Computer-implemented system and method for identifying lamps and measuring the brightness of the public lighting system, and computer-readable medium

Abstract

The present invention relates to a system for identifying lamps and measuring the brightness of the public lighting system, comprising: at least one camera 1, at least one brightness sensor 2, at least one computing device 3, at least one power supply 4, and at least one display means 5. The present invention also relates to a computer-implemented method for identifying lamps and measuring the brightness of the public lighting system, which comprises at least the following steps: 1) capturing the image, 2) separating the colour channels of the image, 3) obtaining the histograms of the colour channels of the image, 4) identifying the type of lamp, 5) measuring the luminous flux, 6) calculating the depreciation of the luminous flux, and 7) displaying the results. The present invention also relates to a computer-readable medium comprising computer-readable instructions that, when executed by one or more processors, enable one or more processors to implement the method of the invention.

Description

"COMPUTER-IMPLEMENTED SYSTEM AND METHOD FOR IDENTIFYING LAMPS AND MEASURING THE BRIGHTNESS OF THE STREET LIGHTING SYSTEM, AND COMPUTER-READABLE MEDIUM" TECHNICAL FIELD

[0001] The present invention is in the field of management and preservation of the public lighting system, more specifically it describes a system and a method implemented by computer for identifying lamps and measuring the brightness of the public lighting system, and a computer-readable medium. BACKGROUND OF THE INVENTION

[0002] Public lighting systems in Brazil are important components of the electricity consumption matrix and, consequently, of the environmental impact, being a topic of utmost importance for sustainable development, since minimizing energy waste in public lighting systems favors the preservation of the environment.

[0003] Currently, different types of lamps can be found on streetlights. Some are more yellowish and others are whitish, each lamp has certain operating characteristics, which determine, among other factors, its consumption and useful life.

[0004] The first known form of public lighting, after street lamps, was the gas lamp, used in the 19th century. Then, around the 20th century, mercury-based electric discharge lamps were invented, which were widely used to illuminate streets due to their strong lighting potential. Still used today, they are whiter and have a temperature color range between 4000K and 4200K, which allows it to be used in large areas.

[0005] With the popularization of mercury-based electric discharge lamps, it was only a matter of time before other lighting technologies were developed, such as mercury vapor lamps with metal halide, or simply metal vapor lamps. Their lifespan is slightly shorter than that of mercury-based electric discharge lamps, but their luminous efficiency is higher, meaning they offer more light than the previous model and can save up to 60% energy.

[0006] Another advantage is the development of lamps with different color temperatures, which, for the first time, allowed for a variety of street colors, from blue to yellow. Today, this color mix can be found in the lighting of tourist attractions such as museums, statues, and bridges, where the aim is to create a striking effect with white lamps amid the yellow ones found on most streets.

[0007] Then, in the 1930s to be precise, the sodium vapor lamp emerged, consuming even less energy than mercury and metal vapor lamps and being more efficient. Its color temperature is 2000K, meaning it's a bit more yellowish, but it's still considered a good option due to its energy efficiency.

[0008] The technology currently considered most advanced, and which is gradually dominating the public lighting market, is based on the light-emitting diode (LED). With it, luminaires can be made with different color temperatures, from whitish to yellowish. with a long service life, high efficiency, and better color reproduction of objects. There is still some resistance to the use of this type of luminaire, as its initial cost is higher. However, there is a strong migration to luminaires that use this type of technology, considering the amortization time of the investment.

[0009] In addition to the types of lamps used in the public lighting system, and consequently their consumption, another aspect to be taken into consideration is the depreciation factor of the lamps' luminous flux. Luminous flux can be understood as the amount of radiant energy emitted by a lamp for a given unit of time, and evaluated according to the luminous sensation produced.

[0010] Luminous flux depreciation is the percentage reduction in luminous flux, or light output, of a lamp during its operating period. All light sources undergo luminous flux depreciation. The percentage depreciation of luminous flux loss used to determine end-of-life varies from 10% to 30%, depending on the type of lamp technology.

[0011] Identifying which type of lamp is installed on each public lighting pole and evaluating its luminous power is important for the proper management of the public lighting system, in order to provide quality lighting and minimize energy waste, favoring the preservation of the environment.

[0012] In the state of the art, one can find some works related to systems for identification / measurement of the public lighting system.

[0013] Document FR2976662, "Dispositif pour determiner la distribution de l'intensi te lumineuse de l' eclairage publi c sur une zone geographique donnee, vehi cul e comprenant ce dispositif et procede associ e", discloses a device and a method for determining the luminous intensity of street lighting lamps and a motor vehicle containing a device comprising at least one means for measuring the luminous intensity of several light sources; a satellite positioning system for determining the geographical position of at least some of these light sources; a means for processing the data provided by the means for measuring the luminous intensity and by the satellite positioning system, allowing this means of processing to determine the distribution of the intensity of the street lighting in the geographical area considered.

[0014] Document WO2017001233, "Street Light Detection", describes a method, a system and a vehicle especially adapted for measuring the light from street lighting lamps, the system comprising several light sensors arranged on a vehicle, where a part of these sensors is configured to measure the intensity and another part is configured to detect the angle of incidence of the light coming from the street lighting; a processing unit configured to calculate the position of the street lighting lamp in relation to the vehicle based on the angle of incidence of the light detected; and wherein the processing unit is configured to calculate the intensity of the street lighting lamp based on the light measurement.

[0015] None of the documents cited above, however, In turn, they anticipate the use of means of identifying the types of lamps used in the public lighting system through their color temperatures. However, an existing technique for such identification uses spectrophotometry to analyze the light pattern. This technique, in addition to being economically expensive, is based on the prismatic decomposition of the lamp light using Fourier Series, unlike the present invention, as described below. OBJECTIVES OF THE INVENTION

[0016] One of the objectives of the present invention is to provide a system, a computer-implemented method and a computer-readable means for identifying the type of lamp on streetlights and measuring the quality of the luminosity radiated in the public lighting system. SUMMARY OF THE INVENTION

[0017] The present invention relates to a system for identifying lamps and measuring the brightness of a public lighting system, comprising: at least one camera 1; at least one brightness sensor 2; at least one computing device 3; at least one power supply 4; and at least one display means 5. The at least one camera 1 is a digital camera with a USB connection, which captures images of the lamps 9 and transmits them to the at least one computing device 3 uninterruptedly. The at least one brightness sensor 2 measures the intensity / power of the luminous flux of the lamps 9 and transmits them to the at least one computing device 3 uninterruptedly. The at least one computing device 3 processes the images coming from the at least one a camera 1 and the data on the intensity / power of the luminous flux of the lamps and identifies the type of lamp 9 and measures the depreciation of the luminous flux. The at least one power supply 4 electrically supplies the at least one computing device 3 and the at least one display means 5. The at least one display means 5 provides the visualization and consultation of the identification data of the lamps 9 and measurement of the luminosity for an operator in real time.

[0018] The present invention also relates to a computer-implemented method for identifying lamps and measuring the brightness of a public lighting system, which comprises at least the following steps: 1) Image Capture; 2) Separation of the Image Color Channels; 3) Obtaining the Histograms of the Image Color Channels; 4) Identification of the Lamp Type; 5) Measurement of the Luminous Flux; 6) Calculation of the Luminous Flux Depreciation; and 7) Displaying the Results. In the Image Capture step, an image of a lamppost of the public lighting system is captured. In the image color channel separation step, the captured image is decomposed into three RGB channels. In the Histogram Obtaining step, a histogram is generated for each of the decomposed RGB channels of the captured image.The lamp type identification step is performed by a KNN (K-Nearest Neighbors') neural network previously trained from the histograms. In the luminous flux measurement step, the intensity / power of the lamp's luminous flux is measured. In the luminous flux depreciation calculation step, the brightness measurement data is processed together with the data from the identification of the type of lamp 9 to obtain the depreciation of the luminous flux of the lamp 9.

[0019] The present invention also relates to a computer-readable medium comprising computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the method subject to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] A more complete understanding of the present disclosure may be obtained by reference to the detailed description when considered in conjunction with the following illustrative Figures.

[0021] Figure 1 shows an illustration of the iteration of the system elements for identifying lamps and measuring the brightness of the public lighting system, in one of the preferred configurations of the present invention.

[0022] Figure 2 shows an illustration of the system for identifying lamps and measuring the brightness of the public lighting system implemented in a vehicle, in one of the preferred configurations of the present invention.

[0023] Figure 3 shows a general flowchart of the steps of the computer-implemented method for identifying lamps and measuring the brightness of the public lighting system, in one of the preferred configurations of the present invention.

[0024] Figure 4 shows a flowchart of the flow of information obtained for training the neural network for identifying lamps in the public lighting system, in one of the preferred configurations of the present invention.

[0025] Figure 5 shows the 24-color card used for training the neural network for identifying lamps in the public lighting system, in one of the preferred configurations of the present invention. DETAILED DESCRIPTION

[0026] The present invention falls within the field of management and preservation of the public lighting system, more specifically it describes a system for identifying lamps and measuring the brightness of the public lighting system, as seen in Figures 1 and 2. The system for identifying lamps and measuring brightness is preferably implemented in a vehicle 7, which travels on the streets and avenues at night, allowing the system to capture images of the lamps 9 on the posts 8 and measure their luminous flux in real time during their journey.

[0027] The system for identifying lamps and measuring brightness comprising: at least one camera 1; at least one brightness sensor 2; at least one computing device 3; at least one power supply 4; and at least one display means 5.

[0028] The at least one camera 1 has the function of capturing images of the lamps 9 on the public lighting poles 8 uninterruptedly throughout the entire route taken by the vehicle 7. The at least one camera 1 is preferably implemented in the upper part of the vehicle 7 with its capture lens facing upwards, thus enabling the capture of images of the lamps 9 on the poles 8, due to the fact that, in the public lighting system, the lamps are arranged mostly in places of relatively considerable height, as observed in Figure 2. The at least a camera 1 may be any simple camera that has the ability to capture and transmit images continuously, preferably a digital camera with a USB connection, such as, for example: a webcam. The at least one camera 1 is connected to at least one computing device 3, which receives images continuously from the at least one camera 1.

[0029] The at least one brightness sensor 2 has the function of measuring the luminous flux of the lamps 9 on the public lighting poles 8 uninterruptedly throughout the entire route taken by the vehicle 7. It is preferably implemented in the upper part of the vehicle 7, thus enabling the measurement of the luminous flux of the lamps 9. The at least one brightness sensor 2 may be any sensor that has the capacity to measure and transmit the measured luminous flux power continuously. For prototyping purposes, the TSL2561 brightness sensor was used. The at least one brightness sensor 2 is connected to the at least one computing device 3, which receives the measured luminous flux powers continuously from the at least one brightness sensor 2.

[0030] The at least one computing device 3 has the function of identifying the types of lamps 9 installed on the public lighting poles 8 and also measuring the depreciation of their luminous flux. The at least one computing device 3 receives data from the at least one camera 1 and from the at least one brightness sensor 2, stores, processes and makes available for viewing such received and processed data.

[0031] At least one computing device 3 receives images from at least one camera 1 continuously, processes the images by decomposing them into 3 color channels (red, green and blue - RGB), then a histogram is extracted for each color channel and, from the histograms, the type of lamp 9 is identified. The identification of the type of lamp 9 is performed by a previously trained KNN (K-Nearest Neighbors) neural network.

[0032] The at least one computing device 3 also receives data from the measurements of the luminous flux power from the brightness sensor 2 continuously, processes it - together with the lamp type identification data 9 - and the depreciation of the luminous flux of the lamp 9 and, consequently, data on its useful life are obtained.

[0033] The at least one computing device 3 additionally has a GPS (Global Positioning System) module that continuously provides location data for the vehicle 7 in which the system is implemented, to link the information identifying the type of lamp 9 and its luminous flux power to its location. This makes it possible to distinguish which type of lamp 9 is used in a given location and whether it is functioning properly, that is, whether the luminous flux power is at an acceptable level.

[0034] The at least one computing device 3 may be any computer that has the capacity to receive and process images from at least one camera 1 and the luminous flux power data coming from at least one brightness sensor 2 in a continuous manner, for prototyping purposes the computer board was used Multiplatform single board Raspberry Pi.

[0035] The at least one power supply 4 has the function of providing electrical energy to the system for identifying lamps and measuring brightness, but specifically electrically supplying the at least one computing device 3 and the at least one display means 5. The at least one power supply 4 may be a battery or the electrical system of the vehicle 7 in which the system is implemented, etc.

[0036] The at least one display means 5 has the function of providing the visualization and consultation of lamp identification and brightness measurement data for an operator in real time, the at least one display means 5 being connected to at least one computing device (3) and preferably being a monitor, a television or any device that has a screen and the display capacity.

[0037] The at least one computing device 3, the at least one power supply 4 and the at least one display means 5 may be replaced by a computer having the same capabilities, namely: connectivity with the at least one camera 1 and with the at least one light sensor 2; data processing capability from the at least one camera 1 and the at least one light sensor 2; and display capability. The computer may be a desktop computer, a notebook, a tablet, a smartphone, etc.

[0038] Additionally, the present invention presents a computer-implemented method for identifying lamps and measuring the brightness of the lighting system. public, as observed in Figure 3, the method comprising at least the following steps: 1) Image Capture; 2) Separation of Image Color Channels; 3) Obtaining the Histograms of the Image Color Channels; 4) Identification of the type of lamp; 5) Luminous Flux Measurement; 6) Calculation of luminous flux depreciation; and 7) Displaying results.

[0039] In the image capture stage, an image of a lamp on a streetlight pole is captured. Next, the color channel separation stage of the captured image is performed, where the image is decomposed into three channels (red, green, and blue - RGB).

[0040] In the Histograms acquisition stage, a histogram is generated for each of the decompositions of the captured image, that is, a histogram is provided for the red channel R, a histogram for the green channel G and a histogram for the blue channel B.

[0041] Using the histograms generated for each RGB channel, the lamp type on the streetlight is identified. This identification is performed by a previously trained KNN (K-Nearest Neighbors) neural network.

[0042] The KNN neural network is trained from the refraction of light on a 24-color checker card. As seen in figures 4 and 5, the 24-color checker card 6 is illuminated by a lamp where The image of the refracted light is captured by a camera. After the image is captured by the camera, the image is decomposed into three channels (red, green, and blue - RGB). Histograms are then generated for each of the channel decompositions: a histogram for the red channel R, a histogram for the green channel G, and a histogram for the blue channel B.

[0043] This procedure is performed with 10 different types of lamps used in the public lighting system, one at a time. Using the histogram data from each of the images related to each of the lamps, the KNN neural network is trained to identify each of the different types of lamps used.

[0044] In the Luminous Flux Measurement step, the luminous flux intensity / power of the streetlight's lamppost is measured. Then, in the Luminous Flux Depreciation Calculation step, the luminous flux power measurement data—along with lamp type identification data (lamp luminous flux intensity / power as reported by the manufacturer)—are processed to obtain the lamp's luminous flux depreciation. 9

[0045] In the Results Display stage, the results of the lamp type identification and luminous flux depreciation calculation steps are displayed on a display medium for viewing and consultation by an operator. The information displayed consists of the lamp type, luminous flux intensity / power, and luminous flux depreciation, linked to the lamp's location data.

[0046] It is also noteworthy that this method is implemented on a computer. The computer comprises at least one processor and a computer-readable storage medium, wherein the storage medium comprises computer-readable instructions that, when executed by at least one or more processors, cause the computer to perform the method as described above.

[0047] Thus, the method may be implemented using hardware, software, or any combination thereof, and may be implemented on one or more computer systems or other processing systems. Additionally, one or more of the steps described above may be implemented, at least in part, by machines. Examples of machines that may be used to perform one or more steps of the method include general-purpose digital computers, specially programmed computers, desktop computers, server computers, client computers, portable computers, mobile communication devices, tablet computers, and / or similar devices.

[0048] For example, an illustrative example system for carrying out the one or more steps of the method may include one or more components, such as one or more processors or microprocessors, for performing the arithmetic and / or logical operations required for executing a computer program, and storage media, such as one or more disk drives or memory cards (e.g., flash memory) for storing the program and data, and a random access memory, for temporarily storing data and program instructions.

[0049] The system may also include resident software on a storage medium (e.g., a disk drive or memory card), which, when executed, directs the processor(s) or microprocessor(s) in performing one or more steps of the method. The software may execute on an operating system stored on the storage medium, such as, for example, UNIX or Windows, Linux, Android, and the like, and may adhere to various protocols, such as Ethernet, ATM, TCP / IP protocols, and / or other connectionless or connectionless protocols.

[0050] As is well known in technology, microprocessors can run different operating systems and can contain different types of software, each type being devoted to a different function, such as manipulating and managing data / information from a particular source, or transforming data / information from one format to another. The method described should not be construed as being limited to use with any particular type of server computer, and that any other suitable type of device to facilitate the exchange and storage of information may be employed instead.

[0051] The method described in this document can be performed by a computer program that can be provided as a computer program product, or software. Given this, the present invention further provides a computer-readable medium recorded with a sequence of instructions for executing the described method by a computer. The computer-readable medium is an article of manufacture on a non-transitory machine-accessible or computer-readable medium. The instructions on the computer-readable medium can be used to program a computer system or other electronic device. Computer-readable storage media may include, but are not limited to, floppy disks, optical discs, CD-ROMs, and magneto-optical discs or other machine-readable media suitable for the storage or transmission of electronic instructions.

[0052] The method and computer-readable storage medium described herein are not limited to any particular software configuration. They may be applicable in any computing or processing environment. The term "computer-readable medium" shall include any transient or non-transitory medium that is capable of storing, encoding, or transmitting a sequence of instructions for execution by a computer (e.g., a CPU or other type of processing device) and that causes the computer to perform the method described herein. Furthermore, it is common in technology to speak of software, in one form or another (e.g., program, procedure, process, application, module, unit, logic, and the like), as taking an action or causing a result.Such expressions are merely a quick way of stating that the execution of software by a processing system causes the processor to perform an action to produce a result.

[0053] Numerous variations affecting the scope of protection of the present application are permitted. This reinforces the fact that the present invention is not limited to the particular configurations / embodiments described above.

Claims

CLAIMS 1. System for identifying lamps and measuring the brightness of the public lighting system comprising: at least one camera (1); at least one brightness sensor (2); at least one computing device (3); at least one power supply (4); and at least one display means (5), in which the at least one camera (1) captures images of the lamps (9) and transmits them to the at least one computing device (3) in an uninterrupted manner; in which the at least one brightness sensor (2) measures the intensity / power of the luminous flux of the lamps (9) and transmits them to the at least one computing device (3) in an uninterrupted manner; in which the at least one computing device (3) identifies the type of lamps (9) and measures the depreciation of their luminous flux; in which the at least one power supply (4) electrically supplies the at least one computing device (3) and the at least one display means (5);and in which the at least one display means (5) provides the visualization and consultation of the identification data of the lamps (9) and measurement of the luminosity for an operator in real time, characterized by the fact that the at least one camera (1) is a digital camera with USB connection; the at least one computing device (3) processes the images coming from the at least one camera (1) decomposing them into 3 RGB color channels, extracts a histogram; each RGB color channel and identifies the type of lamp (9) from the histograms with a previously trained KNN (K-Nearest Neighbors') neural network.

2. System, according to claim 1, characterized by the fact that it is preferably implemented in a vehicle (7), in which the at least one camera (1) and the at least one brightness sensor (2) are arranged in the upper part of the vehicle (7).

3. System, according to claim 1, characterized by the fact that the at least one computing device (3) receives the images from the at least one camera (1) and the brightness measurement data from the at least one brightness sensor (2), stores, processes and makes available for viewing such received and processed data, in which by processing the brightness measurement data from the at least one brightness sensor (2), together with the lamp type identification data (9), the depreciation of the luminous flux of the lamp (9) is obtained.

4. System, according to claim 1 or 3, characterized by the fact that the computing device (3) additionally presents a GPS module and links the information on the identification of the type of lamp (9), its intensity / power of the luminous flux and the depreciation of the luminous flux to its location.

5. System, according to claim 1, characterized by the fact that the at least one power supply (4) electrically supplies the at least one computing device (3) and at least one display means (5).

6. System, according to claim 1, characterized by the fact that the at least one display means (5) provides the visualization and consultation of the lamp identification data (9) and the luminosity measurement for an operator in real time.

7. Computer-implemented method for identifying lamps and measuring the brightness of the public lighting system, comprising at least the following steps: 1) Image Capture; 2) Separation of Image Color Channels; 3) Obtaining the Histograms of the Image Color Channels; 4) Identification of the type of lamp; 5) Luminous Flux Measurement; 6) Calculation of luminous flux depreciation; and 7) Displaying the results, in which in the Image capture stage, an image of a lamp on a streetlight is captured; in which in the color channel separation stage, the captured image is decomposed into three RGB channels; in which in the Histogram acquisition stage, a histogram is generated for each of the decomposed RGB channels of the captured image; in which in the luminous flux measurement stage, the intensity / power of the lamp's luminous flux is measured; in which in the results display stage the information on lamp type, luminous flux intensity / power, luminous flux depreciation, and lamp location data are displayed, characterized by the fact that the lamp type identification stage is performed by a KNN (K-Nearest Neighbors) neural network previously trained from the histograms; and the luminous flux depreciation calculation stage processes the brightness measurement data together with the lamp type identification data (9) and the luminous flux depreciation of the lamp (9) is obtained.

8. Method, according to claim 7, characterized by the fact that the KNN neural network is trained from the refraction of light in a 24-color verification card (6), in which the 24-color verification card (6) is illuminated by a lamp, the light refracted by the 24-color verification card (6) is captured by a camera, the image is decomposed into three RGB channels and histograms are generated for each of the decompositions in the RGB channels, in which from the histograms the KNN neural network is trained to identify the type of lamps used.

9. Method according to claim 7 or 8, characterized in that the training of the KNN neural network is carried out for at least 10 different types of lamps.

10. Computer-readable medium, characterized by the fact that it comprises computer-readable instructions that, when executed by one or more processors, make whereby the one or more processors perform the method as defined in any one of claims 7 to 9.

Images