CN213585989U

CN213585989U - Video acquisition device for pedestrian re-identification

Info

Publication number: CN213585989U
Application number: CN202023100215.0U
Authority: CN
Inventors: 陆光建; 徐增敏; 李麒麟; 言姜毅; 宋鉴伟; 陆游尤
Original assignee: Guilin University of Electronic Technology
Current assignee: Guilin University of Electronic Technology
Priority date: 2020-12-21
Filing date: 2020-12-21
Publication date: 2021-06-29
Anticipated expiration: 2030-12-21

Abstract

The utility model discloses a video acquisition device for pedestrian weight identification, wherein a motor is fixedly connected with a fixed frame and is positioned below the fixed frame, a first rotating shaft is movably connected with the motor and is positioned below the first rotating shaft, a driving wheel is fixedly connected with the first rotating shaft and is positioned below the first rotating shaft, two driven wheels are respectively engaged with the driving wheel and are symmetrically arranged at both sides of the driving wheel, two second rotating shafts are respectively fixedly connected with the corresponding driven wheels and are respectively positioned above the corresponding driven wheels, two main cameras are respectively fixedly connected with the fixed frame and are symmetrically arranged at both sides of the fixed frame, two auxiliary cameras are respectively fixedly connected with the corresponding second rotating shafts and are respectively positioned above the second rotating shafts, the auxiliary camera is switched into an overlapping acquisition mode, so that the workload of the main camera is reduced, and the acquisition precision is ensured.

Description

Video acquisition device for pedestrian re-identification

Technical Field

The utility model relates to a computer identification technical field especially relates to a video acquisition device is used in heavy discernment of pedestrian.

Background

The pedestrian re-identification refers to a process of carrying out similarity matching on pedestrian targets under the monitoring of a plurality of cameras without overlapped visual angles, namely, a pedestrian target is given, the target is found and locked in videos shot by a plurality of cameras at different positions at different moments, only one acquisition end of the conventional video acquisition device is provided, and when the pedestrian flow is too large, too much information is difficult to process by the single acquisition end.

SUMMERY OF THE UTILITY MODEL

An object of the utility model is to provide a video acquisition device is used in heavy discernment of pedestrian aims at solving among the prior art video acquisition device's collection end only one, and when the flow of people was too big, single collection end was difficult to handle the technical problem of too much information.

In order to achieve the above object, the present invention provides a video capture device for pedestrian weight recognition, comprising a fixing frame, a housing, a rotating assembly and a camera assembly, wherein the housing is fixedly connected to the fixing frame and located below the fixing frame, the rotating assembly comprises a motor, a first rotating shaft, a driving wheel, a driven wheel and a second rotating shaft, the motor is fixedly connected to the fixing frame and located below the fixing frame, the first rotating shaft is movably connected to the motor and located below the motor, the driving wheel is fixedly connected to the first rotating shaft and located below the first rotating shaft, the number of the driven wheels is two, the two driven wheels are respectively engaged with the driving wheel and symmetrically arranged at two sides of the driving wheel, the number of the second rotating shafts is two, and the two second rotating shafts are respectively fixedly connected to the corresponding driven wheels, and be located respectively the correspondence the top from the driving wheel, the subassembly of making a video recording includes main camera and supplementary camera, the quantity of main camera is two, two main camera respectively with mount fixed connection to the symmetry set up in the both sides of mount, the quantity of supplementary camera is two, two supplementary camera respectively with correspond second pivot fixed connection, and be located respectively the second pivot top.

The fixing frame comprises a fixing plate and a fixing column, the fixing plate is detachably connected with the fixing column and is positioned above the fixing column, and the fixing column is detachably connected with the shell and is positioned above the shell.

Wherein, the inside wall of casing is provided with the recess.

The second rotating shaft comprises a shaft body and a limiting block, the shaft body is fixedly connected with the driven wheel and is positioned above the driven wheel, and the limiting block is fixedly connected with the shaft body and is positioned in the groove.

The video acquisition device for pedestrian re-identification further comprises a supporting rod, wherein the supporting rod is detachably connected with the shell and is positioned below the shell.

The camera shooting assembly comprises four light shielding plates, wherein the number of the light shielding plates is four, the two light shielding plates are respectively and correspondingly fixedly connected with the main cameras and respectively located above the main cameras, and the other two light shielding plates are respectively and correspondingly fixedly connected with the auxiliary cameras and respectively located above the corresponding auxiliary cameras.

The beneficial effects of the utility model are embodied in: the indoor environment can be arranged on a ceiling through the fixing frame, the outdoor environment can be arranged on the ground through the supporting rod, the two main cameras are symmetrically arranged and used for collecting people coming and going on a road, the auxiliary cameras can increase the collection range, when the flow of people is overlarge, the auxiliary cameras are switched to an overlapping collection mode, the motor rotates to drive the driving wheel to rotate, the driven wheel rotates under the action of meshing, so that the auxiliary cameras rotate along with the second rotating shaft, the two auxiliary cameras are symmetrically arranged and are arranged on two sides of the two main cameras in a crossed mode, the two auxiliary cameras are close to the main cameras, the collection range of the main cameras is overlapped with the range of the auxiliary cameras, the main cameras do not process information of an overlapping collection area any more, and the workload of the main cameras is reduced, the acquisition precision is ensured.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is the utility model relates to a video acquisition device for pedestrian heavy identification's structural schematic diagram.

Fig. 2 is a schematic structural diagram of the rotating assembly of the video capture device for pedestrian re-identification of the present invention.

100-video acquisition device for pedestrian heavy identification, 1-fixed frame, 2-shell, 3-motor, 4-first rotating shaft, 5-driving wheel, 6-driven wheel, 7-second rotating shaft, 8-main camera, 9-auxiliary camera, 10-fixed plate, 11-fixed column, 12-shaft body, 13-limited block, 14-supporting rod and 15-shading plate.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present invention, and should not be construed as limiting the present invention.

In the description of the present invention, it is to be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are merely for convenience of description and simplicity of description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. In addition, in the description of the present invention, "a plurality" means two or more unless specifically limited otherwise.

Referring to fig. 1 and fig. 2, the present invention provides a technical solution: a video acquisition device 100 for pedestrian heavy identification comprises a fixed frame 1, a shell 2, a rotating assembly and a camera shooting assembly, wherein the shell 2 is fixedly connected with the fixed frame 1 and is positioned below the fixed frame 1, the rotating assembly comprises a motor 3, a first rotating shaft 4, a driving wheel 5, a driven wheel 6 and a second rotating shaft 7, the motor 3 is fixedly connected with the fixed frame 1 and is positioned below the fixed frame 1, the first rotating shaft 4 is movably connected with the motor 3 and is positioned below the motor 3, the driving wheel 5 is fixedly connected with the first rotating shaft 4 and is positioned below the first rotating shaft 4, the number of the driven wheels 6 is two, the two driven wheels 6 are respectively meshed with the driving wheel 5 and are symmetrically arranged at two sides of the driving wheel 5, and the number of the second rotating shaft 7 is two, two second pivot 7 respectively with correspond from 6 fixed connection of driving wheel to be located the correspondence respectively from the top of driving wheel 6, the subassembly of making a video recording includes main camera 8 and supplementary camera 9, the quantity of main camera 8 is two, two main camera 8 respectively with 1 fixed connection of mount, and the symmetry set up in the both sides of mount 1, the quantity of supplementary camera 9 is two, two supplementary camera 9 respectively with correspond 7 fixed connection of second pivot, and be located respectively the 7 tops of second pivot.

In this embodiment, the main camera 8 and the auxiliary camera 9 are used as an acquisition end to acquire image data of pedestrians, the image data is transmitted to respective computer ports through a network, a computer is used as a processing end, a computer vision technology is used to determine whether a specific pedestrian exists in an image or a video sequence, the indoor environment can be installed on a ceiling through the fixing frame 1, the outdoor environment can be installed on the ground through the supporting rod 14, the two main cameras 8 are symmetrically arranged and used for acquiring people coming and going on a road, the auxiliary camera 9 can increase an acquisition range, normally collects environmental information outside the road and is used as a general monitoring device, when the processing end finds that the flow of people is too large, the auxiliary camera 9 is converted into an overlapping acquisition mode, the motor 3 rotates to drive the driving wheel 5 to rotate, because the meshing effect, it is rotatory from driving wheel 6, make supplementary camera 9 follows the rotation of second pivot 7, two supplementary camera 9 symmetry sets up, and the cross arrangement is two the both sides of main camera 8, two supplementary camera 9 all to main camera 8 is close to, main camera 8's collection scope with the scope of supplementary camera 9 overlaps, main camera 8 no longer handles the information of overlapping collection region, alleviates main camera 8's work load, has guaranteed the collection precision.

Further, the fixing frame 1 includes a fixing plate 10 and a fixing column 11, the fixing plate 10 is detachably connected to the fixing column 11 and is located above the fixing column 11, and the fixing column 11 is detachably connected to the housing 2 and is located above the housing 2.

In this embodiment, the support rod 14 is removed, the fixing frame 1 can be installed on a ceiling in an indoor environment, and the fixing post 11 is used for connecting the main camera 8 and the housing 2.

Further, the inner side wall of the shell 2 is provided with a groove.

In this embodiment, the limiting block 13 is disposed in the groove, so that the second rotating shaft 7 can only rotate clockwise and counterclockwise and cannot move up and down, and the auxiliary camera 9 is prevented from dropping.

Further, the second rotating shaft 7 comprises a shaft body 12 and a limiting block 13, the shaft body 12 is fixedly connected with the driven wheel 6 and is located above the driven wheel 6, and the limiting block 13 is fixedly connected with the shaft body 12 and is located inside the groove.

Further, the video capture device 100 for pedestrian re-identification further comprises a support rod 14, wherein the support rod 14 is detachably connected with the housing 2 and is located below the housing 2.

In the present embodiment, the support rod 14 is fixed to the ground, and the housing 2 is fixed above the support rod 14, so that it can be used for outdoor installation.

Further, the camera shooting assembly comprises four light shielding plates 15, wherein two of the light shielding plates 15 are respectively and fixedly connected with the corresponding main cameras 8 and respectively located above the main cameras 8, and the other two light shielding plates 15 are respectively and fixedly connected with the corresponding auxiliary cameras 9 and respectively located above the corresponding auxiliary cameras 9.

In the present embodiment, the light shielding plate 15 is disposed above the auxiliary camera 9 and the main camera 8 to prevent strong light from directly irradiating the lens, which results in that the images collected by the auxiliary camera 9 and the main camera 8 are not clear.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims

1. A video acquisition device for pedestrian heavy identification is characterized by comprising a fixing frame, a shell, a rotating assembly and a camera shooting assembly, wherein the shell is fixedly connected with the fixing frame and is positioned below the fixing frame, the rotating assembly comprises a motor, a first rotating shaft, a driving wheel, driven wheels and second rotating shafts, the motor is fixedly connected with the fixing frame and is positioned below the fixing frame, the first rotating shaft is movably connected with the motor and is positioned below the motor, the driving wheel is fixedly connected with the first rotating shaft and is positioned below the first rotating shaft, the number of the driven wheels is two, the two driven wheels are respectively meshed with the driving wheel and are symmetrically arranged on two sides of the driving wheel, the number of the second rotating shafts is two, and the two second rotating shafts are respectively fixedly connected with the corresponding driven wheels, and be located respectively the correspondence the top from the driving wheel, the subassembly of making a video recording includes main camera and supplementary camera, the quantity of main camera is two, two main camera respectively with mount fixed connection to the symmetry set up in the both sides of mount, the quantity of supplementary camera is two, two supplementary camera respectively with correspond second pivot fixed connection, and be located respectively the second pivot top.

2. The video capture device for pedestrian re-identification as claimed in claim 1, wherein the fixing frame comprises a fixing plate and a fixing post, the fixing plate is detachably connected with the fixing post and located above the fixing post, and the fixing post is detachably connected with the housing and located above the housing.

3. The video capture device for pedestrian re-identification as claimed in claim 2 wherein the inner side wall of the housing is provided with a groove.

4. The video capture device for pedestrian re-identification as claimed in claim 3, wherein the second shaft comprises a shaft body and a limiting block, the shaft body is fixedly connected with the driven wheel and located above the driven wheel, and the limiting block is fixedly connected with the shaft body and located inside the groove.

5. The video capture device for pedestrian re-identification as claimed in claim 4, further comprising a support bar detachably connected to the housing and located below the housing.

6. The video capturing device for pedestrian re-identification as claimed in claim 5, wherein the camera assembly includes four light shielding plates, two of the light shielding plates are respectively and fixedly connected to and respectively located above the corresponding main cameras, and the other two of the light shielding plates are respectively and fixedly connected to and respectively located above the corresponding auxiliary cameras.