CN113850845B - Moving track tracking method and system for moving target object - Google Patents
Moving track tracking method and system for moving target object Download PDFInfo
- Publication number
- CN113850845B CN113850845B CN202111446792.1A CN202111446792A CN113850845B CN 113850845 B CN113850845 B CN 113850845B CN 202111446792 A CN202111446792 A CN 202111446792A CN 113850845 B CN113850845 B CN 113850845B
- Authority
- CN
- China
- Prior art keywords
- target object
- moving target
- grid
- moving
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method and a system for tracking a moving track of a moving target object, wherein the method comprises the following steps: respectively inquiring the video sources to obtain video sample data of different video sources in a target area; constructing a GeoSOT model of a target area; respectively discretizing each video sample data into a three-dimensional grid of a GeoSOT model; traversing each three-dimensional grid of the GeoSOT model, and determining the three-dimensional grid where the moving target object is located as a target grid; respectively extracting dynamic characteristic information of a moving target object in each target grid, and constructing a track point set of the moving target object; and connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area. The method is based on the GeoSOT model, and realizes the rapid and accurate identification of the moving target by carrying out discretization processing on the video sample data.
Description
Technical Field
The invention relates to the field of visual tracking, in particular to a method and a system for tracking a moving track of a moving target object.
Background
In recent decades, with the advance of smart cities and other projects, major streets and minor roadways of various cities are full of cameras (electronic eyes). The continuous updating of the storage technology and the audio-video technology also accumulates massive video information for industries such as security protection, traffic and the like, which brings great convenience for people finding, object finding, solution solving and the like. At this time, how to quickly extract valuable information in a mass of multi-source videos is very important, and with the increasing intelligent demand, the video scheduling retrieval technology is also quickly developed. For video information, there are mainly two problems: firstly, the intelligent analysis capability of the machine is limited, the main analysis means is mainly manual identification, the workload is huge, and the identification is inaccurate; secondly, massive and multi-source video data cannot be subjected to effective information processing and storage analysis, and no analysis and duplication means is provided for historical activity conditions of various moving targets, because research and judgment on action intentions of the moving targets are limited.
How to realize the rapid and accurate identification of the moving target object becomes a technical problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a method and a system for tracking a moving track of a moving target object so as to realize quick and accurate identification of the moving target object.
In order to achieve the purpose, the invention provides the following scheme:
the invention provides a method for tracking a moving track of a moving target object, which comprises the following steps:
respectively inquiring the video sources to obtain video sample data of different video sources in a target area;
constructing a GeoSOT model of a target area;
respectively discretizing each video sample data into a three-dimensional grid of the GeoSOT model;
traversing each three-dimensional grid of the GeoSOT model, and determining the three-dimensional grid where the moving target object is located as a target grid;
respectively extracting dynamic characteristic information of the moving target object in each target grid, and constructing a track point set of the moving target object; the dynamic characteristic information comprises a spatial position, a motion direction and time;
and connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
Optionally, the traversing each three-dimensional mesh of the GeoSOT model, determining the three-dimensional mesh where the moving target object is located, as a target mesh, and before, further includes:
determining a moving target object in a rectangular query mode;
extracting static characteristic information of the moving target object, wherein the static characteristic information comprises: walking angle, facial features, clothing features.
Optionally, the determining the moving target object by the rectangular query specifically includes:
for any video source, the moving target object in the image of each frame in the process from appearance to disappearance of the moving target object is determined in a rectangular query mode.
Optionally, the traversing each three-dimensional mesh of the GeoSOT model, determining the three-dimensional mesh where the moving target object is located, as a target mesh, specifically includes:
extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in a stereoscopic grid;
respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object;
and when the video sample data in the three-dimensional grid has the image sample consistent with the static characteristic information of the moving target object, determining the three-dimensional grid as the three-dimensional grid where the moving target object is located.
Optionally, the respectively extracting dynamic feature information of the moving target object in each target grid specifically includes:
determining distance information between a moving target object and an electronic eye for acquiring video sample data in a target grid according to the shooting size of the moving target object in an image sample in the target grid, the actual size of the moving target object and correction parameters of the electronic eye for acquiring the video sample data in the target grid;
determining the space position of the moving target object in the target grid according to the distance information and the position of an electronic eye of video sample data in the target grid;
determining the motion direction of the moving target object in the target grid according to the difference value of the distance information between the moving target object in two adjacent image samples in the video sample data in the target grid and the electronic eye for acquiring the video sample data in the target grid;
and determining the time range of motion in the target grid according to the time of the moving target object appearing in the video sample data in the target grid.
A system for active trajectory tracking of a moving target object, the system comprising:
the video sample data acquisition module is used for respectively inquiring the video sources and acquiring video sample data of different video sources in the target area;
the GeoSOT model building module is used for building a GeoSOT model of the target area;
the video sample data discretization module is used for discretizing each video sample data into a three-dimensional grid of the GeoSOT model;
the target grid determining module is used for traversing each three-dimensional grid of the GeoSOT model, determining the three-dimensional grid where the moving target object is located, and using the three-dimensional grid as a target grid;
the dynamic characteristic information extraction module is used for respectively extracting the dynamic characteristic information of the moving target object in each target grid and constructing a track point set of the moving target object; the dynamic characteristic information comprises a spatial position, a motion direction and time;
and the track generation module is used for connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
Optionally, the system further includes:
the moving target object query module is used for determining a moving target object in a rectangular query mode;
the static characteristic information extraction module is used for extracting static characteristic information of the moving target object, and the static characteristic information comprises: walking angle, facial features, clothing features.
Optionally, the moving target object querying module specifically includes:
and the moving target object query submodule is used for determining the moving target object in each frame of image in the process from appearance to disappearance of the moving target object in a rectangular query mode for any video source.
Optionally, the target grid determining module specifically includes:
the static characteristic information extraction submodule is used for extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in the three-dimensional grid;
the consistency comparison submodule is used for respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object;
and the stereoscopic grid determining submodule is used for determining the stereoscopic grid as the stereoscopic grid where the moving target object is located when the image sample consistent with the static characteristic information of the moving target object exists in the video sample data in the stereoscopic grid.
Optionally, the dynamic feature information extracting module specifically includes:
the distance information determining submodule is used for determining the distance information between the moving target object and the electronic eye for acquiring the video sample data in the target grid according to the shooting size of the moving target object in the image sample in the target grid, the actual size of the moving target object and the correction parameters of the electronic eye for acquiring the video sample data in the target grid;
the spatial position determining submodule is used for determining the spatial position of the moving target object in the target grid according to the distance information and the position of an electronic eye of video sample data in the target grid;
the motion direction determining submodule is used for determining the motion direction of the moving target object in the target grid according to the difference value of the distance information between the moving target object in two adjacent image samples in the video sample data in the target grid and the electronic eye for acquiring the video sample data in the target grid;
and the time determining submodule is used for determining the time range of motion in the target grid according to the time of the moving target object appearing in the video sample data in the target grid.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method and a system for tracking a moving track of a moving target object, wherein the method comprises the following steps: respectively inquiring the video sources to obtain video sample data of different video sources in a target area; constructing a GeoSOT model of a target area; respectively discretizing each video sample data into a three-dimensional grid of the GeoSOT model; traversing each three-dimensional grid of the GeoSOT model, and determining the three-dimensional grid where the moving target object is located as a target grid; respectively extracting dynamic characteristic information of the moving target object in each target grid, and constructing a track point set of the moving target object; and connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area. The method is based on the GeoSOT model, the video sample data is dispersed into the three-dimensional grid of the GeoSOT model, the video sample data is subjected to discretization processing, the moving target is quickly and accurately identified, meanwhile, effective support is provided for target action intention prediction through moving target motion track generation, and the processing and service capacity of the video data is comprehensively improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 without inventive exercise.
FIG. 1 is a flowchart of a method for tracking a moving trajectory of a moving target object according to the present invention;
FIG. 2 is a schematic diagram of a rectangular query provided by the present invention;
fig. 3 is a schematic structural diagram of a moving trajectory tracking device for a moving target object according to the present invention.
Detailed Description
The drawings in the embodiments of the present invention are collected below to clearly and completely describe the technical solutions in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present 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 invention aims to provide a method and a system for tracking a moving track of a moving target object so as to realize quick and accurate identification of the moving target object.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, the present invention is described in further detail with reference to the accompanying drawings and detailed description.
Example 1
As shown in fig. 1, the present invention provides a method for tracking a moving trajectory of a moving target object, the method comprising the following steps:
103, discretizing each video sample data into a three-dimensional grid of the GeoSOT model; in other words, for massive video data of different sources in different regions within a certain time, spatial discretization processing is performed on the data with reference to specified analysis accuracy, and the video data are discretized into different three-dimensional grids.
And step 104, traversing each three-dimensional grid of the GeoSOT model, and determining the three-dimensional grid where the moving target object is located as a target grid.
the moving target object is determined in a rectangular query mode, and specifically, the moving target object is determined through rectangular query (manually defining a space range at a fixed time point of video source information) according to a certain single-source video. Through a certain single-source video imported into the system, a moving target object sample is selected according to actual needs through rectangular query, for example, a license plate number in electronic eye video information on a certain road and pedestrians at a certain parking lot monitoring camera are collected, wherein the principle of the rectangular query is shown in fig. 2.
Extracting static characteristic information of the moving target object, wherein the static characteristic information comprises: walking angle, facial features, clothing features. The invention utilizes a computer to query a video source for a plurality of times through static characteristic information (such as walking angles of pedestrians and pedestrians, facial characteristics, clothes characteristics and the like) of a moving target object sample, and finds different samples of the moving target object. And simultaneously, detecting precision.
The determining of the moving target object in the rectangular query mode specifically includes: for any video source, the moving target object in the image of each frame in the process from appearance to disappearance of the moving target object is determined in a rectangular query mode. And forming a moving target object data set containing different dimensions of the moving target object.
The traversing each three-dimensional grid of the GeoSOT model, determining the three-dimensional grid where the moving target object is located as a target grid, and specifically comprising: extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in a stereoscopic grid; respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object; and when the video sample data in the three-dimensional grid has the image sample consistent with the static characteristic information of the moving target object, determining the three-dimensional grid as the three-dimensional grid where the moving target object is located. Namely, traversing all the stereo grids, and finding out the stereo grid unit containing the moving target object information by combining the video sample data set containing the moving target object.
105, respectively extracting dynamic characteristic information of the moving target object in each target grid, and constructing a track point set of the moving target object; the dynamic characteristic information comprises a spatial position, a motion direction and time; namely, a single stereo grid unit is input into a video data gridding management system, and by extracting a feature map (such as the walking angle of a pedestrian, the walking angle of the pedestrian, the facial feature, the clothes feature and the like), the feature information of a moving target object, including information of a spatial position, a direction, time and the like, is successfully extracted, so as to form a track point set of the moving target object in the stereo grid unit.
And 106, connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
Namely, all moving target track points in the three-dimensional grid are collected and sequenced according to the time sequence, and finally a moving track of the moving target in a target area within a certain time range is formed.
For example, the motion track of a pedestrian is searched, the characteristics of the pedestrian may include the walking angle, the facial characteristics, the clothes characteristics and the like of the pedestrian, a space and a time range are divided according to the actual required pedestrian characteristic information by combining with the created video sample data set containing the pedestrian information, so that a specific target object is positioned, and the motion track of the target object can be found after multiple traversals.
Example 2
The invention also provides a moving track tracking system of a moving target object, which comprises:
and the video sample data acquisition module is used for respectively inquiring the video sources and acquiring the video sample data of different video sources in the target area.
And the GeoSOT model building module is used for building a GeoSOT model of the target area.
And the video sample data discretization module is used for discretizing each video sample data into a three-dimensional grid of the GeoSOT model respectively.
And the target grid determining module is used for traversing each three-dimensional grid of the GeoSOT model, determining the three-dimensional grid where the moving target object is located, and using the three-dimensional grid as the target grid.
The target grid determining module specifically includes: the static characteristic information extraction submodule is used for extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in the three-dimensional grid; the consistency comparison submodule is used for respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object; and the stereoscopic grid determining submodule is used for determining the stereoscopic grid as the stereoscopic grid where the moving target object is located when the image sample consistent with the static characteristic information of the moving target object exists in the video sample data in the stereoscopic grid.
The dynamic characteristic information extraction module is used for respectively extracting the dynamic characteristic information of the moving target object in each target grid and constructing a track point set of the moving target object; the dynamic characteristic information comprises spatial position, motion direction and time.
The dynamic feature information extraction module specifically includes: the distance information determining submodule is used for determining the distance information between the moving target object and the electronic eye for acquiring the video sample data in the target grid according to the shooting size of the moving target object in the image sample in the target grid, the actual size of the moving target object and the correction parameters of the electronic eye for acquiring the video sample data in the target grid; the spatial position determining submodule is used for determining the spatial position of the moving target object in the target grid according to the distance information and the position of an electronic eye of video sample data in the target grid; the motion direction determining submodule is used for determining the motion direction of the moving target object in the target grid according to the difference value of the distance information between the moving target object in two adjacent image samples in the video sample data in the target grid and the electronic eye for acquiring the video sample data in the target grid; and the time determining submodule is used for determining the time range of motion in the target grid according to the time of the moving target object appearing in the video sample data in the target grid.
And the track generation module is used for connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
As a preferred embodiment, the system further includes: the moving target object query module is used for determining a moving target object in a rectangular query mode; the static characteristic information extraction module is used for extracting static characteristic information of the moving target object, and the static characteristic information comprises: walking angle, facial features, clothing features. The moving target object query module specifically comprises: and the moving target object query submodule is used for determining the moving target object in each frame of image in the process from appearance to disappearance of the moving target object in a rectangular query mode for any video source.
Example 3
As shown in fig. 3, the present invention further provides an apparatus for tracking a moving trajectory of a moving target object, the apparatus comprising: the video target meshing system comprises a video target meshing system construction module, a mass data space discretization processing module and a moving target analysis and track generation module.
The video target gridding system construction module is mainly responsible for constructing a video data gridding management system based on a GeoSOT model, and demarcating the target detection accuracy and performance of a network by self-constructing a test sample data set including various moving targets.
The massive data space discretization processing module is mainly used for performing space discretization on massive video data of different sources in different regions within a certain time according to specified analysis precision, and discretizing the video data into different three-dimensional grids to form a plurality of three-dimensional grid sets containing the video data.
And the moving target analysis and track generation module is mainly used for circularly inputting the three-dimensional grid set into the video data gridding management system, smoothly extracting the characteristic information of the moving target object, including information such as spatial position, direction, time and the like, and superposing all moving target track points in the three-dimensional grid space according to the time sequence to finally form a moving track of the moving target in a target area within a certain time range.
The method and the system have the following advantages:
the method has the advantages that: and the target retrieval efficiency is improved. By constructing a video data gridding management system based on a GeoSOT model, the problem of low efficiency of watching videos by relying on a large amount of manual work originally is changed into a spatial retrieval problem, and when the number of moving targets is increased, the moving targets are processed only once, so that the video target detection performance and accuracy are improved.
The advantages are two: and the mass data retrieval efficiency is improved. By the spatial discretization of the mass video data, target retrieval and analysis in batches are realized, distributed calculation and scheduling are supported, and the target retrieval efficiency under the mass video data is comprehensively improved.
The advantages are three: the usability of target retrieval information is improved, and the moving target data and the space/time information can be automatically associated through data space discretization, so that the finally generated moving target effective activity track can provide support for various applications.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, it should be understood that no limitation of the invention is thereby intended within the scope of this specification.
Claims (8)
1. A method for tracking the moving track of a moving target object is characterized by comprising the following steps:
respectively inquiring the video sources to obtain video sample data of different video sources in a target area;
constructing a GeoSOT model of a target area;
respectively discretizing each video sample data into a three-dimensional grid of the GeoSOT model;
traversing each three-dimensional grid of the GeoSOT model, determining the three-dimensional grid where the moving target object is located as a target grid, and specifically comprising the following steps: extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in a stereoscopic grid; respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object; when image samples consistent with the static characteristic information of the moving target object exist in the video sample data in the three-dimensional grid, determining the three-dimensional grid as the three-dimensional grid where the moving target object is located;
respectively extracting dynamic characteristic information of the moving target object in each target grid, and constructing a track point set of the moving target object; the dynamic characteristic information comprises a spatial position, a motion direction and time;
and connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
2. The method according to claim 1, wherein the traversing each three-dimensional mesh of the GeoSOT model, determining the three-dimensional mesh where the moving object is located as a target mesh, further comprises:
determining a moving target object in a rectangular query mode;
extracting static characteristic information of the moving target object, wherein the static characteristic information comprises: walking angle, facial features, and clothing features.
3. The method for tracking the moving track of the moving target object according to claim 2, wherein the determining the moving target object by the rectangular query specifically comprises:
for any video source, the moving target object in the image of each frame in the process from appearance to disappearance of the moving target object is determined in a rectangular query mode.
4. The method for tracking a moving trajectory of a moving target object according to claim 1, wherein the extracting dynamic feature information of the moving target object in each target mesh respectively specifically includes:
determining distance information between a moving target object and an electronic eye for acquiring video sample data in a target grid according to the shooting size of the moving target object in an image sample in the target grid, the actual size of the moving target object and correction parameters of the electronic eye for acquiring the video sample data in the target grid;
determining the space position of the moving target object in the target grid according to the distance information and the position of an electronic eye of video sample data in the target grid;
determining the motion direction of the moving target object in the target grid according to the difference value of the distance information between the moving target object in two adjacent image samples in the video sample data in the target grid and the electronic eye for acquiring the video sample data in the target grid;
and determining the time range of motion in the target grid according to the time of the moving target object appearing in the video sample data in the target grid.
5. A system for tracking a trajectory of a moving target object, the system comprising:
the video sample data acquisition module is used for respectively inquiring the video sources and acquiring video sample data of different video sources in the target area;
the GeoSOT model building module is used for building a GeoSOT model of the target area;
the video sample data discretization module is used for discretizing each video sample data into a three-dimensional grid of the GeoSOT model;
the target grid determining module is used for traversing each three-dimensional grid of the GeoSOT model, determining the three-dimensional grid where the moving target object is located, and using the three-dimensional grid as a target grid;
the target grid determining module specifically includes: the static characteristic information extraction submodule is used for extracting static characteristic information of an object to be identified of each frame of image sample of video sample data in the three-dimensional grid; the consistency comparison submodule is used for respectively carrying out consistency comparison on the static characteristic information of the object to be identified of each frame of image sample and the static characteristic information of the moving target object; the three-dimensional grid determining submodule is used for determining the three-dimensional grid as the three-dimensional grid where the moving target object is located when the image sample consistent with the static characteristic information of the moving target object exists in the video sample data in the three-dimensional grid;
the dynamic characteristic information extraction module is used for respectively extracting the dynamic characteristic information of the moving target object in each target grid and constructing a track point set of the moving target object; the dynamic characteristic information comprises a spatial position, a motion direction and time;
and the track generation module is used for connecting the track point sets according to the time sequence to generate a movable track of the movable target object in the target area.
6. The moving object trajectory tracking system of claim 5, further comprising:
the moving target object query module is used for determining a moving target object in a rectangular query mode;
the static characteristic information extraction module is used for extracting static characteristic information of the moving target object, and the static characteristic information comprises: walking angle, facial features, clothing features.
7. The system for tracking the moving track of a moving target object according to claim 6, wherein the moving target object query module specifically comprises:
and the moving target object query submodule is used for determining the moving target object in each frame of image in the process from appearance to disappearance of the moving target object in a rectangular query mode for any video source.
8. The system for tracking the moving track of a moving target object according to claim 5, wherein the dynamic feature information extraction module specifically comprises:
the distance information determining submodule is used for determining the distance information between the moving target object and the electronic eye for acquiring the video sample data in the target grid according to the shooting size of the moving target object in the image sample in the target grid, the actual size of the moving target object and the correction parameters of the electronic eye for acquiring the video sample data in the target grid;
the spatial position determining submodule is used for determining the spatial position of the moving target object in the target grid according to the distance information and the position of an electronic eye of video sample data in the target grid;
the motion direction determining submodule is used for determining the motion direction of the moving target object in the target grid according to the difference value of the distance information between the moving target object in two adjacent image samples in the video sample data in the target grid and the electronic eye for acquiring the video sample data in the target grid;
and the time determining submodule is used for determining the time range of motion in the target grid according to the time of the moving target object appearing in the video sample data in the target grid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111446792.1A CN113850845B (en) | 2021-12-01 | 2021-12-01 | Moving track tracking method and system for moving target object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111446792.1A CN113850845B (en) | 2021-12-01 | 2021-12-01 | Moving track tracking method and system for moving target object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113850845A CN113850845A (en) | 2021-12-28 |
| CN113850845B true CN113850845B (en) | 2022-03-01 |
Family
ID=78982520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111446792.1A Active CN113850845B (en) | 2021-12-01 | 2021-12-01 | Moving track tracking method and system for moving target object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113850845B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108959373A (en) * | 2018-05-23 | 2018-12-07 | 北京都在哪网讯科技有限公司 | Footprint point generation method and device |
| CN110866015A (en) * | 2019-11-18 | 2020-03-06 | 中国电子科技集团公司第二十八研究所 | Moving target moving range recording method based on local grid |
| CN112182279A (en) * | 2020-12-03 | 2021-01-05 | 武大吉奥信息技术有限公司 | Indoor self-positioning method and equipment based on discrete grid and image matching |
-
2021
- 2021-12-01 CN CN202111446792.1A patent/CN113850845B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108959373A (en) * | 2018-05-23 | 2018-12-07 | 北京都在哪网讯科技有限公司 | Footprint point generation method and device |
| CN110866015A (en) * | 2019-11-18 | 2020-03-06 | 中国电子科技集团公司第二十八研究所 | Moving target moving range recording method based on local grid |
| CN112182279A (en) * | 2020-12-03 | 2021-01-05 | 武大吉奥信息技术有限公司 | Indoor self-positioning method and equipment based on discrete grid and image matching |
Non-Patent Citations (2)
| Title |
|---|
| 一种基于剖分格网的新型导航定位服务方法;杨宇博等;《测绘通报》;20140125(第1期);第1-5页 * |
| 移动对象时空轨迹及社交关系一体化数据模型;张恒才等;《武汉大学学报·信息科学版》;20140630;第39卷(第6期);第711-718页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113850845A (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109783685B (en) | Query method and device | |
| Bae et al. | High-precision vision-based mobile augmented reality system for context-aware architectural, engineering, construction and facility management (AEC/FM) applications | |
| CN110428449B (en) | Target detection tracking method, device, equipment and storage medium | |
| CN105761500A (en) | Traffic accident handling method and traffic accident handling device | |
| CN113177518B (en) | Vehicle re-identification method based on weak supervision area recommendation | |
| Rathore et al. | Real-time video processing for traffic control in smart city using Hadoop ecosystem with GPUs | |
| CN103208008A (en) | Fast adaptation method for traffic video monitoring target detection based on machine vision | |
| CN113762044A (en) | Road recognition method, road recognition device, computer equipment and storage medium | |
| CN109857891A (en) | A kind of querying method and device | |
| CN112380894B (en) | Video overlapping region target deduplication method and system based on three-dimensional geographic information system | |
| CN113420679A (en) | Artificial intelligent cross-camera multi-target tracking system and tracking algorithm | |
| CN111881777A (en) | Video processing method and device | |
| CN114328780A (en) | Hexagonal lattice-based smart city geographic information updating method, device and medium | |
| CN114299230B (en) | Data generation method and device, electronic equipment and storage medium | |
| Gao et al. | Multi-object tracking with Siamese-RPN and adaptive matching strategy | |
| Zaman et al. | A robust deep networks based multi-object multi-camera tracking system for city scale traffic | |
| CN113850845B (en) | Moving track tracking method and system for moving target object | |
| Rishika et al. | Real-time vehicle detection and tracking using YOLO-based deep sort model: A computer vision application for traffic surveillance | |
| Li et al. | Rethink geographical generalizability with unsupervised self-attention model ensemble: A case study of openstreetmap missing building detection in africa | |
| Simsek et al. | Sompt22: A surveillance oriented multi-pedestrian tracking dataset | |
| Ganesh et al. | An intelligent video surveillance framework with big data management for Indian road traffic system | |
| Shamsollahi et al. | Construction progress monitoring and reporting using computer vision techniques–a review | |
| CN112860821A (en) | Human-vehicle trajectory analysis method and related product | |
| Sreekumar et al. | TPCAM: Real-time traffic pattern collection and analysis model based on deep learning | |
| Zhao et al. | A decoding-based method for fast background filtering of roadside LiDAR data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221122 Address after: Room 501-507, Building 1, Artificial Intelligence Industrial Park, 266 Chuangyan Road, Qilin Science and Technology Innovation Park, Nanjing, Jiangsu 211135 Patentee after: Nanjing Hanhai Fuxi Defense Technology Co.,Ltd. Address before: 211000 Room 201, 13 / F, building a, qiaomeng garden, Nanjing, Jiangsu, No. 100, Tianjiao Road, Qilin science and Technology Innovation Park, Jiangning District, Nanjing, Jiangsu Patentee before: Nanjing Hanhai Xingyu Information Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |