CN212936030U

CN212936030U - Image shooting system for reducing reflection and expanding visual field through multi-camera combined shooting

Info

Publication number: CN212936030U
Application number: CN202022099218.0U
Authority: CN
Inventors: 杜黎
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-09-23
Filing date: 2020-09-23
Publication date: 2021-04-09
Anticipated expiration: 2030-09-23

Abstract

The utility model discloses a many cameras combination is shot and is reduced reflection of light and enlarge image shooting system in the field of vision to the less problem of single camera shooting image reflection of light sum shooting field of vision scope, provides following technical scheme, and a many cameras combination is shot and is reduced the image shooting system in reflection of light and expansion field of vision. The system comprises a hardware system and an image processing algorithm system which are connected by a plurality of cameras in a combined way. The method can be used for reducing scenes such as light spots generated in shooting of the camera, expansion of shooting visual field or reduction of shooting distance.

Description

Image shooting system for reducing reflection and expanding visual field through multi-camera combined shooting

Technical Field

The utility model relates to a many cameras combination is shot and is reduced reflection of light and enlarge image shooting system in field of vision, a whole set of system that software and hardware including many cameras combination hardware and image processing algorithm combines.

Background

With the development of artificial intelligence and computer vision, the utilization of images is more and more popular, and the camera shooting target is often accompanied by the limitations of reflection, shooting visual field range, shooting deformation and the like, so that the integrity of the image and the shooting expectation cannot be reached.

When an object target is shot by using a single camera to form an image, reflection light is easily formed in scenes such as smooth appearance, plastic coating or strong light sources, light spots exist on the image, and key information can be lost or the image is incomplete.

When the shooting range is required when a single camera is used for shooting a target to form an image, the wider the shooting visual field of the camera is, the easier the image is to deform by using the ultra-wide-angle lens, and the wide angle is also limited. And the area of the shot object needs to be complete, so that a sufficient distance between the camera and the shot object must be ensured. Some of these require a closer range or smaller volume.

The following mentions that reducing the reflection and enlarging the field of view are relative concepts, as opposed to the effect of a single camera.

SUMMERY OF THE UTILITY MODEL

The in-process image reflection of light to overcoming among the prior art camera shooting target, the defect that camera and target distance are far away, the utility model provides an adopt the collection of many cameras to shoot the image mode, use image processing algorithm to align many pictures of many cameras shooting to synthesize into a picture to this solution image reflection of light enlarges the shooting visual angle.

The hardware device comprises a camera base, a plurality of cameras (the number of the cameras is more than or equal to 2), a chip, a storage device, a data communication interface and a power interface. The cameras are combined, and a gap with a certain distance is reserved between the cameras, so that the complementary effect on the shot targets between the cameras can be ensured, and the multiple shot images are not required to be completely identical or overlapped. The utility model discloses a design, simple structure is practical, and image algorithm's cooperation has very much the practicality.

The utility model provides a technical scheme that its technical problem adopted:

a multi-camera combined image shooting system capable of reducing reflection and expanding visual field comprises a hardware system and an image processing algorithm system, wherein the hardware system is connected with a host through a multi-camera combination, the hardware system is connected with the host through the multi-camera combination and comprises a plurality of cameras and the host, the cameras are arranged at any angles and at any relative positions, the number of the cameras is more than or equal to 2, the cameras are all electrically connected with the host, the host hardware comprises a CPU, a RAM, a memory, a GPU/NPU and a TPU, a vision algorithm module is arranged in the host, the vision algorithm module comprises an image preprocessing module, an image analysis module, an image alignment module and an image combination module, the input end of the image preprocessing module is electrically connected with the host, the output end of the image preprocessing module is electrically connected with the image analysis module, and the output end of the image analysis module is electrically connected with the image alignment module, the image alignment module is electrically connected with the input end of the image combination module, and the output end of the image combination module is electrically connected with the host.

1. The multiple cameras shoot the target at the same time to form multiple pictures;

2. combining a plurality of pictures into one picture by using an image processing algorithm, so that the human can not visually distinguish whether the picture is shot by one camera or a plurality of cameras as much as possible;

3. the pictures shot by the cameras are overlapped or the shot objects can be seamlessly connected;

4. image processing and an image alignment algorithm are used, and image splicing is carried out on a plurality of images;

5. multiple cameras shoot to solve the problem of light reflection;

6. the shooting range of the target shot by the multiple cameras is larger than that of a shooting range shot by the same single camera;

7. the shooting of many cameras and single camera shoot same target, and many cameras are closer with shooting target distance.

To sum up, the utility model discloses following beneficial effect has:

1. the picture is taken, so that the reflection is avoided, and the loss or incompleteness of effective information of the picture is reduced;

2. the utility model can enlarge the field of vision for taking pictures;

3. the camera and the shooting target can be shot in a closer distance, and a smaller physical space is needed;

4. the camera is general camera, and many cameras reduce the hardware cost than single camera under the same effect.

Drawings

FIG. 1 is a schematic view of two cameras with enlarged visual fields;

reference numerals: camera 1, light source 2, camera 3, base 4, shooting target 5, shooting target 6, shooting distance 7, shooting distance 8, shooting range 9, shooting range 10, shooting range 11

FIG. 2 is a schematic view of an enlarged field of view of three cameras;

reference numerals: camera 1, camera 2, camera 3, light source 4, light source 5, base 6, shooting target 7, shooting target 8, shooting distance 9, shooting distance 10, shooting range 11, shooting range 12, shooting range 13, shooting range 14

FIG. 3 is a schematic view of two cameras for reducing reflection;

reference numerals: camera 1, light source 2, camera 3, base 4, light source 5, facula 6, shooting target 7, facula 8

FIG. 4 is a schematic view of three cameras to reduce reflections;

reference numerals: camera 1, light source 2, camera 3, light source 4, camera 5, base 6, light source 7, facula 8, shooting target 9, facula 10

FIG. 5 is a schematic view of the overall structure;

FIG. 6 is a schematic diagram of an embodiment.

Detailed Description

The following is further detailed by way of specific embodiments:

in the description of the present invention, it should be noted that, unless explicitly stated or limited otherwise, the terms "interface," "connection" and "connection" are to be construed broadly, e.g., as a fixed connection, a detachable connection, or an integral connection; the connection can be mechanical connection, electrical connection or logic connection between modules; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art.

In the description of the present invention, a plurality of means are one or more, a plurality of means are two or more, and the terms greater than, less than, exceeding, etc. are understood as not including the number, and the terms greater than, less than, within, etc. are understood as including the number.

The camera refers to a common camera, and includes but is not limited to a CMOS camera, a CCD camera, an infrared camera, and the like, which generate images. The shooting distance refers to a distance between a shooting target and the camera. The combination of a plurality of cameras is an arbitrary combination in space, and is not necessarily on a line or a horizontal plane. The meaning of the image is that the image comprises a static image and a dynamic image, and the utility model discloses do not distinguish. The image algorithm means that the sum of a series of algorithms such as image detection, image recognition, image alignment and the like is a general term. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.

Fig. 1 is an enlarged view of two cameras, and a photographic subject 5 and a photographic subject 6 are completely the same photographic subject. The shooting range 9 is the shooting range of the camera 1, the shooting range 10 is the shooting range of the camera 3, and the images shot by the camera 1 and the camera 3 are combined into one image by using an image algorithm, namely the shooting range 9 and the shooting range 10 completely comprise and are more than or equal to the shooting target 5 and the shooting distance 7 of the shooting target. If the shooting of the shooting target 6 by the single-camera 1 is complete and the shooting range 11 completely includes and is greater than or equal to the shooting target 6, a longer shooting distance is needed than the single-camera 1, and the shooting distance is the shooting distance 8. It is apparent that the photographing distance 8 is greater than the photographing distance 7.

Fig. 2 is a schematic view of an enlarged view of three cameras, which is the same as the two cameras and is the same as the three cameras.

Fig. 3 is a schematic view of reducing light reflection of two cameras, a camera 1 and a camera 3 shoot a shooting target 7, a light spot 6 and a light spot 8 are formed on the shooting target 7 by a light source 2 and a light source 5, and the light spot 6 and the light spot 8 are in the shooting range of the camera 1 and the camera 3, so that a picture is formed by using an image algorithm on a picture shot by the camera 1 and a picture shot by the camera 3, and the picture can reduce or eliminate the light spot 6 and the light spot 8.

Fig. 4 is a schematic view of three cameras for reducing reflection, which is the same as the principle of the two cameras in fig. 3, and the principle of more than or equal to three cameras is the same.

Referring to fig. 5 and 6, the present invention includes two parts, namely a hardware multi-camera combination system and an image algorithm software system.

Hardware camera combined system, the arbitrary angle of a plurality of cameras and arbitrary relative position, a plurality of cameras quantity should be more than or equal to 2 to directly link to each other in host computer hardware, the multiple form of camera outward appearance form, with camera module or with shell camera etc. do not restrict. The host hardware comprises a CPU, a RAM, a memory, a GPU/NPU/TPU or a connecting interface which can be connected with host hardware equipment, the memory and the GPU/NPU/TPU are equipped according to scenes, and the GPU/NPU/TPU is mainly used for algorithm calculation and algorithm acceleration. Host types include, but are not limited to, intelligent modules, computers, embedded terminals, single-chip computers, mobile devices, and servers. The fixed support of camera to and whether the shell, whether have the exposure lamp, these are as non-core parts, do not influence the implementation of whole function.

The image algorithm software system comprises the acquisition of image data of each camera and the synchronous or asynchronous selection of each camera image at the same time, and performs image processing on a plurality of images to combine the plurality of images.

The above description is only the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution and the improvement concept of the present invention within the technical scope disclosed in the present invention.

Claims

1. The utility model provides a many cameras combination is shot and is reduced reflection of light and enlarge image shooting system in field of vision which characterized in that: the system comprises a hardware system and an image processing algorithm system, wherein the hardware system is connected with a host through a multi-camera combination, the hardware system is connected with the host through the multi-camera combination comprises a plurality of cameras and the host, the cameras have any angles and any relative positions, the number of the cameras is more than or equal to 2, the cameras are all electrically connected with the host, the host hardware comprises a CPU (central processing unit), a RAM (random access memory), a storage, a GPU (graphic processing unit)/NPU (non-graphics processing unit) and a TPU (thermoplastic polyurethane), a vision algorithm module is arranged in the host, the vision algorithm module comprises an image preprocessing module, an image analysis module, an image alignment module and an image combination module, the input end of the image preprocessing module is electrically connected with the host, the output end of the image preprocessing module is electrically connected with the image analysis module, the output end of the image analysis module is electrically connected with the image alignment module, and the input end of the image combination, the output end of the image combination module is electrically connected with the host.

2. The system of claim 1, wherein the multiple cameras are configured to capture reduced reflections and an enlarged field of view of the image capture system, wherein: the common camera is used for shooting a plurality of images by combining a plurality of cameras, and the images are combined into one picture by using the images to perform image algorithm processing.

3. The multi-camera combined image capturing system of claim 2, wherein the multi-camera combined image capturing system is characterized in that: the reflection of light can be reduced to many cameras shooting combination for a picture.

4. The multi-camera combined image capturing system of claim 3, wherein the multi-camera combined image capturing system is characterized in that: the shooting field of vision can be enlarged by shooting and combining multiple cameras into one picture.

5. The multi-camera combined image capturing system of claim 4, wherein the multi-camera combined image capturing system is characterized in that: the requirement of physical space can be reduced or the shooting distance can be shortened by shooting and combining multiple cameras into one picture.