Light source state detection system and light source state detection method

Abstract

The invention provides a light source state detection system and a light source state detection method. The light source state detection method comprises an image acquisition step, a frame selection step, a lamp signal identification step, a marking step, a verification step and a lamp signal detection step. The image acquisition step acquires a detection image. In the frame selection step, each target light source is selected in a frame selection area in each detection image. The lamp signal identification step identifies the color and the light-emitting state of each target light source. In the marking step, a target light source serial number is marked for each detection image. In the verification step, when the light-emitting state of each target light source is off, an updated light source sequence number is generated, and when the target light source sequence number is different from the updated light source sequence number, each target light source sequence number is updated to the updated light source sequence number. The lamp signal detection step generates a detection result. Therefore, the flicker frequency and the flicker behavior of the target light source are detected and identified.

Description

Technical Field

[0001] The present invention relates to a light source state detection system and a light source state detection method, and in particular to a light source state detection system and a light source state detection method on a circuit board. Background Art

[0002] There are multiple light-emitting units on the circuit board of the electronic product. When the circuit on the circuit board is operating normally, the light-emitting units on the circuit board will emit light in a certain order, lighting duration, and flashing frequency. Therefore, by detecting the light-emitting state of the light source on the circuit board, it can be used to determine whether the circuit is operating normally. However, currently, the light source of the circuit board is manually detected by the operator. When it is found that the circuit is operating incorrectly in the subsequent process, it is difficult to trace the light-emitting state of the light-emitting unit, so it is impossible to quickly find the circuit error based on the light-emitting state of the individual light-emitting unit.

[0003] In view of this, developing a light source status detection system and a light source status detection method that can simultaneously identify and record the light emission status of multiple target light sources has become a goal worth researching and developing for related industries. Summary of the invention

[0004] Therefore, the object of the present invention is to provide a light source state detection system and a light source state detection method, which acquire images of multiple target light sources on a circuit board through multiple image acquisition devices and identify the light emission state. Thus, the light source state detection system and the light source state detection method of the present invention can quickly identify the light source state on the circuit board and record it.

[0005] According to an embodiment of the system state of the present invention, a light source state detection system is provided, comprising a test frame, a plurality of image acquisition devices and a processor. The test frame is provided for a circuit board. The circuit board comprises a plurality of target light sources. The image acquisition devices are arranged on the test frame and correspond to these target light sources respectively. These image acquisition devices are used to acquire a plurality of detection images including these target light sources. The processor signals are connected to these image acquisition devices and receive these detection images. The processor is configured to implement an operation comprising the following steps: a frame selection step, a light signal recognition step, a marking step, a verification step and a light signal detection step. The frame selection step comprises frame selection of each target light source in a frame selection area in each detection image. The light signal recognition step comprises identifying a color and a light emitting state of each target light source located in each detection image according to a deep learning algorithm. The marking step comprises identifying these detection images according to another deep learning algorithm and marking a target light source serial number for each detection image. Each target light source corresponds to a target light source serial number. The verification step includes verifying the target light source serial number according to the framed area in each detection image, and generating an updated light source serial number when the light state of each target light source is off, and when the target light source serial number is different from the updated light source serial number, the target light source serial number is updated to the updated light source serial number. The light signal detection step includes generating a detection result according to each detection image corresponding to the target light source serial number. The detection result includes a flickering frequency and a flickering behavior of each target light source.

[0006] According to an embodiment of the method aspect of the present invention, a light source status detection method is provided, comprising a setting step, an image acquisition step, a framing step, a light signal recognition step, a marking step, a verification step and a light signal detection step. The setting step comprises setting a circuit board on a test stand. The circuit board comprises a plurality of target light sources. The image acquisition step comprises driving a plurality of image acquisition devices to acquire a plurality of detection images comprising these target light sources. The framing step comprises driving a processor to frame each target light source in a framing area in each detection image. The light signal recognition step comprises driving the processor to identify a color and a luminous state of each target light source located in each detection image according to a deep learning algorithm. The marking step comprises driving the processor to identify these detection images according to another deep learning algorithm and mark each detection image with a target light source serial number. Each target light source corresponds to a target light source serial number. The verification step includes driving the processor to verify the target light source serial number according to the framed area in each detection image, and generating an updated light source serial number when the light state of each target light source is off, and when the target light source serial number is different from the updated light source serial number, updating the target light source serial number to the updated light source serial number. The light signal detection step includes driving the processor to generate a detection result according to each detection image corresponding to the target light source serial number. The detection result includes a flickering frequency and a flickering behavior of each target light source. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a schematic diagram showing a light source state detection system according to a first embodiment of the present invention;

[0008] Figure 2 is a flow chart showing a light source state detection method according to a second embodiment of the present invention;

[0009] Figure 3 It shows that according to Figure 2 A flowchart of the verification steps of the light source status detection method;

[0010] Figure 4 It shows that according to Figure 2 A flowchart of a compensation step in a verification step of a light source state detection method; and

[0011] Figure 5 It shows that according to Figure 2 Flow chart of the light signal detection steps of the light source status detection method.

[0012] Description of reference numerals:

[0013] 10: Circuit Board

[0014] 100: Light source status detection system

[0015] 110: Test stand

[0016] 111: Positioning hole

[0017] 120: Image acquisition device

[0018] 130: Processor

[0019] S100: Light source status detection method

[0020] S01: Setup Steps

[0021] S02: Image acquisition steps

[0022] S03: Box selection steps

[0023] S04: Light signal recognition steps

[0024] S05: Marking Step

[0025] S06: Verification Step

[0026] S061: Loading Steps

[0027] S062: Estimation Steps

[0028] S063: Confirmation Step

[0029] S064: Judgment Steps

[0030] S065, S066, S071, S072, S073, S074, S075: Steps S067, S068, S069: Sub-steps

[0031] S07: Compensation Step

[0032] S08: Light signal detection steps

[0033] S081: Statistical steps

[0034] S082: Calculation steps

[0035] CL: Color

[0036] Imt: Detection Image

[0037] L1, L2, L3: target light source

[0038] R1: Test results

[0039] RG1: Select area

[0040] SE: Target light source number

[0041] ST: Light status DETAILED DESCRIPTION

[0042] See also Figure 1 , Figure 1 1 is a schematic diagram showing a light source state detection system 100 according to a first embodiment of the present invention. The light source state detection system 100 includes a test stand 110, a plurality of image acquisition devices 120, and a processor 130. The test stand 110 is provided for a circuit board 10. The circuit board 10 includes a plurality of target light sources L1, L2, and L3. The image acquisition devices 120 are provided on the test stand 110 and correspond to the target light sources L1, L2, and L3, respectively. These image acquisition devices 120 are used to acquire a plurality of detection images Imt (see FIG. 1 ) including the target light sources L1, L2, and L3. Figure 2 The processor 130 is connected to the image acquisition device 120 and receives the detection images Imt. The processor 130 is configured to implement the light source state detection method S100 (see Figure 2 ).

[0043] Specifically, the test stand 110 may include a plurality of positioning holes 111 disposed at different positions, and the positioning holes 111 may be used for inserting the circuit board 10. The image acquisition device 120 moves on the test stand 110 according to the position of the target light sources L1, L2, and L3. The processor 130 may be a microprocessing unit, a central processing unit, or other electronic computing processor, but the present invention is not limited thereto. Thus, the light source state detection system 100 of the present invention is configured with a plurality of image acquisition devices 120, which can be used to detect a plurality of target light sources L1, L2, and L3 on an electronic device with a complex structure or composed of a plurality of circuit boards 10 inserted in different directions and angles.

[0044] See also Figure 1 and Figure 2 ,in Figure 2 1 is a flow chart showing a light source state detection method S100 according to a second embodiment of the present invention. The light source state detection method S100 includes a setting step S01, an image acquisition step S02, a frame selection step S03, a light signal recognition step S04, a marking step S05, a verification step S06, and a light signal detection step S08. The setting step S01 includes setting a circuit board 10 on a test stand 110, and the circuit board 10 includes target light sources L1, L2, and L3. The image acquisition step S02 includes driving the image acquisition device 120 to acquire a plurality of detection images Imt including the target light sources L1, L2, and L3. The frame selection step S03 includes driving the processor 130 to frame a frame selection area RG1 of each target light source L1, L2, and L3 in each detection image Imt. The light signal recognition step S04 includes driving the processor 130 to recognize a color CL and a light state ST of each target light source L1, L2, and L3 in each detection image Imt according to a deep learning algorithm. The marking step S05 includes driving the processor 130 to identify these detection images Imt according to another deep learning algorithm and mark each detection image Imt with a target light source serial number SE. Each target light source L1, L2, and L3 corresponds to the target light source serial number SE. The verification step S06 includes driving the processor 130 to verify the target light source serial number SE according to the framed area RG1 in each detection image Imt, and when the light-emitting state ST of each target light source L1, L2, and L3 is off, an updated light source serial number is generated, and when the target light source serial number SE is different from the updated light source serial number, each target light source serial number SE is updated to the updated light source serial number. The light signal detection step S08 includes driving the processor 130 to generate a detection result R1 according to each detection image Imt corresponding to the target light source serial number SE. The detection result R1 includes a flickering frequency and a flickering behavior of each target light source L1, L2, and L3. In this way, the light source state detection method S100 of the present invention can quickly identify the light source state on the circuit board 10 and record it.

[0045] The light source state detection system 100 may further include at least one light guiding element (not shown). The light guiding element connects at least one of the target light sources L1, L2, L3. The light source state detection method S100 may further include a light guiding step (not shown). The light guiding step connects the light guiding element to at least one of the target light sources L1, L2, L3, and is used to extend a light beam emitted by at least one of the target light sources L1, L2, L3. In this way, when at least one of the target light sources L1, L2, L3 is blocked by the circuit or electronic components on the circuit board 10, the light source state detection method S100 of the present invention can extend and guide the target light sources L1, L2, L3 to the position where the image acquisition device 120 can successfully acquire the image through the light guiding element, and perform subsequent detection and identification.

[0046] In the image acquisition step S02 , the image acquisition device 120 is disposed at a position where an image including the target light sources L1 , L2 , and L3 can be acquired.

[0047] In the frame selection step S03 , a frame selection area RG1 including one of the target light sources L1 , L2 , L3 is framed in the detection image Imt.

[0048] In the light signal recognition step S04, the processor 130 recognizes the color CL and lighting state ST (i.e., lighting or extinguishing) of the target light sources L1, L2, L3 in all the detection images Imt through a deep learning algorithm. The deep learning algorithm can be a feature acquirer, a classifier, or a convolutional layer, but the present invention is not limited thereto.

[0049] In the marking step S05, the processor 130 determines the target light sources L1, L2, L3 (e.g., target light source L1) corresponding to the detection image Imt in which the colors CL and the luminous states ST of the target light sources L1, L2, L3 have been identified according to another deep learning algorithm, and marks the corresponding target light source serial number SE on the current detection image Imt. The other deep learning algorithm may be a machine learning algorithm, an image processing algorithm, a model training, a classifier, or a Kalman filter, but the present invention is not limited thereto.

[0050] Specifically, although the marking step S05 uses a deep learning algorithm to determine the target light source serial number SE corresponding to one of the target light sources L1, L2, and L3 in the detection image Imt, when the light emitting state ST of the target light source L1, L2, and L3 is off, it may be impossible to identify the target light source L1, L2, and L3 corresponding to the current detection image Imt, or a wrong judgment may be made. Therefore, the light source state detection method S100 of the present invention further verifies the previously marked target light source serial number SE through a verification step S06 to ensure that the marking result is correct. The details of the operation of the verification step S06 will be described below through a more detailed embodiment.

[0051] Please also read Figures 1 to 3 ,in Figure 3 It shows that according to Figure 2 Flowchart of verification step S06 of the light source state detection method S100. Verification step S06 may further include a loading step S061, an estimation step S062, a confirmation step S063 and a determination step S064. Loading step S061 includes driving the processor 130 to load a plurality of framed regions RG1 of target light sources L1, L2, L3. Specifically, in loading step S061, the framed regions RG1 corresponding to all target light sources L1, L2, L3 framed in framed step S03 in the detection image Imt are loaded.

[0052] The estimation step S062 includes driving the processor 130 to estimate a light source area and a light source center coordinate in one of the detection images Imt. In other words, in the estimation step S062, the processor 130 calculates the light source area and the light source center coordinate according to one of the target light sources L1, L2, L3 in each detection image Imt.

[0053] The confirmation step S063 includes driving the processor 130 to confirm whether the light state ST of one of the detection images Imt is lighted. In the confirmation step S063, the processor 130 confirms whether the light state ST of each detection image Imt is lighted or off (i.e., not lighted). If it is lighted, step S065 is executed; if it is not lighted (i.e., off), the determination step S064 is executed.

[0054] Step S065 records the light source area and the light source center coordinates of the current detection image Imt estimated in step S062 when the light state ST corresponding to the current detection image Imt is light, and marks the target light source sequence number SE on the current detection image Imt. Step S066 stores the target light source sequence number SE and the light state ST of the target light sources L1, L2, and L3 in the database.

[0055] The judgment step S064 includes driving the processor 130 to judge whether one of the detection images Imt has a corresponding target light source number SE when the light state ST of one of the detection images Imt is off, and to mark the target light source number SE when the detection image Imt does not have the corresponding target light source number SE. In detail, the judgment step S064 includes sub-steps S067, S068, and S069. Sub-step S067 judges whether the detection image Imt with the light state ST as off has the target light source number SE marked in the previous marking step S05. If not, execute sub-step S068. If yes, execute compensation step S07.

[0056] Sub-step S068 calculates the light source area and the light source center coordinates in the detection image Imt that has not been marked with the target light source number SE. Sub-step S069 marks the target light source number SE of the detection image Imt according to the light source area and the light source center coordinates.

[0057] Please also read Figures 1 to 4 ,in Figure 4 It shows that according to Figure 2 FIG. 1 is a flow chart of the compensation step S07 in the verification step S06 of the light source state detection method S100 of FIG. The compensation step S07 includes re-identifying each detection image Imt and generating an updated light source number when the light state ST of one of these detection images Imt is off and one of these detection images Imt has a corresponding target light source number SE. Specifically, the compensation step S07 includes steps S071, S072, S073, S074, and S075. Step S071 loads the detection image Imt marked with the target light source number SE.

[0058] Step S072 performs the same operation as the marking step S05 on the current detection image Imt again, identifies the target light source L1 corresponding to the current detection image Imt, and generates an updated light source serial number. Step S073 determines whether the currently generated updated light source serial number is the same as the target light source serial number SE generated in the previous marking step S05. If not, execute step S074. If so, execute step S075. Step S074 updates the target light source serial number SE corresponding to the current detection image Imt to the updated light source serial number. Step S075 stores one of the target light source serial number SE and the updated light source serial number in the database according to the judgment result of step S073.

[0059] See also Figure 1 to Figure 2 and Figure 5 ,in Figure 5 It shows that according to Figure 2 FIG. 1 is a flow chart of the light signal detection step S08 of the light source state detection method S100 of FIG. 1 . The light signal detection step S08 may further include a counting step S081 and a calculation step S082. The counting step S081 includes driving the processor 130 to count the light emission states ST of each detection image Imt corresponding to the target light source sequence number SE. The calculation step S082 includes driving the processor 130 to calculate the flickering frequency and flickering behavior of the target light sources L1, L2, and L3 according to these light emission states ST.

[0060] Specifically, in the statistical step S081, the lighting states ST of all the detection images Imt with the same target light source serial number SE are statistically recorded in sequence. For example, the lighting states ST of the target light sources L1, L2, and L3 corresponding to the target light source serial number SE are shown in Table 1.

[0061] Table 1

[0062]

[0063]

[0064] In the calculation step S082, the processor 130 calculates the flickering frequency of each target light source L1, L2, L3 according to the luminous state ST of each target light source L1, L2, L3. In addition, the calculation step S082 can further remove the luminous state ST whose flickering frequency is far from the standard deviation, and calculate the flickering frequency of the target light sources L1, L2, L3 for the luminous state ST within the standard deviation. In this way, the light source state detection method S100 of the present invention can automatically filter out the detection image Imt of the target light sources L1, L2, L3 in the initial state, and only detect the light source state of the target light sources L1, L2, L3 after the circuit board 10 enters normal operation.

[0065] In other embodiments of the present invention, the light source state detection method may further include a recording step. The recording step includes driving the processor to store the color, flickering frequency and flickering behavior of each target light source in a database. In this way, the light source state detection method of the present invention can trace back the detection result of the light source state when a fault is found in the subsequent process of the circuit board, thereby accelerating the error finding speed.

[0066] Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Any person skilled in the art can make various changes and modifications without departing from the concept and scope of the present invention. Therefore, the scope of protection of the present invention shall be based on what is defined in the claims.

Claims

1. A light source status detection system, It is characterized in that Include: A test frame is provided for a circuit board, wherein the circuit board includes a plurality of target light sources; A plurality of image acquisition devices are disposed on the test frame and correspond to the plurality of target light sources respectively, and the plurality of image acquisition devices are used to acquire a plurality of detection images including the plurality of target light sources; and A processor is signal-connected to the plurality of image acquisition devices and receives the plurality of detection images, and the processor is configured to implement an operation comprising the following steps: A framing step, comprising framing each target light source in a framing area in each detection image; a light signal recognition step, comprising recognizing a color and a light-emitting state of each target light source in each detection image according to a deep learning algorithm; a marking step, comprising identifying the plurality of detection images according to another deep learning algorithm and marking a target light source serial number for each of the detection images, wherein each of the target light sources corresponds to the target light source serial number; a verification step, comprising verifying the target light source serial number according to the framed area in each of the detection images, and generating an updated light source serial number when the light emitting state of each of the target light sources is off, and updating the target light source serial number to the updated light source serial number when the target light source serial number is different from the updated light source serial number; and A light signal detection step includes generating a detection result according to each detection image corresponding to the target light source serial number, wherein the detection result includes a flickering frequency and a flickering behavior of each target light source.

2. The light source status detection system according to claim 1, It is characterized in that This verification step also includes: A loading step, comprising loading a plurality of the framed areas of the plurality of target light sources; an estimation step, comprising estimating a light source area and a light source center coordinate in one of the plurality of detection images; a confirmation step, comprising confirming whether the light emitting state of the one of the plurality of detection images is light emitting; a determination step, comprising, when the light-emitting state of the one of the plurality of detection images is off, determining whether the one of the plurality of detection images has the corresponding target light source number, and marking the target light source number when the one of the plurality of detection images does not have the corresponding target light source number; A compensation step includes re-identifying each of the detection images and generating the updated light source number when the light-emitting state of the one of the plurality of detection images is off and the one of the plurality of detection images has the corresponding target light source number.

3. The light source status detection system according to claim 1, It is characterized in that Also includes: At least one light guide element is connected to at least one of the plurality of target light sources and is used to extend a light beam emitted by the at least one of the plurality of target light sources.

4. The light source status detection system according to claim 1, It is characterized in that The light signal detection step also includes: a counting step, comprising counting the luminous state of each of the detection images corresponding to the target light source serial number; and A calculation step includes calculating the flickering frequency and the flickering behavior of each target light source according to the light emitting state.

5. The light source status detection system according to claim 1, It is characterized in that The processor is further configured to perform: A recording step includes storing the color, the flickering frequency and the flickering behavior of each target light source into a database.

6. A method for detecting light source status, It is characterized in that Include: A setting step includes setting a circuit board on a test frame, wherein the circuit board includes a plurality of target light sources; an image acquisition step, comprising driving a plurality of image acquisition devices to acquire a plurality of detection images including the plurality of target light sources; A frame selection step, comprising driving a processor to frame a frame selection area of ​​each target light source in each detection image; a light signal recognition step, comprising driving the processor to recognize a color and a light-emitting state of each target light source in each detection image according to a deep learning algorithm; a marking step, comprising driving the processor to identify the plurality of detection images according to another deep learning algorithm and marking a target light source serial number for each of the detection images, wherein each of the target light sources corresponds to the target light source serial number; a verification step, comprising driving the processor to verify the target light source serial number according to the framed area in each of the detection images, and generating an updated light source serial number when the light-emitting state of each of the target light sources is off, and when the target light source serial number is different from the updated light source serial number, updating the target light source serial number to the updated light source serial number; and A light signal detection step includes driving the processor to generate a detection result according to each detection image corresponding to the target light source sequence number, wherein the detection result includes a flickering frequency and a flickering behavior of each target light source.

7. The light source state detection method according to claim 6, It is characterized in that This verification step also includes: A loading step, comprising driving the processor to load the plurality of framed areas of the plurality of target light sources; An estimation step, comprising driving the processor to estimate a light source area and a light source center coordinate in one of the plurality of detection images; a confirmation step, comprising driving the processor to confirm whether the light emitting state of the one of the plurality of detection images is light emitting; a determination step, comprising driving the processor to determine whether the one of the plurality of detection images has the corresponding target light source serial number when the light emitting state of the one of the plurality of detection images is off, and marking the target light source serial number; A compensation step includes re-identifying each of the detection images and generating the updated light source number when the light-emitting state of the one of the plurality of detection images is off and the one of the plurality of detection images has the corresponding target light source number.

8. The light source state detection method according to claim 6, It is characterized in that Also includes: A light guiding step is to connect at least one light guiding element to at least one of the plurality of target light sources to extend a light beam emitted by the at least one of the plurality of target light sources.

9. The light source state detection method according to claim 6, It is characterized in that The light signal detection step also includes: A counting step, comprising driving the processor to count the luminous state of each of the detection images corresponding to the target light source serial number; and A calculation step includes driving the processor to calculate the flickering frequency and the flickering behavior of each target light source according to the light emitting state.

10. The light source state detection method according to claim 6, It is characterized in that Also includes: A recording step includes driving the processor to store the color, the flickering frequency and the flickering behavior of each target light source into a database.

Images