Camera-attached length marker equipment for evaluating depth recognition sensor usability according to operating environment and measuring method using the same

Abstract

A camera-mounted length marker device for evaluating the usability of a depth recognition sensor according to an operating environment and a measurement method using the same are provided. A depth recognition sensor evaluation method according to an embodiment of the present invention generates a depth image by photographing an evaluation device that marks different depths within the FOV of the depth recognition sensor, wherein one end of the depth recognition sensor is mounted on the depth recognition sensor and the device is photographed to generate a depth image. The depth recognition sensor is then evaluated based on the generated depth image. By doing so, a depth recognition sensor that satisfies the target distance resolution at the main operating distance under the application environment can be selected and utilized.

Description

Technology Field

[0001] The present invention relates to the evaluation and operation of depth sensing sensors, and more specifically, to a method for evaluating the performance of a distance sensing sensor by measuring the distance resolution in an actual usage distance range, and to an apparatus and system for the same. Background Technology

[0003] Figures 1 and 2 show RGB color images and corresponding depth (distance) images. In fields requiring 3D information, depth sensing sensors are used to estimate the distance of a location and utilize it.

[0004] Representative depth sensing sensors include Microsoft's Azure Kinect and Intel's RealSense series. It is necessary to select the appropriate depth sensing sensor from among these based on the operating environment.

[0005] Specifically, after determining in advance the distance and depth range required for the application field, as well as the required resolution and FOV (Field of View, sensor recognition range in the height-width-diagonal area), the selection is made using the distance (depth) recognition area and resolution and FOV data provided by the manufacturer.

[0006] However, this is limited to merely utilizing information provided by the manufacturer, and the user does not evaluate the distance (depth) recognition area and resolution. As shown in Fig. 3, only additional color images are used for correction in the selected camera.

[0007] However, since the actual operating environment of depth sensing sensors differs significantly from the environment provided by the manufacturer (light, air, temperature, etc.), it is necessary to evaluate the depth and distance recognition resolution performance of the depth sensing sensors in actual operating environments. The problem to be solved

[0009] The present invention has been devised to solve the aforementioned problems, and the objective of the present invention is to provide a method for quantitatively evaluating which type of camera to select for actual environmental application among a number of depth sensing cameras released on the market, as well as a mechanism and system for this purpose. means of solving the problem

[0011] A depth recognition sensor evaluation mechanism according to one embodiment of the present invention for achieving the above objective includes: a frame having one end mounted on a depth recognition sensor; and a marker unit coupled to the tardin of the frame and marking different depths within the Field of View (FOV) of the depth recognition sensor.

[0012] The cover part can be joined at the other end of the frame in a direction perpendicular to the frame.

[0013] The marker can be located in the center of the FOV of the depth recognition sensor.

[0014] The marker may include a first marker for indicating a depth equal to the main usage distance of the depth recognition sensor.

[0015] The marker may further include a second marker for marking a depth spaced apart from the first marker by a target distance resolution.

[0016] If the depth indicated by the first marker and the depth indicated by the second marker are distinguished and recognized by the depth recognition sensor, the depth recognition sensor can be evaluated as satisfying the target distance resolution at the main application distance.

[0017] If the depth indicated by the first marker and the depth indicated by the second marker are not distinguished and recognized by the depth recognition sensor, the depth recognition sensor may be evaluated as not satisfying the target distance resolution at the main application distance.

[0018] The second label may be multiple.

[0019] The depths marked by multiple second markers may be different from each other.

[0020] According to another aspect of the present invention, a depth recognition sensor evaluation system is provided, characterized by comprising: an evaluation mechanism mounted on a depth recognition sensor and marking different depths within the FOV of the depth recognition sensor on a tardin; and an image processing device that evaluates the depth recognition sensor based on a depth image generated from the depth recognition sensor mounted on the evaluation mechanism.

[0021] According to another aspect of the present invention, a depth recognition sensor evaluation method is provided, characterized by comprising: a step of generating a depth image by photographing an evaluation mechanism, one end of which is mounted on the depth recognition sensor and which marks different depths within the FOV of the depth recognition sensor; and a step of evaluating the depth recognition sensor based on the generated depth image by an image processing system.

[0022] According to another aspect of the present invention, a depth recognition sensor evaluation method is provided, comprising: a step in which a depth recognition sensor photographs an evaluation mechanism to generate a depth image; and a step in which an image processing system evaluates the depth recognition sensor based on the generated depth image; wherein the evaluation mechanism displays depths according to a resolution set at a distance set by a user. Effects of the invention

[0024] As described above, according to the embodiments of the present invention, by utilizing an evaluation mechanism that indicates different depths within the FOV of a depth sensing sensor, it is possible to select and utilize a depth sensing sensor that satisfies the target distance resolution at the main usage distance under the application environment. Brief explanation of the drawing

[0026] FIGS. 1 and FIGS. 2 are drawings illustrating an RGB color image and a corresponding depth image, Figure 3 shows a conventional camera image correction process, FIG. 4 is a drawing provided for explaining the process of a depth recognition sensor evaluation method according to an embodiment of the present invention. FIG. 5 is a drawing illustrating a depth recognition sensor evaluation mechanism according to an embodiment of the present invention. FIG. 6 is a drawing illustrating the detailed structure of the cover section. FIG. 7 is a drawing provided for explaining depth images generated by a depth recognition sensor and the evaluation process through them. FIG. 8 is a diagram illustrating the configuration of a depth recognition sensor evaluation system in another embodiment of the present invention. Specific details for implementing the invention

[0027] The present invention will be described in more detail below with reference to the drawings.

[0028] An embodiment of the present invention presents a camera-mounted length marker device for evaluating the usability of depth recognition sensors according to the operating environment, and a measurement method using the same. This is a technology that performs performance evaluation by measuring the distance resolution of multiple depth (distance) sensors in the actual distance range in which they are used.

[0029] FIG. 4 is a diagram provided to explain the process of a depth recognition sensor evaluation method according to an embodiment of the present invention. As illustrated, the depth recognition sensor evaluation method according to an embodiment of the present invention comprises a utilization indicator selection step (S10), an evaluation mechanism installation step (S20), a depth image resolution verification step (S30), and a camera selection step (S40). Each step is described in detail below one by one.

[0031] 1) Selection of Utilization Indicators (S10)

[0032] This is the process of selecting the primary operating distance (ℓ) and target distance resolution (δ) of the depth sensing sensor based on the environment in which the user utilizes the depth sensing sensor. The primary operating distance (ℓ) is the distance at which the object requiring distance (depth) recognition is primarily located, and the target distance resolution (δ) is the depth resolution of the depth sensing sensor.

[0034] 2) Evaluation mechanism installation stage (S20)

[0035] This is a process of installing an evaluation mechanism on a depth sensing sensor to evaluate whether the depth sensing sensor satisfies the main utilization distance (ℓ) and target distance resolution (δ) set above.

[0036] FIG. 5 is a drawing illustrating a depth recognition sensor evaluation mechanism according to an embodiment of the present invention. FIG. 5 is a drawing showing the evaluation mechanism installed on the side of a depth recognition sensor (50) as viewed from above. As illustrated, the evaluation mechanism according to an embodiment of the present invention is configured to include a frame (110) and a label (120).

[0037] The frame (110) is configured to be mounted and fixed to the side of the depth recognition sensor (50) and corresponds to the body of the evaluation mechanism. The length of the frame (110) is determined based on the main usage distance (ℓ) of the depth recognition sensor (50).

[0038] The indicator (120) is connected to the other end of the frame (110) in a direction perpendicular to the frame (110). The indicator (120) is configured to indicate different depths within the Field of View (FOV) of the depth recognition sensor (50). The length of the indicator (120) is determined to be a length that allows it to be positioned in the center of the FOV of the depth recognition sensor (50).

[0039] FIG. 6 illustrates an enlarged view of the marker section (120) shown in FIG. 5. As shown, the marker section (120) includes a usable distance marker section (121) and a distance resolution marker section (122).

[0040] The usable distance marker (121) is configured to indicate a depth equal to the main usable distance (ℓ) to the depth recognition sensor (50). That is, the distance from the depth recognition sensor (50) to the usable distance marker (121) is made to be the main usable distance (ℓ).

[0041] The distance resolution indicator (122) is configured to indicate a depth separated from the usable distance indicator (121) by a target distance resolution (δ). That is, the depth of the usable distance indicator (121) and the depth of the distance resolution indicator (122) are separated by a target distance resolution (δ).

[0043] 3) Check depth image resolution (S30)

[0044] This is a process of generating a depth image by photographing the label portion (120) of the evaluation mechanism with a depth recognition sensor (50), and evaluating the performance of the depth recognition sensor (50) by analyzing the generated depth image.

[0045] As shown on the left side of FIG. 7, in the depth image generated by the depth recognition sensor (50), if the depth indicated by the utilization distance indicator (121) and the depth indicated by the distance resolution indicator (122) are distinguished and recognized, the depth recognition sensor (50) is evaluated as satisfying the target distance resolution (δ) at the main utilization distance (ℓ).

[0046] On the other hand, as shown in the center of FIG. 7, if the depth indicated by the distance indicator (121) and the depth indicated by the distance resolution indicator (122) are not distinguished and recognized in the depth image generated by the depth recognition sensor (50), the depth recognition sensor (50) is evaluated as not satisfying the target distance resolution (δ) at the main distance (ℓ).

[0048] 4) Camera Selection (S40)

[0049] In the preceding evaluation, if the depth recognition sensor (50) is evaluated to satisfy the target distance resolution (δ) at the main usage distance (ℓ), the depth recognition sensor (50) is selected and utilized to implement the system / service.

[0050] On the other hand, if the depth recognition sensor (50) is evaluated in the preceding evaluation as not satisfying the target distance resolution (δ) at the main usage distance (ℓ), the depth recognition sensor (50) is replaced with another one, and then the process is repeated starting from ‘2) evaluation mechanism installation step (S20)’.

[0052] FIG. 7 is a diagram illustrating the configuration of a depth recognition sensor evaluation system in another embodiment of the present invention. In an embodiment of the present invention, the depth recognition sensor evaluation system is configured to include an evaluation mechanism (100) and an image processing system (200) as illustrated.

[0053] As the evaluation mechanism (100) has been described above, a detailed explanation is omitted. The image processing system (200) is a system that automatically evaluates the performance of the depth recognition sensor (50) by processing and analyzing a depth image generated by the depth recognition sensor (50) capturing the marker portion (120) of the evaluation mechanism (100).

[0054] So far, a camera-mounted length marker device for evaluating the usability of depth recognition sensors according to operating environments and a measurement method using the same have been described in detail with reference to preferred embodiments.

[0055] In the above embodiment, it is assumed that there is one distance resolution indicator (122), but it can be modified as an exemplary case. For instance, the number of distance resolution indicators (122) can be implemented as two or more, with different depths for each indicator, so that multiple target distance resolutions can be evaluated at once.

[0056] According to an embodiment of the present invention, a quantitative evaluation can be made regarding which type of camera to select for actual environment application among a number of depth (distance) recognition cameras available on the market, and the optimal sensor can be selected according to the various purposes for which the sensor (camera) is used, and the sensor selection can also be made in accordance with environmental changes.

[0057] The technical concept of the present invention can be applied to various fields, including fields where depth (distance) recognition sensors are used, picking robot fields, and autonomous driving fields.

[0058] Meanwhile, it goes without saying that the technical concept of the present invention may also be applied to a computer-readable recording medium containing a computer program that enables the device and method according to the present embodiment to perform their functions. Furthermore, the technical concept according to various embodiments of the present invention may be implemented in the form of computer-readable code recorded on a computer-readable recording medium. A computer-readable recording medium may be any data storage device that can be read by a computer and store data. For example, a computer-readable recording medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, etc. Additionally, computer-readable code or a program stored on a computer-readable recording medium may be transmitted through a network connected between computers.

[0059] Furthermore, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. Various modifications are possible by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention. Explanation of the symbols

[0061] 50: Depth sensing sensor 100: Evaluation body 110 : Frame 120 : Cover section 121 : Usage distance marker 122 : Distance resolution marker 200: Image Processing System

Claims

Claim 1 A depth recognition sensor evaluation mechanism comprising: a frame having one end mounted on a depth recognition sensor; and a marker unit coupled to the other end of the frame and indicating different depths within the Field of View (FOV) of the depth recognition sensor; wherein the marker unit comprises: a first marker unit for indicating a depth equal to the main utilization distance of the depth recognition sensor; and a second marker unit for indicating a depth spaced apart from the first marker unit by a target distance resolution; wherein the first marker unit and the second marker unit are integrally formed, the second marker unit is formed at one end of the first marker unit, and the frame has one end mounted on the depth recognition sensor. Claim 2 A depth recognition sensor evaluation mechanism according to claim 1, wherein the label is coupled at the other end of the frame in a direction perpendicular to the frame. Claim 3 A depth recognition sensor evaluation mechanism according to claim 2, wherein the label is located at the center of the FOV of the depth recognition sensor. Claim 4 delete Claim 5 delete Claim 6 A depth recognition sensor evaluation mechanism according to claim 1, characterized in that when the depth indicated by the first indicator and the depth indicated by the second indicator are distinguished and recognized by the depth recognition sensor, the depth recognition sensor is evaluated as satisfying the target distance resolution at the main application distance. Claim 7 A depth recognition sensor evaluation mechanism according to claim 1, characterized in that if the depth indicated by the first indicator and the depth indicated by the second indicator are not distinguished and recognized by the depth recognition sensor, the depth recognition sensor is evaluated as not satisfying the target distance resolution at the main application distance. Claim 8 A depth recognition sensor evaluation mechanism according to claim 1, wherein the second label is a plurality of individuals. Claim 9 A depth recognition sensor evaluation mechanism according to claim 8, characterized in that the depths indicated by a plurality of second indicators are different from each other. Claim 10 A depth recognition sensor evaluation system comprising: an evaluation mechanism having one end mounted on a depth recognition sensor and the other end marking different depths within the FOV of the depth recognition sensor; and an image processing device that evaluates the depth recognition sensor based on a depth image generated from the depth recognition sensor equipped with the evaluation mechanism; wherein the evaluation mechanism includes a first marking part for marking a depth equal to the main utilization distance of the depth recognition sensor; and a second marking part for marking a depth spaced apart from the first marking part by a target distance resolution; wherein the first marking part and the second marking part are integrally formed, the second marking part is formed at one end of the first marking part, and the evaluation mechanism has one end mounted on the depth recognition sensor. Claim 11 A depth recognition sensor evaluation method comprising: a step of generating a depth image by photographing an evaluation mechanism, one end of which is mounted on the depth recognition sensor and the other end of which indicates different depths within the FOV of the depth recognition sensor; and a step of an image processing system evaluating the depth recognition sensor based on the generated depth image; wherein the evaluation mechanism comprises: a first indicator for indicating a depth equal to the main utilization distance of the depth recognition sensor; and a second indicator for indicating a depth separated from the first indicator by a target distance resolution; wherein the first indicator and the second indicator are integrally formed, the second indicator is formed at one end of the first indicator, and the evaluation mechanism is characterized in that one end of which is mounted on the depth recognition sensor. Claim 12 A depth recognition sensor evaluation method comprising: a step of a depth recognition sensor capturing an evaluation mechanism to generate a depth image; and a step of an image processing system evaluating the depth recognition sensor based on the generated depth image; wherein the evaluation mechanism comprises: a first marker for indicating a depth equal to the main usage distance of the depth recognition sensor; and a plurality of second markers for indicating depths according to a resolution set at a distance set by a user from the first marker; wherein the first marker and the second markers are integrally formed, the second markers are formed at one end of the first marker, and the evaluation mechanism is characterized in that one end is mounted on the depth recognition sensor.

Images