area.
The second threshold range refers to a number range in which the number of the search targets is larger than the first threshold range, and is recorded as [ L min, L max ].
Wherein, the L max is an integer greater than L min.
204. And when the number of the search targets is within a third threshold range, determining the partition type of the original partition with the number of the search targets within the third threshold range as a target dense distribution area.
The third threshold range refers to a number range in which the number of the search targets is greater than the second threshold range, and is marked as [ L max, + -%).
When the number of the search targets of the original partition is more than L min, the original partition is regarded as an area with more targets.
When the number of the search targets of the original partition is less than L, the original partition is regarded as an area with fewer targets.
And determining the partition type of the areas with more search targets, and determining the search step length of the candidate frame of the areas with less search targets according to the number of the search targets.
Further, in combination with the foregoing method flows, in another possible implementation manner of the embodiment of the present invention, a specific step of how to determine the candidate box search step size in each original partition according to the partition type is provided, and the following specific flow is provided for implementation of step 104, as shown in fig. 3, and includes:
301. and setting the candidate frame searching step length in the original partition with the partition type as the target sparse distribution area as a first step length.
The first step length can be defined according to the distribution condition of the search target in the target sparse distribution area.
302. And setting the candidate frame searching step length in the original partition with the partition type as the target middle distribution area as a second step length.
And the second step length can define the length according to the distribution condition of the search target in the target middle distribution area.
Wherein the second step size is smaller than the first step size.
303. And setting the candidate frame searching step size in the original partition with the partition type being the target dense distribution area as a third step size.
And the third step length can be defined according to the distribution condition of the search target in the target dense distribution area.
Wherein the third step size is smaller than the second step size.
It should be noted that, when the original partition belongs to an area with few search targets, the step length is directly determined according to the number of the search targets, and the step length is not less than the first step length.
Further, with reference to the foregoing method flow, another possible implementation manner is provided in the embodiment of the present invention, as shown in fig. 4, before the acquiring an image to be searched, the method further includes:
401. an original region within an original image is acquired.
Wherein the original image refers to n frames of images in the detection area.
Wherein n is an integer greater than 0.
And partitioning the original partition according to the size and the characteristics of the detection area.
When the number of the original partitions is larger, the function can accurately reflect the frequency and distribution density information of the target in the partitions, and the statistical distribution in each original partition can be considered to be basically consistent.
The more the number of the original partitions is, the more data needs to be calculated, and the number of the original partitions is determined according to the size and the characteristics of the search area in consideration of both the complexity and the accuracy of the calculation method.
402. And collecting the occurrence frequency and the distribution density of the search target in the original partition.
And acquiring the appearance frequency and the distribution density of the search targets in the original subareas refers to acquiring the appearance frequency and the distribution density of the search targets in each original subarea of the n frames of images.
403. And determining the Poisson distribution function of the original subarea according to the occurrence frequency and the density of the search target.
And the Poisson distribution function carries out parameter estimation by collecting the occurrence frequency and density information of the search target in the n frames of images to obtain an initial value.
According to the method for acquiring the candidate frame search step length, the Poisson model is established in a partitioning mode, the position information of the specific search target obtained through continuous learning and updating is obtained, the candidate frame search step length of each area in each frame of image can be adjusted, the number of target candidate frames is restricted, and therefore the search target is detected according to different areas. The method improves the detection effect and can obtain higher detection rate.
In order to better understand the technical solution, the embodiments of the present invention provide more specific implementations, and the embodiments of the present invention are applicable to, but not limited to, the following implementations.
Step 1, dividing a detection area into 12(3x4) small areas, establishing a poisson position of a pedestrian for each area of the previous 2400 frame image, performing parameter estimation to obtain a model initial value, and thus obtaining an average occurrence rate initial value of the pedestrian in the poisson model at each area within unit time.
And 2, training a Poisson model, and dynamically acquiring frequency information of pedestrians appearing in each area and density information of pedestrian distribution in the learning process.
And step 21, learning and updating by using a gradient descent method according to the initial value of the established Poisson model to obtain the density information of each original subarea distribution of the pedestrian in each frame of image.
Step 22, regarding to the pedestrian distribution condition of each position area obtained in step 21, regarding to the scene in the embodiment, more block areas appear for pedestrians:
when the number of the pedestrians is within 10, regarding the area as a pedestrian sparse distribution area;
when the number of the pedestrians is 10-30, the region is regarded as a pedestrian middle distribution region;
when the number of occurrences of pedestrians is greater than 30, the region is regarded as a pedestrian dense distribution region.
And 23, setting the number threshold of the pedestrians to be 8 for the blocking area with less pedestrians.
And 3, setting different search step lengths of candidate frames in the areas of different distribution density sets of a search target according to the density information of the pedestrian in each frame of image distribution obtained by the Poisson position model learning, and controlling the number of the candidate frames of the whole frame of image.
Step 31, setting the step length for the area with more distributed search targets as follows: the pedestrian sparse distribution area step is 16, the pedestrian medium distribution area step is 8, and the pedestrian dense distribution area step is 4.
Step 32, setting step length for the area with less distribution of the search target as follows: in the case where the number of pedestrian occurrences is greater than 8, step is 16, whereas step is 32.
In the embodiment of the present invention, the aspect ratio of the frame candidates set in each region is locked to 0.5, and in addition, in the case where no pedestrian is present in each region, no frame candidate is generated.
According to the method for acquiring the candidate frame search step length, the Poisson model is established in a partitioning mode, the position information of the specific search target obtained through continuous learning and updating is obtained, the candidate frame search step length of each area in each frame of image can be adjusted, the number of target candidate frames is restricted, and therefore the search target is detected according to different areas. The method improves the detection effect and can obtain higher detection rate.
The embodiment of the present invention provides an apparatus for obtaining a candidate frame search step length, which can be used to implement the foregoing methods, and the composition of the apparatus is shown in fig. 5, where the apparatus includes:
a first acquiring unit 51 for acquiring an image to be searched.
The second obtaining unit 52 is configured to obtain image information of each original partition in the image to be searched and a poisson distribution function corresponding to each original partition.
A first determining unit 53, configured to determine a partition type of each original partition according to the image information and the poisson distribution function of each original partition.
A second determining unit 54, configured to determine a candidate frame search step size in each original partition according to the partition type.
Optionally, as shown in fig. 6, the first determining unit 53 includes:
the first determining module 531 is configured to determine the number of search targets in each original partition according to the image information and the poisson distribution function of each original partition.
A second determining module 532, configured to determine, when the number of the search targets is within the first threshold range, the partition type of the original partition whose number of the search targets is within the first threshold range as the target sparse distribution area.
A third determining module 533, configured to determine, when the number of the search targets is within the second threshold range, the partition type of the original partition whose number of the search targets is within the second threshold range as the target middle distribution area.
And the fourth determining module 534 is configured to determine, when the number of the search targets is within the third threshold range, the partition type of the original partition whose number of the search targets is within the third threshold range as the target dense distribution area.
Optionally, as shown in fig. 7, the second determining unit 54 includes:
a first setting module 541, configured to set a candidate frame search step size in an original partition whose partition type is a target sparse distribution area as a first step size.
A second setting module 542, configured to set the step size of the candidate box search in the original partition whose partition type is the target middle distribution area as a second step size.
A third setting module 543, configured to set the candidate box search step length in the original partition whose partition type is the target dense distribution area as a third step length.
Optionally, as shown in fig. 8, the apparatus further includes:
a third obtaining unit 55, configured to obtain an original partition in the original image.
And the acquisition unit 56 is used for acquiring the occurrence frequency and the distribution density of the search targets in the original partition.
A third determining unit 57, configured to determine a poisson distribution function of the original partition according to the occurrence frequency and the density of the search target.
According to the device for acquiring the candidate frame search step length, the Poisson model is established in a partitioning mode, the position information of the specific search target obtained through continuous learning and updating is obtained, the candidate frame search step length of each area in each frame of image can be adjusted, the number of target candidate frames is restricted, and therefore the search target is detected according to different areas. The device improves the detection effect and can obtain higher detection rate.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (4)
1. A method for obtaining a candidate frame search step length is characterized by comprising the following steps:
acquiring an image to be searched;
acquiring image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition;
determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition;
determining a candidate frame search step length in each original partition according to the partition type;
determining the partition type of each original partition according to the image information and the poisson distribution function of each original partition comprises:
determining the number of search targets in each original partition according to the image information and the Poisson distribution function of each original partition;
when the number of the search targets is within a first threshold range, determining the partition type of the original partition with the number of the search targets within the first threshold range as a target sparse distribution area;
when the number of the search targets is within a second threshold range, determining the partition type of the original partition with the number of the search targets within the second threshold range as a target middle distribution area;
when the number of the search targets is within a third threshold range, determining the partition type of the original partition with the number of the search targets within the third threshold range as a target dense distribution area;
the determining a candidate frame search step size in each original partition according to the partition type includes:
setting the candidate frame searching step length in the original partition with the partition type as the target sparse distribution area as a first step length;
setting the candidate frame search step length in the original partition with the partition type as the target middle distribution area as a second step length;
setting the candidate frame searching step length in the original partition with the partition type being the target dense distribution area as a third step length;
the first threshold range is smaller than the second threshold range, the second threshold range is smaller than the third threshold range, the third step length is smaller than the second step length, and the second step length is smaller than the first step length.
2. The method according to claim 1, wherein before the acquiring the image to be searched, further comprising:
acquiring an original partition in an original image;
collecting the occurrence frequency and the distribution density of the search target in the original partition;
and determining the Poisson distribution function of the original subarea according to the occurrence frequency and the density of the search target.
3. An apparatus for obtaining a frame candidate search step size, the apparatus comprising:
the device comprises a first acquisition unit, a second acquisition unit and a search unit, wherein the first acquisition unit is used for acquiring an image to be searched;
the second acquisition unit is used for acquiring the image information of each original partition in the image to be searched and a Poisson distribution function corresponding to each original partition;
the first determining unit is used for determining the partition type of each original partition according to the image information and the Poisson distribution function of each original partition;
a second determining unit, configured to determine, according to the partition type, a candidate frame search step size in each original partition;
the first determination unit includes:
the first determining module is used for determining the number of the search targets in each original partition according to the image information and the Poisson distribution function of each original partition;
the second determining module is used for determining the partition type of the original partition with the number of the search targets in the first threshold range as a target sparse distribution area when the number of the search targets is in the first threshold range;
a third determining module, configured to determine, when the number of the search targets is within a second threshold range, a partition type of an original partition whose number of the search targets is within the second threshold range as a target middle distribution area;
a fourth determining module, configured to determine, when the number of the search targets is within a third threshold range, a partition type of an original partition whose number of the search targets is within the third threshold range as a target dense distribution area; the second determination unit includes:
the first setting module is used for setting the candidate frame searching step length in the original partition with the partition type as the target sparse distribution area as a first step length;
the second setting module is used for setting the candidate frame searching step length in the original partition with the partition type being the target middle distribution area as a second step length;
a third setting module, configured to set a candidate frame search step size in an original partition whose partition type is a target dense distribution area to a third step size;
the first threshold range is smaller than the second threshold range, the second threshold range is smaller than the third threshold range, the third step length is smaller than the second step length, and the second step length is smaller than the first step length.
4. The apparatus of claim 3, further comprising:
a third obtaining unit, configured to obtain an original partition in an original image;
the acquisition unit is used for acquiring the occurrence frequency and the distribution density of the search target in the original partition;
and the third determining unit is used for determining the Poisson distribution function of the original subarea according to the occurrence frequency and the density of the search target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610716184.0A CN106407887B (en) | 2016-08-24 | 2016-08-24 | Method and device for acquiring search step length of candidate frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610716184.0A CN106407887B (en) | 2016-08-24 | 2016-08-24 | Method and device for acquiring search step length of candidate frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106407887A CN106407887A (en) | 2017-02-15 |
| CN106407887B true CN106407887B (en) | 2020-07-31 |
Family
ID=58004405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610716184.0A Active CN106407887B (en) | 2016-08-24 | 2016-08-24 | Method and device for acquiring search step length of candidate frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407887B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144784A (en) * | 2007-09-04 | 2008-03-19 | 杭州电子科技大学 | Automatic tracking method for video frequency microscopic image cell |
| CN103150566A (en) * | 2011-12-06 | 2013-06-12 | 中国科学院电子学研究所 | Automatic detecting method of remote sensing ground object target based on random geometric model |
| CN104715451A (en) * | 2015-03-11 | 2015-06-17 | 西安交通大学 | Seamless image fusion method based on consistent optimization of color and transparency |
| CN104778358A (en) * | 2015-04-09 | 2015-07-15 | 西安工程大学 | Method for tracking extended target by multiple sensors with partially overlapped monitoring areas |
| CN105205450A (en) * | 2015-08-24 | 2015-12-30 | 辽宁工程技术大学 | SAR image target extraction method based on irregular marked point process |
-
2016
- 2016-08-24 CN CN201610716184.0A patent/CN106407887B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144784A (en) * | 2007-09-04 | 2008-03-19 | 杭州电子科技大学 | Automatic tracking method for video frequency microscopic image cell |
| CN103150566A (en) * | 2011-12-06 | 2013-06-12 | 中国科学院电子学研究所 | Automatic detecting method of remote sensing ground object target based on random geometric model |
| CN104715451A (en) * | 2015-03-11 | 2015-06-17 | 西安交通大学 | Seamless image fusion method based on consistent optimization of color and transparency |
| CN104778358A (en) * | 2015-04-09 | 2015-07-15 | 西安工程大学 | Method for tracking extended target by multiple sensors with partially overlapped monitoring areas |
| CN105205450A (en) * | 2015-08-24 | 2015-12-30 | 辽宁工程技术大学 | SAR image target extraction method based on irregular marked point process |
Non-Patent Citations (4)
| Title |
|---|
| "Poisson models for extended target and group tracking";Kevin Gilholm等;《Signal & Data Processing of Small Targets》;20050915;第59130R-59130R-12页 * |
| "Spatial distribution model for tracking extended objects";K.Gilhol等;《IEEE Proceedings-Radar,Sonar and Navigation》;20050725;第152卷(第5期);第364-371页 * |
| "天基红外传感器对中段目标群跟踪技术研究";张慧;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20151115(第11期);第46页 * |
| "采用在线高斯模型的行人检测候选框快速生成方法";覃剑等;《光学学报》;20160802;第36卷(第11期);正文第2-3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106407887A (en) | 2017-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242088B (en) | Target detection method and device, electronic equipment and storage medium | |
| Kim et al. | Spatiotemporal saliency detection for video sequences based on random walk with restart | |
| US10402627B2 (en) | Method and apparatus for determining identity identifier of face in face image, and terminal | |
| KR102275452B1 (en) | Method for tracking image in real time considering both color and shape at the same time and apparatus therefor | |
| Wang et al. | Consistent video saliency using local gradient flow optimization and global refinement | |
| CN105005992B (en) | A kind of based on the background modeling of depth map and the method for foreground extraction | |
| Haines et al. | Background subtraction with dirichlet processes | |
| Badenas et al. | Motion-based segmentation and region tracking in image sequences | |
| US9189867B2 (en) | Adaptive image processing apparatus and method based in image pyramid | |
| US20150310297A1 (en) | Systems and methods for computer vision background estimation using foreground-aware statistical models | |
| Cuevas et al. | Improved background modeling for real-time spatio-temporal non-parametric moving object detection strategies | |
| CN106295598A (en) | A kind of across photographic head method for tracking target and device | |
| Subudhi et al. | Statistical feature bag based background subtraction for local change detection | |
| KR102119897B1 (en) | Skin condition detection method and electronic device | |
| US10657625B2 (en) | Image processing device, an image processing method, and computer-readable recording medium | |
| KR20110074107A (en) | Method for detecting object using camera | |
| CN111723773A (en) | Remnant detection method, device, electronic equipment and readable storage medium | |
| CN113424516A (en) | Method of processing a series of events received asynchronously from a pixel array of an event-based photosensor | |
| JP2016058085A (en) | Method and device for detecting shielding of object | |
| CN113888586A (en) | Target tracking method and device based on correlation filtering | |
| CN102314591A (en) | Method and equipment for detecting static foreground object | |
| Yang et al. | Scene adaptive online surveillance video synopsis via dynamic tube rearrangement using octree | |
| JP2014110020A (en) | Image processor, image processing method and image processing program | |
| KR102211541B1 (en) | Apparatus and method for validating image data for learning | |
| CN106407887B (en) | Method and device for acquiring search step length of candidate frame |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200325 Address after: 400044 Shapingba District Sha Street, No. 174, Chongqing Applicant after: Chongqing University Address before: 400044 Shapingba District Sha Street, No. 174, Chongqing Applicant before: Chongqing University Applicant before: SHENZHEN TINNO WIRELESS TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |