CN105791686B - Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking - Google Patents
Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking Download PDFInfo
- Publication number
- CN105791686B CN105791686B CN201610121742.9A CN201610121742A CN105791686B CN 105791686 B CN105791686 B CN 105791686B CN 201610121742 A CN201610121742 A CN 201610121742A CN 105791686 B CN105791686 B CN 105791686B
- Authority
- CN
- China
- Prior art keywords
- tracked
- acousto
- optic modulator
- image
- moving target
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/68—Control of cameras or camera modules for stable pick-up of the scene, e.g. compensating for camera body vibrations
- H04N23/681—Motion detection
Abstract
The present invention provides multiple mobile object capture and tracking equipment and multiple mobile object capture and tracking, and wherein equipment includes: panoramic picture collector, the controller being electrically connected with panoramic picture collector, multiple points of mirror camera systems being electrically connected with controller;Panoramic picture collector transmits collected panorama ambient image to controller;Controller determines the position of multiple moving targets to be tracked and each moving target to be tracked according to panorama ambient image, instructs to dividing mirror camera system to send corresponding motion target tracking;Divide mirror camera system to reflect the light from moving target to be tracked, captured using light principle of reflection when camera lens is directed toward constant and tracks multiple moving targets to be tracked.The present invention carries out the capture and tracking of multiple moving targets in the case where keeping taking lens to be directed toward constant by light principle of reflection, and the problem for avoiding mechanical adjustment lens direction adjustment speed slow improves the capture tracking velocity of multiple moving targets.
Description
Technical field
It captures the present invention relates to field of optical equipment more particularly to multiple mobile object and is caught with tracking equipment and multiple mobile object
It catches and tracking.
Background technique
Multiple mobile object capture with tracking be computer vision field research hotspot, multiple mobile object capture with
Track refers to determines interested multiple self-movement targets with certain notable feature using computer in the video sequence
Position, size and the complete motion profile of each moving target.In recent years, at full speed with computer digital animation ability
Increase and the development of image analysis technology, real-time capture and the tracking technique of moving target are shown one's talent.To multiple movement mesh
Mark carry out real-time capture and tracking, video monitoring, video compression coding, robot navigation and positioning, intelligent human-machine interaction with
And there is important practical value in the fields such as virtual reality.
The prior art provides the capture and tracking equipment of multiple mobile object, which includes controller, with controller electricity
The PTZ camera of connection.The working principle of the equipment is: obtaining the image of moving target by PTZ camera and is transmitted to
Controller, controller carry out moving object detection and tracking to the image received, determine the multiple moving targets for needing to track,
Control instruction, which is sent, after PTZ camera receives control instruction to PTZ camera adjusts camera lens under the control of control instruction
Shooting direction, track up is carried out to multiple moving targets for tracking of needs.
In the prior art, track up is carried out to multiple moving targets using PTZ camera, due to multiple moving targets
Position dynamic change, therefore PTZ camera need in time adjust lens direction.However, PTZ camera is using mechanical rotation
Mode adjust lens direction, with the slow defect of adjustment speed, cause to reduce the capture tracking velocity of multiple moving targets.
Summary of the invention
The present invention provides multiple mobile objects to capture and tracking equipment and multiple mobile object capture and tracking, Neng Gou
Keep taking lens be directed toward it is constant in the case where by light principle of reflection carry out moving target capture and tracking, avoid machinery
The slow problem of lens direction adjustment speed is adjusted, the capture tracking velocity of multiple moving targets is improved.
In a first aspect, the embodiment of the invention provides a kind of capture of multiple mobile object and tracking equipments, comprising: panoramic picture
Collector, the controller being electrically connected with the panoramic picture collector, multiple points of mirrors being electrically connected with the controller are taken the photograph
As system;Specific bit in multiple pickup areas for dividing mirror camera system to be respectively arranged at the panoramic picture collector
It sets;The panorama ambient image is transmitted to the controller for acquiring panorama ambient image by the panoramic picture collector;
The controller determines multiple movement mesh to be tracked according to the panorama ambient image for receiving the panorama ambient image
Mark is generated and is instructed with multiple one-to-one motion target trackings of moving target to be tracked, by multiple moving targets
Trace command is transmitted separately to corresponding point of mirror camera system;Described point of mirror camera system is for receiving the motion target tracking
Instruction reflects the light for carrying out the self-corresponding moving target to be tracked according to motion target tracking instruction, benefit
The corresponding moving target to be tracked is captured and tracked when camera lens is directed toward constant with light line reflection principle, obtains corresponding institute
It states the image of moving target to be tracked and is transmitted to the controller;The controller, which is also used to receive, each described divides mirror to image
The image for multiple moving targets to be tracked that system returns carries out sorting processing to described image, generate with it is each described
The one-to-one motion profile video of moving target to be tracked.
With reference to first aspect, the first possible embodiment the embodiment of the invention provides first aspect, wherein described
Controller includes the GPU (Graphic Processing Unit, graphics processor) and CPU (Central being electrically connected to each other
Processing Unit, central processing unit);The CPU is electrically connected with the panoramic picture collector, described complete for receiving
The current frame image is transferred to the GPU by the current frame image of scape ambient image;The GPU is used for the present frame
Image carries out moving object detection, obtains the characteristics of image of each moving target in the current frame image and is sent to described
CPU;Wherein, the characteristics of image of the moving target includes image coordinate, color characteristic and the textural characteristics of the moving target;
The CPU respectively with it is multiple it is described divide mirror camera system to be electrically connected, will for receiving the characteristics of image of each moving target
The characteristics of image of each moving target merges respectively, and is matched with pre-stored characteristics of image, according to the spy
Sign matching result determines the position of multiple moving targets to be tracked and each moving target to be tracked;According to it is each it is described to
The position of pursuit movement target generates one-to-one motion target tracking instruction;Determining and each moving target to be tracked
Corresponding point of position mirror camera system;Each motion target tracking instruction of generation is respectively corresponded and is transmitted to really
Divide mirror camera system described in fixed.
The first possible embodiment with reference to first aspect, may the embodiment of the invention provides second of first aspect
Embodiment, wherein the GPU for being pre-processed to the current frame image, the pretreatment include decoding and/or
Denoising;Background modeling is carried out using mixed Gaussian, generates the background model of preset quantity;According to the background mould of the preset quantity
Type carries out moving object detection to the pretreated current frame image, obtains each moving target in the current frame image
Characteristics of image and be sent to the CPU.
The first possible embodiment with reference to first aspect, the embodiment of the invention provides first aspect, the third may
Embodiment, wherein the CPU is generated each for being analyzed according to the position of each moving target to be tracked
The corresponding light deflection parameter of the moving target to be tracked, focus adjustment parameter and acquisition parameters, it is inclined according to the light
Turn parameter, focus adjustment parameter and acquisition parameters and generates motion target tracking instruction;It is closed according to preset position is corresponding
System determines each described corresponding point of mirror camera system of moving target to be tracked;By each moving target of generation with
Track instruction, which respectively corresponds to be transmitted to, determining described divides mirror camera system.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiments of first aspect, wherein described
Motion target tracking instruction carries light deflection parameter and acquisition parameters;Described point of mirror camera system include acousto-optic modulator and
High-definition camera;The acousto-optic modulator is electrically connected with the controller, the motion target tracking instruction is received, according to described
The light deflection parameter that motion target tracking instruction carries carries out the light for carrying out the self-corresponding moving target to be tracked anti-
It penetrates, the light is reflexed in the high-definition camera;The high-definition camera is electrically connected with the controller, described in reception
Motion target tracking instruction, the acquisition parameters carried according to motion target tracking instruction are when camera lens is directed toward constant to correspondence
The moving target to be tracked shot.
4th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 5th kind of possibility of first aspect
Embodiment, wherein the acousto-optic modulator includes longitudinal acousto-optic modulator and lateral acousto-optic modulator, the longitudinal direction acousto-optic
Modulator, the lateral acousto-optic modulator and the high-definition camera are arranged successively, the longitudinal direction acousto-optic modulator and the cross
It is electrically connected respectively with the controller to acousto-optic modulator;The longitudinal direction acousto-optic modulator receives the motion target tracking and refers to
It enables, according to the light deflection parameter self-corresponding moving target to be tracked in future of motion target tracking instruction carrying
Light longitudinally reflexes to the lateral acousto-optic modulator;The transverse direction acousto-optic modulator receives the motion target tracking instruction,
Light after longitudinal reflection is laterally reflexed to institute by the light deflection parameter carried according to motion target tracking instruction
It states in high-definition camera.
5th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 6th kind of possibility of first aspect
Embodiment, wherein described that mirror camera system is divided to further include liquid crystal lens, the longitudinal direction acousto-optic modulator, the lateral sound
Optical modulator, the liquid crystal lens and the high-definition camera are arranged successively;The liquid crystal lens are electrically connected with the controller;
The motion target tracking instruction carries focus adjustment parameter;The liquid crystal lens receive the motion target tracking instruction,
Focus adjustment is carried out according to the focus adjustment parameter that motion target tracking instruction carries;Light after the laterally reflection is worn
The liquid crystal lens are crossed into the high-definition camera.
4th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 7th kind of possibility of first aspect
Embodiment, wherein the acousto-optic modulator includes lateral acousto-optic modulator and longitudinal acousto-optic modulator, described that mirror is divided to image
System further includes liquid crystal lens, the transverse direction acousto-optic modulator, longitudinal acousto-optic modulator, the liquid crystal lens and the height
Clear camera is arranged successively;The transverse direction acousto-optic modulator, longitudinal acousto-optic modulator and the liquid crystal lens respectively with institute
State controller electrical connection.
6th kind of possible embodiment with reference to first aspect, the embodiment of the invention provides the 8th kind of possibility of first aspect
Embodiment, wherein it is described that mirror camera system is divided to further include liquid crystal lens mounting rack, high-definition camera mounting rack, lateral sound
Optical modulator mounting rack and longitudinal acousto-optic modulator mounting rack;The liquid crystal lens mounting rack, the high-definition camera mounting rack,
Regulating element is respectively arranged on the transverse direction acousto-optic modulator mounting rack and longitudinal acousto-optic modulator mounting rack;Pass through institute
It states regulating element and adjusts the liquid crystal lens, the high-definition camera, the lateral acousto-optic modulator and longitudinal sound respectively
The installation site of optical modulator.
Second aspect, the embodiment of the invention provides a kind of capture of multiple mobile object and trackings, comprising: acquisition panorama
Ambient image determines multiple moving targets to be tracked according to the panorama ambient image;It generates and multiple movements to be tracked
The one-to-one motion target tracking instruction of target;Multiple motion target tracking instructions are transmitted separately to corresponding point of mirror
Camera system;Wherein, the designated position in image acquisition region, which is respectively arranged with, multiple described divides mirror camera system;Described point of mirror
Camera system is instructed according to the motion target tracking reflects the light for carrying out the self-corresponding moving target to be tracked,
The corresponding moving target to be tracked is captured and tracked when camera lens is directed toward constant using light principle of reflection, is obtained corresponding
The image of the moving target to be tracked;Sorting processing is carried out to the image of each moving target to be tracked, is generated and each
A one-to-one motion profile video of moving target to be tracked.
In the embodiment of the present invention, divides mirror camera system to reflect the light from moving target to be tracked, utilize light
Line reflection principle captures when camera lens is directed toward constant and tracks multiple moving targets to be tracked.Due to capture and track it is multiple to
Camera lens direction haves no need to change when track moving target, therefore the device and method in the present embodiment can be improved multiple moving targets
Capture tracking velocity, avoid the problem that mechanical adjustment lens direction adjustment speed is slow in the prior art.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of structural representation of the capture and tracking equipment of multiple mobile object provided by first embodiment of the invention
Figure;
It captures Fig. 2 shows multiple mobile object provided by first embodiment of the invention and shows with another structure of tracking equipment
It is intended to;
Fig. 3 shows a kind of structural schematic diagram for dividing mirror camera system provided by first embodiment of the invention;
Fig. 4 shows another structural schematic diagram for dividing mirror camera system provided by first embodiment of the invention;
Fig. 5 shows the flow diagram of image processing algorithm provided by first embodiment of the invention;
Fig. 6 shows the flow diagram of the capture and tracking of multiple mobile object provided by second embodiment of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
In view of carrying out track up to multiple moving targets using PTZ camera in the prior art, PTZ camera is adopted
Adjust lens direction with the mode of machinery rotation, with the slow defect of adjustment speed, cause the capture to multiple moving targets with
Track speed reduces, and the present invention provides multiple mobile object capture and tracking equipment and multiple mobile object captures and tracking, under
Face is specifically described in conjunction with the embodiments.
Embodiment one
Fig. 1 shows a kind of structural representation of the capture and tracking equipment of multiple mobile object provided by first embodiment of the invention
Figure.As shown in Figure 1, the multiple mobile object in the present embodiment captures with tracking equipment 1 and includes:
Panoramic picture collector 10, the controller 20 being electrically connected with panoramic picture collector 10 are electric respectively with controller 20
Multiple points of mirror camera systems 30 of connection;Multiple points of mirror camera systems 30 are respectively arranged at the acquisition zone of panoramic picture collector 10
Designated position in domain;
Panorama ambient image is transmitted to controller 20 for acquiring panorama ambient image by panoramic picture collector 10;
Controller 20 is used to receive panorama ambient image, determines multiple moving targets to be tracked according to panorama ambient image,
It generates and is instructed with multiple one-to-one motion target trackings of moving target to be tracked, multiple motion target trackings are instructed and are distinguished
It is transmitted to corresponding point of mirror camera system 30;
Divide mirror camera system 30 for receiving motion target tracking instruction, according to motion target tracking instruction to from correspondence
The light of moving target to be tracked reflected, captured using light principle of reflection when camera lens is directed toward constant and track correspondence
Moving target to be tracked, the image for obtaining corresponding moving target to be tracked is simultaneously transmitted to controller 20;
Controller 20 is also used to receive the image of multiple moving targets to be tracked of each point of mirror camera system 30 return, right
The image carries out sorting processing, generates and each one-to-one motion profile video of moving target to be tracked.
In the embodiment of the present invention, mirror camera system 30 is divided to reflect the light from moving target to be tracked, utilized
Light principle of reflection captures when camera lens is directed toward constant and tracks multiple moving targets to be tracked.Due to capture and track it is multiple to
Camera lens direction haves no need to change when pursuit movement target, therefore the equipment in the present embodiment can be improved catching for multiple moving targets
Tracking velocity is caught, the problem that mechanical adjustment lens direction adjustment speed is slow in the prior art is avoided.
In the present embodiment, the pickup area of panoramic picture collector 10 is divided into several subregions, and each subregion is all
Coordinate is demarcated, each sub-regions are all correspondingly arranged a point of mirror camera system 30.When moving target to be tracked is located at a certain sub-district
When in domain, pass through the capture and tracking for dividing mirror camera system 30 to carry out moving target to be tracked in the subregion.
In the present embodiment, controller 20 determines multiple moving targets to be tracked and each to be tracked according to panorama ambient image
The position of moving target;One-to-one motion target tracking instruction is generated according to the position of each moving target to be tracked;Really
Determine and corresponding point of the position mirror camera system 30 of each moving target to be tracked;By each motion target tracking of generation
Instruction, which respectively corresponds to be transmitted to, determining divides mirror camera system 30.
Table 1
Table 1 is shown after controller 20 receives panorama ambient image, is obtained after analyzing panorama ambient image
Multiple moving targets to be tracked, each moving target to be tracked position, one-to-one with each moving target to be tracked
Motion target tracking instruction is shown with a kind of table of corresponding point of the position mirror camera system of each moving target to be tracked
Meaning.As shown in table 1, controller sends No. 1 motion target tracking instruction in order to which 1,2, No. 3 target is captured and tracked
To No. 3 points of mirror camera systems for being located at 3 work song regions, No. 2 motion target tracking instructions are sent to 1 positioned at 1 work song region
No. 3 motion target trackings instructions are sent to No. 2 points of mirror camera systems positioned at 2 work song regions by number point mirror camera system.Pass through
Table 1 is, it can be seen that controller 20 can generate corresponding motion target tracking instruction for each moving target to be tracked, concurrently
It send to corresponding point of mirror camera system 30, therefore the equipment in the present embodiment can capture and track multiple movement mesh to be tracked
Mark.
When due to capturing and tracking multiple moving targets to be tracked, imaged with each corresponding point of mirror of moving target to be tracked
System 30 can be transmitted back to the image of corresponding moving target to be tracked to controller 20, these images mix,
Each moving target to be tracked cannot be distinguished, therefore controller 20 also carries out the image that each point of mirror camera system 30 is transmitted back to
Sorting processing, the image of each moving target to be tracked is individually sorted out, and is generated with each moving target to be tracked one by one
Corresponding motion profile video file, to record the motion profile of each moving target to be tracked.
In the present embodiment, panoramic picture collector 10 is mounted on predeterminated position.Panoramic picture collector 10 preferably uses
CMOS (Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductor) panoramic high-definition
1080P video camera, CMOS panoramic high-definition 1080P video camera with the rate of 25 frame per second by resolution ratio for 1080P (1920 ×
1080) video streaming image passes through network cable real-time Transmission to controller 20 with the rate of 1000Mbps.It adopts in the prior art
Video flowing resolution ratio is usually (video graphics array, Video Graphics Array) (640 × 480) VGA, seldom energy
Reach 720P (1280 × 720).It compared with prior art, can by CMOS panoramic high-definition 1080P video camera in the present embodiment
The high panorama ambient image of clarity is got, to improve the accuracy of subsequent image analysis processing, also, video resolution
Raising can make controller 20 handle details it is more, improve to small volume or apart from farther away moving target detection success
Rate.
It captures Fig. 2 shows multiple mobile object provided by first embodiment of the invention and shows with another structure of tracking equipment
It is intended to.In Fig. 2, it is described by taking a point of mirror camera system 30 as an example.As shown in Fig. 2, in the present embodiment, controller 20 includes
The GPU21 and CPU22 being electrically connected to each other;CPU22 is electrically connected with panoramic picture collector 10, for receiving panorama ambient image
Current frame image is transferred to GPU21 by current frame image;GPU21 is used to carry out moving object detection to current frame image, obtains
The characteristics of image of each moving target and CPU22 is sent in current frame image;Wherein, the characteristics of image of moving target includes fortune
Image coordinate, color characteristic and the textural characteristics of moving-target;CPU22 is electrically connected with multiple points of mirror camera systems 30 respectively, is used for
The characteristics of image for receiving each moving target merges the characteristics of image of each moving target respectively, and with pre-stored figure
As feature is matched, each moving target in current frame image is screened according to characteristic matching result, is determined multiple
The position of moving target to be tracked and each moving target to be tracked;It is generated one by one according to the position of each moving target to be tracked
Corresponding motion target tracking instruction;It determines and corresponding point of the position mirror camera system of each moving target to be tracked
30;The instruction of each motion target tracking of generation is respectively corresponded to be transmitted to and determining divides mirror camera system 30.Wherein, to be tracked
The position of moving target includes the image coordinate and space coordinate of moving target to be tracked.
Above-mentioned GPU21 carries out moving object detection to current frame image, obtains each moving target in current frame image
The characteristics of image and detailed process for being sent to CPU22 is: GPU21 pre-processes current frame image, which includes solution
Code and/or denoising;Background modeling is carried out using mixed Gaussian, generates the background model of preset quantity;According to the back of preset quantity
Scape model carries out moving object detection to pretreated current frame image, obtains the figure of each moving target in current frame image
As feature and it is sent to CPU22.
Specifically, GPU21 decodes current frame image, perhaps denoises to current frame image or to present frame figure
Picture is decoded and denoising.GPU21 carries out background modeling using mixed Gaussian, generates 5-7 background model.GPU21 root
Moving object detection is carried out to pretreated current frame image according to 5-7 background model, background is rejected from current frame image
Image obtains the characteristics of image of each moving target in each moving target in current frame image and current frame image, and will
The characteristics of image of each moving target is sent to CPU22 in current frame image.Compared with prior art, GPU21 in the present embodiment
Using 5-7 model foundation Steady Background Light, bigger calculation scale leads to the raising of sport foreground Yu background segment accuracy, and
GPU21 parallel computation characteristic guarantees the real-time completion largely calculated.
By GPU21 to current frame image carry out moving object detection, can be detected from current frame image obtain it is multiple
Moving target and the respective image coordinate of multiple moving targets, color characteristic and textural characteristics, wherein color characteristic can lead to
Color histogram expression is crossed, textural characteristics can be indicated by local invariable rotary texture, histogram of gradients.GPU21 will be multiple
The respective image coordinate of moving target, color characteristic and textural characteristics are sent to CPU22.
In the present embodiment, GPU21 will be divided into minor matrix block to the treatment process of high definition digital image and be assigned to
It is carried out simultaneously in thousand computing units and processing thread, greatly improves processing speed.GPU21 utilizes embedded moving target
Most of garbage in image is filtered out with feature detection algorithm, retains effective information, i.e., it is multiple in current frame image
The effective information of data scale very little is only transferred to CPU22 by the characteristics of image of moving target.
CPU22 receives the respective image coordinate of each moving target, color characteristic and textural characteristics, for each movement mesh
Mark, its respective image coordinate, color characteristic and textural characteristics are merged, and by fused feature with it is pre-stored
Characteristics of image is matched, if successful match, it is determined that the corresponding moving target of the fused feature is movement mesh to be tracked
Mark, and in memory by the fused characteristic storage, the template as next frame matching primitives.CPU22 also determines to be tracked
The image coordinate is converted to space coordinate, according to the space of moving target to be tracked by the position of moving target, such as image coordinate
The instruction of Coordinate generation motion target tracking, and determined according to the space coordinate of moving target to be tracked and corresponding mirror is divided to image
The instruction of the motion target tracking of generation is transmitted to and determining divides mirror camera system 30 by system 30.In the present embodiment, CPU22 energy
It is enough that multiple moving targets to be tracked are filtered out according to characteristic matching result, and send movement respectively to multiple points of mirror camera systems 30
Target following instruction, so that control multiple points of mirror camera systems 30 tracks each moving target to be tracked respectively.
In order to make up background modeling method to the inaccuracy of the lower situation of target speed, CPU22 in the present embodiment
When carrying out moving target screening, a variety of characteristics of image of fusional movement target, including image coordinate, color characteristic and texture are special
Sign further improves the accuracy of prospect and background separation, realizes to the accurate of moving target interested in complex environment
Detection.In the present embodiment, CPU22 realizes the matching algorithm of moving target position and color, Texture Feature Fusion, realizes pair
The quick and precisely description of target trajectory.
Due to dividing mirror camera system to need capture and tracking according to the space coordinate of moving target progress moving target, because
This CPU22 generates the specific mistake of one-to-one motion target tracking instruction according to the space coordinate of each moving target to be tracked
Cheng Shi: CPU22 is divided according to the position of each moving target to be tracked, the space coordinate of such as each moving target to be tracked
Analysis generates the corresponding light deflection parameter of each moving target to be tracked, focus adjustment parameter and acquisition parameters, according to light
It deflects parameter, focus adjustment parameter and acquisition parameters and generates motion target tracking instruction.In addition, CPU22 also according to setting in advance
Fixed position corresponding relationship, such as the corresponding relationship of space coordinate and the position for dividing mirror camera system, determining and each fortune to be tracked
Each motion target tracking instruction of generation is respectively corresponded biography by corresponding point of mirror camera system of the space coordinate of moving-target
It transports to and determining divides mirror camera system 30.
Table 2
Table 2 shows the space coordinate, each of the motion target tracking instruction of CPU22 generation, each moving target to be tracked
Corresponding relationship schematic table between corresponding point of mirror camera system of a moving target to be tracked.As shown in Table 2, each fortune to be tracked
Moving-target all has corresponding space coordinate, motion target tracking instruction and divides mirror camera system.In motion target tracking instruction
Light deflection parameter includes light deflection angle, and focus adjustment parameter includes focus adjustment distance, when acquisition parameters include shutter
Length, aperture size etc..
In the present embodiment, controller 20 using GPU21 and CPU22 heterogeneous parallel processing mode to ambient image at
Reason, can mention the working efficiency of GPU21 and CPU22 by this heterogeneous parallel processing mode, to improve image procossing speed
Degree.
As shown in Fig. 2, mirror camera system 30 is divided to include acousto-optic modulator 31 and high-definition camera 32;Above-mentioned moving target with
Track instruction carries light deflection parameter and acquisition parameters;Acousto-optic modulator 31 is electrically connected with controller 20, receives moving target
Trace command, the light deflection parameter carried according to motion target tracking instruction is to the light for carrying out self-corresponding moving target to be tracked
Line is reflected, and light is reflexed in high-definition camera 32;High-definition camera 32 is electrically connected with controller 20, receives movement mesh
Trace command is marked, the acquisition parameters carried according to motion target tracking instruction are when camera lens is directed toward constant to corresponding fortune to be tracked
Moving-target is shot.
It is described by taking a point of mirror camera system as an example, in Fig. 2, between acousto-optic modulator 31 and high-definition camera 32
Line segment indicates paths direction.In the present embodiment, acousto-optic modulator 31 carries out light reflection, the light according to light deflection parameter
It includes the data such as light deflection angle that line, which deflects parameter,.When the light from moving target to be tracked is reflected by acousto-optic modulator 31
After in into high-definition camera 32, high-definition camera 32 is clapped according to acquisition parameters, such as shutter duration, aperture size parameter
It takes the photograph, to achieve the effect that capture and track moving target to be tracked.
Fig. 3 is the structural schematic diagram for dividing mirror camera system 30 in the present embodiment, as shown in figure 3, in order to guarantee acousto-optic tune
Device 31 processed accurately deflects light, and acousto-optic modulator 31 includes longitudinal acousto-optic modulator 311 and lateral acousto-optic modulator
312, longitudinal acousto-optic modulator 311, lateral acousto-optic modulator 312 and high-definition camera 32 are arranged successively, longitudinal acousto-optic modulator
311 and lateral acousto-optic modulator 312 be electrically connected respectively with controller 20;Longitudinal acousto-optic modulator 311 receives motion target tracking
The light of instruction, the light deflection parameter self-corresponding moving target to be tracked in future carried according to motion target tracking instruction is indulged
To reflexing to lateral acousto-optic modulator 312;Lateral acousto-optic modulator 312 receives motion target tracking instruction, according to moving target
The light deflection parameter that trace command carries laterally reflexes to the light after longitudinal reflection in high-definition camera 32.
In the present embodiment, the light from moving target to be tracked passes through longitudinal acousto-optic modulator 311, utilizes acoustooptical effect
The characteristics of generated Donald Bragg diffraction, realizes the control to the light direction of propagation, light progress longitudinal direction is deflected into specified
Light is carried out lateral deflection, converges in high-definition camera 32, taken the photograph by high definition by angle by lateral acousto-optic modulator 312
As first 32 covering power, the capture and tracking of moving target to be tracked are realized.
It also needs to carry out focus adjustment when capturing moving target to be tracked in view of high-definition camera 32, in order to avoid machinery
The slow problem of regulating time is focused, as shown in figure 3, dividing mirror camera system 30 further includes liquid crystal lens 33 in the present embodiment,
Longitudinal acousto-optic modulator 311, lateral acousto-optic modulator 312, liquid crystal lens 33 and high-definition camera 32 are arranged successively;Liquid crystal lens
33 are electrically connected with controller 20;Motion target tracking instruction carries focus adjustment parameter;Liquid crystal lens 33 receive moving target
Trace command carries out focus adjustment according to the focus adjustment parameter that motion target tracking instruction carries;After above-mentioned laterally reflection
Light passes through liquid crystal lens 33 and enters high-definition camera 32.
In Fig. 3, longitudinal acousto-optic modulator 311, lateral acousto-optic modulator 312, liquid crystal lens 33 and high-definition camera 32 it
Between line segment indicate paths direction.By dividing mirror camera system 30 in Fig. 3, the light from moving target to be tracked is first
Longitudinal reflection is first passed through, then by laterally reflection, liquid crystal lens 33 is eventually passed through and enters high-definition camera 32.
It in the present embodiment, is electrically connected by liquid crystal lens 33 with controller 20 and carries out shooting focal length adjusting, can reach burnt
The fast effect away from adjustment speed, avoids the problem that mechanical adjustment shooting focal length adjustment speed is slow in the prior art.
In the present embodiment, acousto-optic modulator 31 can also enough high-speed vibrating mirror replacements.High definition is taken the photograph in dividing mirror camera system 30
As adding liquid crystal lens 33, acousto-optic modulator 31 or high-speed vibrating mirror before head 32, acousto-optic tune can be passed through according to light path principle
Device 31 processed or high-speed vibrating mirror act on the deviation of optical path, and the ken that optical path is passed back is imaged on high-definition camera 32, by liquid crystal
The high speed focusing action of lens 33 can clearly obtain the image of clearly moving target to be tracked.
When it includes multiple for dividing mirror camera system 30, each image for dividing mirror camera system 30 to obtain is returned to control
The reaction speed of device 20, the equipment such as acousto-optic modulator 31 and liquid crystal lens 33 is all up nanosecond order, then divides mirror camera system
The speed of 30 acquisition images can reach musec order, and passing speed image back also can reach musec order, by controller 20 and divide
The cooperation of mirror camera system 30 may be implemented Microsecond grade moving target and capture and track.If replacing acousto-optic tune with high-speed vibrating mirror
Device 31 processed, reaction speed reach millisecond to musec order, then Millisecond moving target can be achieved and capture and track.
In practical application, the different perspectives of same moving target to be tracked can be captured by multiple points of mirror camera systems 30
Image also can get moving target to be tracked in large range of tool to construct the panoramic information of moving target to be tracked
Body moving line.
As shown in figure 4, dividing mirror camera system 30 there are also another structure type in the present embodiment, acousto-optic modulator 31 is wrapped
Lateral acousto-optic modulator 312 and longitudinal acousto-optic modulator 311 are included, dividing mirror camera system 30 further includes liquid crystal lens 33, lateral sound
Optical modulator 312, longitudinal acousto-optic modulator 311, liquid crystal lens 33 and high-definition camera 32 are arranged successively;Lateral acousto-optic modulator
312, longitudinal acousto-optic modulator 311 and liquid crystal lens 33 are electrically connected with controller 20 respectively.
In Fig. 4, longitudinal acousto-optic modulator 311, lateral acousto-optic modulator 312, liquid crystal lens 33 and high-definition camera 32 it
Between line segment indicate paths direction.By dividing mirror camera system 30 in Fig. 4, the light from moving target to be tracked is first
Lateral reflection is first passed through, then by longitudinal reflection, liquid crystal lens 33 is eventually passed through and enters high-definition camera 32.
For the ease of adjusting the position for dividing each device in mirror camera system 30, dividing mirror camera system 30 further includes that liquid crystal is saturating
Mirror mounting rack, high-definition camera mounting rack, lateral acousto-optic modulator mounting rack and longitudinal acousto-optic modulator mounting rack;Liquid crystal lens
It is respectively set on mounting rack, high-definition camera mounting rack, lateral acousto-optic modulator mounting rack and longitudinal acousto-optic modulator mounting rack
There is regulating element;Liquid crystal lens 33, high-definition camera 32,312 and of lateral acousto-optic modulator are adjusted respectively by the regulating element
The installation site of longitudinal acousto-optic modulator 311.
Multiple mobile object in through this embodiment captures and tracking equipment, effectively increases the tracking effect of moving target
Rate the negative effect of the rough sledding to tracking effect such as can eliminate deformation, block, intersect, to establish multiple moving targets
Completely, the motion trace data in long-time.
Fig. 5 shows the flow diagram of image processing algorithm provided in this embodiment, the image processing algorithm by CPU and
GPU is executed jointly, as shown in figure 5, the image processing algorithm includes:
Step 502, current frame image is pre-processed, which includes decoding and/or denoising;
Step 504, background modeling is carried out using mixed Gaussian, generates 5-7 background model;
Step 506, moving object detection is carried out to pretreated current frame image according to 5-7 background model, obtained
The characteristics of image of each moving target in current frame image;Wherein, the characteristics of image of moving target includes the image of moving target
Coordinate, color characteristic and textural characteristics;
Step 508, the characteristics of image of moving target each in current frame image is merged respectively, and be stored in advance
Characteristics of image matched, multiple moving targets in current frame image are screened according to characteristic matching result, determine
The image coordinate of multiple moving targets to be tracked and each moving target to be tracked;
The image coordinate is converted to space coordinate by step S510, according to the space coordinate of each moving target to be tracked
Generate one-to-one motion target tracking instruction, determining corresponding point of space coordinate with each moving target to be tracked
The instruction of each motion target tracking of generation is respectively corresponded to be transmitted to and determining divides mirror camera system by mirror camera system;
Step S512 receives the image for multiple moving targets to be tracked that each point of mirror camera system returns, to the image
Sorting processing is carried out, is generated and each one-to-one motion profile video of moving target to be tracked.
Image processing algorithm shown in Fig. 5 is executed jointly by CPU and GPU, ensure that image procossing accuracy, quickly
Property and robustness, improve image processing speed, realize the fusion of moving target position, color and textural characteristics, realize
The motion profile of moving target is fast and accurately described.
By the method in Fig. 5, using the estimation of Fuzzy Set Theory fusional movement position and speed and color, Gradient Features
Matching, increase search range in the historical data, effectively improve motion target tracking efficiency, can eliminate deform, block,
The motion trace data of moving target completely, in long-time is established in the negative effects of the rough sledding to tracking effect such as intersection.
Embodiment two
The multiple mobile object that Fig. 6 shows second embodiment of the invention offer captures the flow diagram with tracking,
As shown in fig. 6, this method comprises:
Step 602, panorama ambient image is acquired, multiple moving targets to be tracked are determined according to panorama ambient image;
Step 604, it generates and is instructed with multiple one-to-one motion target trackings of moving target to be tracked;
Step 606, the instruction of multiple motion target trackings is transmitted separately to corresponding point of mirror camera system;Wherein, image
Designated position in pickup area is respectively arranged with multiple points of mirror camera systems;
Step 608, divide mirror camera system according to motion target tracking instruction to next self-corresponding moving target to be tracked
Light is reflected, and captures and track corresponding moving target to be tracked when camera lens is directed toward constant using light principle of reflection,
Obtain the image of corresponding moving target to be tracked;
Step 610, sorting processing is carried out to the image of each moving target to be tracked, generated and each movement mesh to be tracked
Mark one-to-one motion profile video.
In the embodiment of the present invention, divides mirror camera system to reflect the light from moving target to be tracked, utilize light
Line reflection principle captures when camera lens is directed toward constant and tracks multiple moving targets to be tracked.Due to capture and track it is multiple to
Camera lens direction haves no need to change when track moving target, therefore the method in the present embodiment can be improved the capture of multiple moving targets
Tracking velocity avoids the problem that mechanical adjustment lens direction adjustment speed is slow in the prior art.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. a kind of multiple mobile object captures and tracking equipment characterized by comprising
Panoramic picture collector, the controller being electrically connected with the panoramic picture collector, is electrically connected with the controller
Multiple points of mirror camera systems;Multiple pickup areas for dividing mirror camera system to be respectively arranged at the panoramic picture collector
Interior designated position;Described point of mirror camera system includes acousto-optic modulator and high-definition camera;
The panorama ambient image is transmitted to the control for acquiring panorama ambient image by the panoramic picture collector
Device;
The controller determines multiple movements to be tracked according to the panorama ambient image for receiving the panorama ambient image
Target is generated and is instructed with multiple one-to-one motion target trackings of moving target to be tracked, by multiple movement mesh
Mark trace command is transmitted separately to corresponding point of mirror camera system;The motion target tracking instruction carries light deflection parameter
And acquisition parameters;
The acousto-optic modulator in described point of mirror camera system is electrically connected with the controller, receives the motion target tracking
Instruction, the light deflection parameter carried according to motion target tracking instruction is to the next self-corresponding moving target to be tracked
Light reflected, the light is reflexed in the high-definition camera, it is described that high definition described in mirror camera system is divided to take the photograph
Picture head is electrically connected with the controller, is received the motion target tracking instruction, is instructed and carried according to the motion target tracking
Acquisition parameters the corresponding moving target to be tracked is shot when camera lens is directed toward constant, obtain it is corresponding it is described to
The image of pursuit movement target is simultaneously transmitted to the controller;
The controller is also used to receive the figure of each multiple moving targets to be tracked for dividing mirror camera system to return
Picture carries out sorting processing to described image, generates and each one-to-one motion profile video of moving target to be tracked.
2. equipment according to claim 1, which is characterized in that the controller includes the GPU and CPU being electrically connected to each other;
The CPU is electrically connected with the panoramic picture collector, will for receiving the current frame image of the panorama ambient image
The current frame image is transferred to the GPU;
The GPU is used to carry out moving object detection to the current frame image, obtains each movement in the current frame image
The characteristics of image of target is simultaneously sent to the CPU;Wherein, the characteristics of image of the moving target includes the figure of the moving target
As coordinate, color characteristic and textural characteristics;
The CPU respectively with it is multiple it is described divide mirror camera system to be electrically connected, the image for receiving each moving target is special
Sign, the characteristics of image of each moving target is merged respectively, and is matched with pre-stored characteristics of image, according to institute
State the position that characteristic matching result determines multiple moving targets to be tracked and each moving target to be tracked;According to each institute
The position for stating moving target to be tracked generates one-to-one motion target tracking instruction;Determining and each movement to be tracked
Corresponding point of the position of target mirror camera system;Each motion target tracking instruction of generation is respectively corresponded into transmission
To dividing mirror camera system described in determining.
3. equipment according to claim 2, which is characterized in that the GPU for locating the current frame image in advance
Reason, the pretreatment include decoding and/or denoising;Background modeling is carried out using mixed Gaussian, generates the background mould of preset quantity
Type;Moving object detection is carried out to the pretreated current frame image according to the background model of the preset quantity, is obtained
The characteristics of image of each moving target and the CPU is sent in the current frame image.
4. equipment according to claim 2, which is characterized in that the CPU is used for according to each movement mesh to be tracked
Target position is analyzed, generate the corresponding light deflection parameter of each moving target to be tracked, focus adjustment parameter with
And acquisition parameters, motion target tracking instruction is generated according to the light deflection parameter, focus adjustment parameter and acquisition parameters;
Each described corresponding point of mirror camera system of moving target to be tracked is determined according to preset position corresponding relationship;It will
The each motion target tracking instruction generated, which respectively corresponds to be transmitted to, determining described divides mirror camera system.
5. equipment according to claim 1, which is characterized in that the acousto-optic modulator includes longitudinal acousto-optic modulator and cross
To acousto-optic modulator, the longitudinal direction acousto-optic modulator, the lateral acousto-optic modulator and the high-definition camera are arranged successively, institute
It states longitudinal acousto-optic modulator and the lateral acousto-optic modulator is electrically connected with the controller respectively;
The longitudinal direction acousto-optic modulator receives the motion target tracking instruction, is carried according to motion target tracking instruction
The light of the light deflection parameter self-corresponding moving target to be tracked in future longitudinally reflexes to the lateral acousto-optic modulator;
The transverse direction acousto-optic modulator receives the motion target tracking instruction, is carried according to motion target tracking instruction
Light deflection parameter laterally reflexes to the light after longitudinal reflection in the high-definition camera.
6. equipment according to claim 5, which is characterized in that it is described that mirror camera system is divided to further include liquid crystal lens, it is described
Longitudinal acousto-optic modulator, the lateral acousto-optic modulator, the liquid crystal lens and the high-definition camera are arranged successively;The liquid
Brilliant lens are electrically connected with the controller;The motion target tracking instruction carries focus adjustment parameter;
The liquid crystal lens receive the motion target tracking instruction, the focal length tune carried according to motion target tracking instruction
It saves parameter and carries out focus adjustment;Light after the laterally reflection passes through the liquid crystal lens and enters the high-definition camera.
7. equipment according to claim 1, which is characterized in that the acousto-optic modulator includes lateral acousto-optic modulator and indulges
It is described that mirror camera system is divided to further include liquid crystal lens to acousto-optic modulator, the transverse direction acousto-optic modulator, longitudinal acousto-optic tune
Device, the liquid crystal lens and the high-definition camera processed are arranged successively;The transverse direction acousto-optic modulator, longitudinal acousto-optic modulation
Device and the liquid crystal lens are electrically connected with the controller respectively.
8. equipment according to claim 6, which is characterized in that described that mirror camera system is divided to further include liquid crystal lens installation
Frame, high-definition camera mounting rack, lateral acousto-optic modulator mounting rack and longitudinal acousto-optic modulator mounting rack;
The liquid crystal lens mounting rack, the high-definition camera mounting rack, the lateral acousto-optic modulator mounting rack and described vertical
Regulating element is respectively arranged on acousto-optic modulator mounting rack;
By the regulating element adjust respectively the liquid crystal lens, the high-definition camera, the lateral acousto-optic modulator and
The installation site of the longitudinal direction acousto-optic modulator.
9. a kind of multiple mobile object captures and tracking characterized by comprising
Panorama ambient image is acquired, multiple moving targets to be tracked are determined according to the panorama ambient image;
It generates and is instructed with multiple one-to-one motion target trackings of moving target to be tracked;The motion target tracking refers to
Order carries light deflection parameter and acquisition parameters;
Multiple motion target tracking instructions are transmitted separately to corresponding point of mirror camera system;Wherein, image acquisition region
Interior designated position, which is respectively arranged with, multiple described divides mirror camera system;Described point of mirror camera system includes acousto-optic modulator and height
Clear camera;
The acousto-optic modulator in described point of mirror camera system is electrically connected with the controller, receives the motion target tracking
Instruction, the light deflection parameter carried according to motion target tracking instruction is to the next self-corresponding moving target to be tracked
Light reflected, the light is reflexed in the high-definition camera, it is described that high definition described in mirror camera system is divided to take the photograph
Picture head is electrically connected with the controller, is received the motion target tracking instruction, is instructed and carried according to the motion target tracking
Acquisition parameters the corresponding moving target to be tracked is shot when camera lens is directed toward constant, obtain it is corresponding it is described to
The image of pursuit movement target;
Sorting processing is carried out to the image of each moving target to be tracked, is generated and each moving target one to be tracked
One corresponding motion profile video.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610121742.9A CN105791686B (en) | 2016-03-03 | 2016-03-03 | Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610121742.9A CN105791686B (en) | 2016-03-03 | 2016-03-03 | Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105791686A CN105791686A (en) | 2016-07-20 |
CN105791686B true CN105791686B (en) | 2019-03-15 |
Family
ID=56387902
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610121742.9A Active CN105791686B (en) | 2016-03-03 | 2016-03-03 | Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105791686B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106791294A (en) * | 2016-11-25 | 2017-05-31 | 益海芯电子技术江苏有限公司 | Motion target tracking method |
TWI690207B (en) * | 2018-05-29 | 2020-04-01 | 圓展科技股份有限公司 | Method for object tracking |
CN109040664A (en) * | 2018-06-01 | 2018-12-18 | 深圳市商汤科技有限公司 | video stream processing method and device, electronic equipment and storage medium |
CN111199203A (en) * | 2019-12-30 | 2020-05-26 | 广州幻境科技有限公司 | Motion capture method and system based on handheld device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1658670A (en) * | 2004-02-20 | 2005-08-24 | 上海银晨智能识别科技有限公司 | Intelligent tracking monitoring system with multi-camera |
CN1976445A (en) * | 2006-12-15 | 2007-06-06 | 上海鼎业电子科技有限公司 | Multi-camera monitoring system based on three-dimensional video frequency dynamic tracking and tracking method thereof |
CN103020990A (en) * | 2012-12-06 | 2013-04-03 | 华中科技大学 | Moving object detecting method based on graphics processing unit (GPU) |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9256117B2 (en) * | 2011-10-07 | 2016-02-09 | L-3 Communications Cincinnati Electronics Corporation | Panoramic imaging systems comprising rotatable mirrors for image stabilization |
US10082664B2 (en) * | 2013-09-23 | 2018-09-25 | Samsung Electronics Co., Ltd. | Tracking optics for a mobile device |
-
2016
- 2016-03-03 CN CN201610121742.9A patent/CN105791686B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1658670A (en) * | 2004-02-20 | 2005-08-24 | 上海银晨智能识别科技有限公司 | Intelligent tracking monitoring system with multi-camera |
CN1976445A (en) * | 2006-12-15 | 2007-06-06 | 上海鼎业电子科技有限公司 | Multi-camera monitoring system based on three-dimensional video frequency dynamic tracking and tracking method thereof |
CN103020990A (en) * | 2012-12-06 | 2013-04-03 | 华中科技大学 | Moving object detecting method based on graphics processing unit (GPU) |
Also Published As
Publication number | Publication date |
---|---|
CN105791686A (en) | 2016-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105592269B (en) | Moving target captures and tracking equipment and moving target capture and tracking | |
CN105791686B (en) | Multiple mobile object captures and tracking equipment and multiple mobile object capture and tracking | |
CN105513087A (en) | Laser aiming and tracking equipment and method for controlling same | |
US20170098117A1 (en) | Method and apparatus for robustly collecting facial, ocular, and iris images | |
CN105210368B (en) | Background difference extraction element and background difference extracting method | |
Ye et al. | Universal semantic segmentation for fisheye urban driving images | |
CN108510520B (en) | A kind of image processing method, device and AR equipment | |
CN112785628B (en) | Track prediction method and system based on panoramic view angle detection tracking | |
CN108198199A (en) | Moving body track method, moving body track device and electronic equipment | |
CN103617631B (en) | A kind of tracking based on Spot detection | |
Liu et al. | A cloud infrastructure for target detection and tracking using audio and video fusion | |
CN108184062B (en) | High-speed tracking system and method based on multi-level heterogeneous parallel processing | |
Sajjadi et al. | Rust: Latent neural scene representations from unposed imagery | |
Baisware et al. | Review on recent advances in human action recognition in video data | |
Hu et al. | Video object detection from one single image through opto-electronic neural network | |
CN205490869U (en) | Motion target is caught and tracking device | |
Baudron et al. | E3d: event-based 3d shape reconstruction | |
Gao et al. | SuperFast: 200$\boldsymbol {\times} $ Video Frame Interpolation via Event Camera | |
Ge et al. | Metabev: Solving sensor failures for bev detection and map segmentation | |
CN205490868U (en) | Target of doing more physical exercises is caught and tracking device | |
Faruqui et al. | Trackez: an iot-based 3d-object tracking from 2d pixel matrix using mez and fsl algorithm | |
Gao et al. | Sparse dense fusion for 3d object detection | |
Zhang et al. | Video extrapolation in space and time | |
CN205486308U (en) | Laser aims and tracking device | |
CN110134222A (en) | A kind of VR shows positioning sighting system and its positioning method of sight |
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: 100088 1, 111, 4 Building 44, North Third Ring Road, Haidian District, Beijing. Applicant after: Sima great (Beijing) Intelligent Systems Ltd Address before: 100080 Beijing, Haidian District, Shanghai 26 Road, 10 floor, 1019 room. Applicant before: Beijing Zhiguang Boyuan Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |