Length detection method and length detection device
The length detection system addresses the challenge of detecting water levels in regulating ponds by employing a reflective patterned tape and image processing to remotely measure liquid or object lengths, overcoming leaf clogging issues and site visit requirements.
Patent Information
- Application Number
- JP2023080056
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-15
- Publication Date
- 2024-11-27
AI Technical Summary
Conventional methods for detecting water levels in regulating ponds, such as using cameras or AI, face challenges due to leaf clogging, requiring extensive data training and site visits to accurately measure levels.
A length detection system using a reflective patterned tape installed at a site, combined with a camera and image processing, determines the length of liquids or objects by counting visible patterns, allowing remote detection.
Enables easy and accurate detection of liquid or object lengths without site visits, even in conditions where patterns are obscured by fallen leaves, by using reflective materials and image processing to calculate based on pattern counts.
Smart Images

Figure 2024164517000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a length detection method and a length detection device that can detect the height of a liquid surface such as water, the height of a load of objects such as snow, soil, or garbage, or the width of luggage placed in a logistics warehouse, etc. [Background technology]
[0002] A known conventional length detection method is, for example, a method for detecting the water level of a regulating reservoir that temporarily stores rainwater during torrential rain to prevent small-scale flooding in downstream areas (see, for example, Patent Document 1).
[0003] However, in many cases, the water level in the reservoir rises due to clogging caused by fallen leaves, and the above method had the problem that the actual water level could not be determined without going to the site to check. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2005-181165 A Summary of the Invention [Problem to be solved by the invention]
[0005] In order to solve the above problems, it is conceivable to install a camera at the site and detect the water level by checking the camera image. However, if there are piles of fallen leaves, it is difficult to detect the water level using only the camera image.
[0006] In order to solve this problem, a method of automatically calculating the water level of a regulating pond using AI (Artificial Intelligence) technology, which has been rapidly spreading in recent years, is being considered. However, when using AI technology, the system must learn whether the regulating pond is clogged or not, and in doing so, the system must learn the shapes of fallen leaves and the shape of the regulating pond. However, because the shapes of fallen leaves and the shapes of regulating ponds vary widely, this method cannot be realized unless a huge amount of data is learned. Therefore, there is a problem in that it is very difficult to automatically calculate the water level of a regulating pond using AI technology.
[0007] SUMMARY OF THE PRESENT DISCLOSURE In view of the above problems, an object of the present invention is to provide a length detection method and a length detection device that can simply and easily detect length without going to the site. [Means for solving the problem]
[0008] The above object of the present invention can be achieved by the following means. Note that the parentheses indicate reference symbols of the embodiments described below, but the present invention is not limited thereto.
[0009] The length detection method of the invention of claim 1 is characterized in that the number of patterns (e.g., pattern 21 shown in FIG. 3) placed at a predetermined interval at a predetermined location (e.g., orifice M shown in FIG. 1) imaged by an imaging means (e.g., camera 3 shown in FIG. 1) is determined using a predetermined device (e.g., height detection device 4 shown in FIG. 1) (e.g., see step S3 shown in FIG. 4), and the length of the liquid or object is detected according to the determined number of patterns (e.g., pattern 21 shown in FIG. 3) (e.g., see step S4 shown in FIG. 4).
[0010] According to a second aspect of the invention, in the length detection method according to the first aspect, the pattern (for example, the pattern 21 shown in FIG. 3) is formed of a reflective material.
[0011] The length detection device according to the invention of claim 3 includes an image processing means (e.g., an image processing unit 42 shown in FIG. 2) for processing a captured image of a predetermined location (e.g., an orifice M shown in FIG. 1) where patterns (e.g., a pattern 21 shown in FIG. 3) are provided at predetermined intervals; A determination means (e.g., a pattern number determination unit 43 shown in FIG. 2) that determines the number of the patterns (e.g., the pattern 21 shown in FIG. 3) from the captured image that has been image-processed by the image processing means (e.g., the image processing unit 42 shown in FIG. 2); The apparatus is characterized by comprising a length detection means (e.g., length calculation unit 44 shown in FIG. 3) that detects the length of the liquid or object according to the number of patterns (e.g., pattern 21 shown in FIG. 3) determined by the determination means (e.g., pattern number determination unit 43 shown in FIG. 2). Effect of the Invention
[0012] Next, the effects of the present invention will be described with reference to the drawings. Note that the reference symbols in the parentheses are those of the embodiments described below, but the present invention is not limited thereto.
[0013] According to the inventions of claims 1 and 3, the length of a liquid or object can be detected by a simple method of determining the number of patterns (e.g., pattern 21 shown in Fig. 3) and detecting the length of the liquid or object according to the number. Therefore, according to the present invention, the length can be detected simply and easily without going to the site.
[0014] On the other hand, if the location is dark and it is difficult to capture an image of the pattern (for example, pattern 21 shown in FIG. 3) using an imaging means (for example, camera 3 shown in FIG. 1), it is preferable to form the pattern (for example, pattern 21 shown in FIG. 3) using a reflective material as in the invention according to claim 2. This is because it becomes possible to capture an image of the pattern (for example, pattern 21 shown in FIG. 3) using an imaging means (for example, camera 3 shown in FIG. 1) simply by shining a small amount of light such as lighting on the pattern 21.
[0015] In this specification, the term "length" is a concept that includes height and width. [Brief description of the drawings]
[0016] [Figure 1] 1 is a schematic overall view of a length detection system according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a functional configuration diagram of the length detection device according to the embodiment. [Diagram 3] 1A and 1B are front views of the pointer according to the embodiment, in which (a) shows a state in which all of the patterns can be recognized, and (b) shows a state in which only a part of the patterns can be recognized due to fallen leaves. [Figure 4] 4 is a flowchart showing the process of the length detection device according to the embodiment. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0017] Hereinafter, an embodiment of a length detection system relating to a length detection method and a length detection device according to the present invention will be described in detail with reference to the drawings. In the following description, when directions such as up, down, left, and right are indicated, they refer to up, down, left, and right when viewed from the front of the figure.
[0018] <Outline of the length detection system> The length detection system according to this embodiment can simply and easily detect the length without going to the site. Specifically, as shown in Fig. 1, the length detection system 1 is composed of a pointer 2, a camera 3, and a length detection device 4. Each component will be described in detail below.
[0019] <Explanation of the guide material> As shown in Fig. 1 and Fig. 3(a), the pointer 2 is formed of a tape material 20 formed in a vertically long rectangular shape, and patterns 21 (six patterns 21 are printed in the figure) are printed on the tape material 20 at predetermined intervals. Such a pointer material 2 is installed at a location where a length is to be detected. To explain using a specific example, in this embodiment, it is used to detect the length, i.e., the height, of a regulating pond. To explain in more detail, Fig. 1 illustrates an orifice M installed in a regulating pond, and this orifice M is provided with a vertically long rectangular hole M1 that regulates the accumulated rainwater and flows the rainwater W into a flow channel R, thereby suppressing the amount of water. And, as shown in Fig. 1, a lattice-shaped screen M2 is attached to this hole M1.
[0020] However, the flow channel R shown in FIG. 1 is prone to accumulation of fallen leaves F (see FIG. 3(b)), which causes a problem in that the hole M1 becomes clogged. If the hole M1 becomes clogged, the rainwater W does not flow properly into the flow channel R, and the length of the surface of the rainwater W, i.e., the water level, which is the height, rises, and in the worst case, there is a risk of the rainwater W overflowing. For this reason, in this embodiment, as shown in FIG. 1, a guide member 2 is provided vertically on the wall surface M3 of the orifice M located on the left side of the screen M2. That is, a tape member 20 is attached vertically to the wall surface M3 of the orifice M, so that a plurality of patterns 21 are positioned at predetermined intervals along the vertical direction (the up-down direction in the drawing), as shown in FIG. 1.
[0021] <Camera description> The camera 3 is, for example, a CCD camera, and captures an image of the vicinity of the orifice M. The camera 3 outputs the captured image to a length detection device 4.
[0022] <Explanation of length detection device> The length detection device 4 has a CPU 4a, a RAM 4b, a ROM 4c, an input device 4d, and an input / output module 4e. The CPU 4a executes and controls each function of the length detection device 4, and the RAM 4b temporarily stores programs and data supplied from an external device, etc.
[0023] On the other hand, the ROM 4c stores programs and various parameters that do not require modification, and the input device 4d is an external input device for receiving operation instructions from a user, such as a keyboard or a mouse. The input / output module 4e transmits and receives data to and from external devices, etc. The functions and processes of the length detection device 4, which will be described later, are realized by the CPU 4a reading out programs stored in the ROM 4c, etc., and executing these programs.
[0024] <Explanation of the functional configuration of the length detection device> Next, the functional configuration of the length detection device 4 will be described with reference to Fig. 2. As shown in Fig. 2, the functional configuration of the length detection device 4 includes a determination unit 40, a storage unit 41, an image processing unit 42, a pattern number determination unit 43, and a length calculation unit 44. Each component will be described below.
[0025] The determination unit 40 exchanges information between the functional blocks based on the state held by the determination unit 40 or the state held by each functional block. Furthermore, the determination unit 40 also exchanges information with the camera 3, and outputs predetermined data to the outside.
[0026] The storage unit 41 stores data necessary for processing.
[0027] The image processing unit 42 performs image processing of the captured image of the vicinity of the orifice M captured by the camera 3. Specifically, the image processing unit 42 performs processing to recognize only the clearly captured patterns 21 of the pointer 2 captured in the captured image as patterns. That is, when all the patterns 21 of the pointer 2 can be clearly recognized as shown in FIG. 3(a), the image processing unit 42 performs image processing to recognize all the patterns 21 of the pointer 2 as patterns. On the other hand, when the fallen leaves F shown in FIG. 3(b) are accumulated in the flow channel R shown in FIG. 1 and the water level, which is the length of the surface of the rainwater W shown in FIG. 1, that is, the height, rises, some of the patterns 21 of the pointer 2 are hidden by the fallen leaves F as shown in FIG. 3(b), and some of the patterns 21 become unclear. Therefore, the image processing unit 42 performs processing to recognize only the clear patterns 21 of all the patterns 21 of the pointer 2 as patterns, without recognizing the unclear patterns 21 as patterns. In the example of this embodiment, the image processing unit 42 performs a process of recognizing the top three patterns 21 of the pointer 2 shown in FIG. 3(b) as patterns.
[0028] The pattern number determination unit 43 determines the number of patterns 21 of the pointer 2 shown in Fig. 1 based on the captured image processed by the image processing unit 42. That is, the pattern number determination unit 43 determines the number of patterns 21 recognized as patterns by the image processing unit 42. To be more specific, in the case of the pointer 2 shown in Fig. 3(a), the pattern number determination unit 43 determines the number of patterns 21 to be six, and in the case of the pointer 2 shown in Fig. 3(b), the pattern number determination unit 43 determines the number of patterns 21 to be three.
[0029] The length calculation unit 44 calculates the length of the liquid surface of the rainwater W shown in Fig. 1, that is, the water level, which is the height, according to the number of patterns 21 determined by the pattern number determination unit 43. Specifically, the calculation is performed using the following Equation 1.
[0030]
number
[0031] Nmax indicates the number of all patterns 21 on the pointer 2, and N is the number of patterns 21 determined by the pattern number determination unit 43. The value of Nmax is stored in advance in the storage unit 41 shown in Fig. 2 by the user using the input device 4d shown in Fig. 1.
[0032] Therefore, in this embodiment, Nmax is "6", and since N is "6" in the case of the pointer material 2 shown in FIG. 3(a), the length calculation unit 44 calculates the length of the surface of the rainwater W shown in FIG. 1, that is, the water level, which is the height, as 10×(6-6)=0 cm. On the other hand, since N is "3" in the case of the pointer material 2 shown in FIG. 3(b), the length calculation unit 44 calculates the length of the surface of the rainwater W shown in FIG. 1, that is, the water level, which is the height, as 10×(6-3)=30 cm. The data of the length of the surface of the rainwater W shown in FIG. 1, that is, the water level, which is the height, calculated by the length calculation unit 44, is output to the outside by the judgment unit 40.
[0033] <Explanation of the processing contents of the length detection device> Next, the process of the length detection device 4 according to this embodiment will be described with reference to the flowchart shown in FIG.
[0034] First, the determination unit 40 shown in FIG. 2 acquires an image of the vicinity of the orifice M shown in FIG. 1 captured by the camera 3 (step S1).
[0035] Next, the determination unit 40 outputs the captured image to the image processing unit 42. In response to this, the image processing unit 42 performs a process of recognizing as a pattern only those clearly captured patterns 21 of the pointer 2 captured in the captured image (step S2).
[0036] Next, the determination unit 40 receives the captured image that has been image-processed by the image processing unit 42 from the image processing unit 42, and outputs it to the pattern number determination unit 43. In response to this, the pattern number determination unit 43 determines the number of patterns 21 (see FIGS. 1 and 3) recognized as patterns by the image processing unit 42 (step S3).
[0037] Next, the judgment unit 40 receives the number of patterns 21 (see FIGS. 1 and 3) determined by the pattern number determination unit 43 from the pattern number determination unit 43, and outputs it to the length calculation unit 44. In response to this, the length calculation unit 44 calculates the length of the liquid surface of the rainwater W shown in FIG. 1, that is, the water level, which is the height, according to the number of patterns 21 determined by the pattern number determination unit 43, using the above-described formula 1 (step S4).
[0038] Thus, the length of the surface of the rainwater W shown in Fig. 1 calculated in this manner, that is, the water level which is the height, is output from the length calculation unit 44 to the determination unit 40. In response to this, the determination unit 40 outputs data on the length of the surface of the rainwater W shown in Fig. 1, that is, the water level which is the height, to the outside.
[0039] The water level data output as described above is transmitted to a location other than the actual site (in this embodiment, the regulating pond in which the orifice M is installed) via a network (not shown). In this way, the length of the liquid surface of the rainwater W shown in FIG. 1, that is, the water level, which is the height, can be confirmed without going to the actual site (in this embodiment, the regulating pond in which the orifice M is installed).
[0040] Therefore, according to the present embodiment described above, the length of the surface of the rainwater W shown in Fig. 1, i.e., the water level, which is the height, can be detected by a simple method of calculating the length of the surface of the rainwater W shown in Fig. 1, i.e., the water level, which is the height, according to the number of patterns 21. Therefore, according to the present embodiment, the length can be detected simply and easily without going to the site.
[0041] <Description of Modifications> The contents exemplified in this embodiment are merely examples, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims. For example, in this embodiment, the length is calculated, but the invention is not limited to this, and the value of the length may be determined in advance according to the number of patterns. For example, a table may be prepared in which the length is 0 cm if the number of recognized patterns is 6, and the length is 30 cm if the number of recognized patterns is 3, and the table may be stored in advance in the storage unit 41 using the input device 4d. Also, the length detection device 4 may not perform any calculation, but may output the number of recognized patterns, and another device may calculate the length according to the number of patterns.
[0042] In addition, when calculating the length in this embodiment, the above-mentioned formula 1 is merely an example, and any formula may be used. In other words, the user may define the formula as desired according to the situation of the place where the device is used.
[0043] Furthermore, the length detection device 4 exemplified in this embodiment may be installed anywhere; for example, it may be installed on-site, on the cloud, or integrated with the camera 3.
[0044] Moreover, the pointer material 2 illustrated in this embodiment is merely an example, and may have any shape. For example, the shape of the pattern 21 on the pointer material 2 may be any shape, and is not particularly limited. Furthermore, the arrangement of the pattern 21 on the pointer material 2 is merely an example, and the patterns can be arranged in various sizes, vertical or horizontal lengths, etc., so as to be easily recognizable, according to the installation location. Furthermore, as illustrated in this embodiment, the patterns 21 do not all have to be the same, and for example, out of the six patterns 21, three patterns 21 may be the same pattern and three patterns 21 may be different patterns.
[0045] On the other hand, the material of the pointer 2 may be any material and is not particularly limited, but when the location is dark and it is difficult to capture the pattern 21 with the camera 3, it is preferable to form the pattern 21 using a reflective material as the material of the pointer 2. In this way, even if the location is dark and it is difficult to capture the pattern 21 with the camera 3, by forming the pattern 21 with a reflective material, a small amount of light such as lighting is applied to the pattern 21 so that the light is reflected toward the camera 3, and the reflection of the light makes it possible to capture the pattern 21 with the camera 3.
[0046] Incidentally, in this embodiment, the length detection system 1 is used to detect the height (length) of the liquid surface of rainwater W, that is, the water level, but it is not limited to this and can be used to detect various lengths such as the height (length) of snow accumulation, the height (length) of soil in a soil-filled area, the height (length) of garbage loaded on a garbage truck, the height (length) of luggage piled up in a logistics warehouse, or the width (length) of luggage piled up in a logistics warehouse. That is, the length detection system 1 in this embodiment can be used to detect the length of a liquid or an object. [Explanation of symbols]
[0047] 1 Length detection system 2 Pointer material 21 Pattern 3. Camera (imaging means) 4 Length detection device (prescribed device) 42 Image processing unit (image processing means) 43 Pattern number determination unit (determination means) 44 Length calculation unit (length detection means) M orifice (specified location)
Claims
1. This length detection method comprises determining the number of patterns placed at a predetermined interval at a predetermined location, imaged by an imaging means, using a predetermined device, and detecting the length of a liquid or object according to the determined number of patterns.
2. 2. The length detecting method according to claim 1, wherein the pattern is formed of a reflective material.
3. an image processing means for processing a captured image of a predetermined location where patterns are provided at predetermined intervals; a determination means for determining the number of the patterns from the captured image that has been image-processed by the image processing means; and length detection means for detecting a length of the liquid or object in accordance with the number of the patterns determined by the determination means.
Citation Information
Patent Citations
Liquid level sensor
JP2005181165A
