CN112738412B - Full-automatic light supplementing method and device based on warp knitting machine flaw detection system - Google Patents
Full-automatic light supplementing method and device based on warp knitting machine flaw detection system Download PDFInfo
- Publication number
- CN112738412B CN112738412B CN202011636852.1A CN202011636852A CN112738412B CN 112738412 B CN112738412 B CN 112738412B CN 202011636852 A CN202011636852 A CN 202011636852A CN 112738412 B CN112738412 B CN 112738412B
- Authority
- CN
- China
- Prior art keywords
- illumination brightness
- interval
- detection
- brightness state
- frame image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/71—Circuitry for evaluating the brightness variation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/72—Combination of two or more compensation controls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/74—Circuitry for compensating brightness variation in the scene by influencing the scene brightness using illuminating means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention discloses a full-automatic light supplementing method based on a warp knitting machine flaw detection system, which comprises the following steps: collecting frame images according to the detection interval; carrying out illumination brightness detection on the frame image to identify the illumination brightness state of the frame image; when the illumination brightness state of the frame image is bright or dark, the detection interval is adjusted to be an initial detection interval, the exposure time, the gamma enable, the automatic gain and the external light source state are adjusted in real time to perform automatic light supplement, when the illumination brightness state of the frame image is normal, a detection interval is constructed and the illumination brightness state of the frame image in the detection interval is tracked, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, the detection interval is increased. The invention also discloses a full-automatic light supplementing device based on the warp knitting machine flaw detection system. By adopting the invention, the full automation of the light supplement can be realized, the consumption is reduced, and the detection speed is not influenced.
Description
Technical Field
The invention relates to the technical field of textiles, in particular to a full-automatic light supplementing method based on a warp knitting machine flaw detection system and a full-automatic light supplementing device based on the warp knitting machine flaw detection system.
Background
In machine vision systems, fill-in light is an important module, i.e., a light source that generally illuminates a subject at or near the axis of the camera, in order to properly expose the details of the shadow.
In practical applications, the fill-in light is limited by many factors (mainly including aperture size, exposure time, gain, gamma enable, brightness, darkness, etc.), and many factors are also limited. For example, the aperture size affects the depth of field, the exposure time affects the high-speed snapshot, the faster the speed is, the smaller the exposure time is, the darker the exposure time is, and the stronger the required external illumination is; the gain can obviously improve the image brightness, but greatly sacrifices the image quality and introduces a large amount of noise; gamma enabling can also change the brightness of the image, and inappropriate gamma values also greatly affect the quality of the image. Therefore, it is very important to set parameters properly.
Currently, the supplementary lighting is usually set manually, but there are many problems in manual setting. For example, if a darker cloth is replaced by a lighter cloth, there is a high possibility that the cloth is too bright, and the pixels of the image are almost 255 and have no analytical significance; similarly, when a relatively bright cloth is detected and a relatively dark cloth is suddenly switched, insufficient brightness occurs. Therefore, if the operator needs to manually set each time, the operator feels a sense of incongruity; and the common culture level of operators is often lower, so that if the operators are forced to learn too much knowledge beyond the bearable knowledge, the operators can do half the job, the operators cannot guarantee the correct use of the product, and the favorable comment of the product can be greatly reduced.
Disclosure of Invention
The invention aims to provide a full-automatic supplementary lighting method and system based on a warp knitting machine flaw detection system, which can realize full automation of new supplementary lighting, reduce consumption and have no influence on detection speed.
In order to solve the technical problem, the invention provides a full-automatic light supplementing method based on a warp knitting machine flaw detection system, which comprises the following steps: collecting frame images according to the detection interval; carrying out illumination brightness detection on the frame image to identify the illumination brightness state of the frame image; when the illumination brightness state of the frame image is bright or dark, the detection interval is adjusted to be an initial detection interval, exposure time, gamma enabling, automatic gain and an external light source state are adjusted in real time to automatically supplement light, when the illumination brightness state of the frame image is normal, a detection interval is established and the illumination brightness state of the frame image in the detection interval is tracked, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, the detection interval is increased.
As an improvement of the above solution, the step of constructing a detection interval and tracking the illumination brightness state of the frame image in the detection interval, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times is greater than a threshold, increasing the detection interval includes: s1, acquiring a detection interval; s2, carrying out illumination brightness detection on all frame images in the detection interval to identify the illumination brightness state of the frame images; s3, acquiring the detection times that the illumination brightness state of the frame image in the detection interval is normal; s4, judging whether the detection times are larger than a threshold value, if so, entering the step S5, if not, acquiring a new detection interval and returning to the step S2, wherein the new detection interval is adjacent to the original detection interval and has the same length; s5, acquiring the current frame number and the translation interval of the counter; s6, increasing the current frame number of the counter; s7, judging whether the current frame number reaches the translation section, if yes, entering the step S8, if no, returning to the step S6; s8, carrying out illumination brightness detection on the frame image in the translation interval to identify the illumination brightness state of the frame image; s9, acquiring the translation times that the illumination brightness state of the frame image in the translation interval is normal; and S10, judging whether the translation times are larger than the threshold value, if yes, doubling the translation amount of the interval to increase the detection interval, increasing the current frame number of the counter, returning to the step S7, if no, acquiring a new translation interval and returning to the step S8, wherein the new translation interval is adjacent to the original translation interval and has the same length.
As an improvement of the above scheme, the full-automatic supplementary lighting method based on the warp knitting machine flaw detection system further includes: acquiring a non-detection interval; dividing the non-detection interval into a plurality of subintervals; allocating a random index to each subinterval; sequentially carrying out illumination brightness detection on the frame image corresponding to each random index so as to identify the illumination brightness state of the frame image; when the illumination brightness states of the frame images corresponding to all the random indexes are normal, increasing the spot check interval; and when the illumination brightness state of the frame image corresponding to the random index is bright or dark, adjusting the spot check interval to be an initial spot check interval.
As an improvement of the above scheme, the step of adjusting the exposure time, the gamma enable, the automatic gain, and the external light source state in real time according to the illumination brightness state to perform automatic light supplement includes: when the illumination brightness state is bright, sequentially adjusting an external light source, automatic gain, gamma enabling and exposure time; and when the illumination brightness state is dark, sequentially adjusting the exposure time, the gamma enable, the automatic gain and the external light source, or sequentially adjusting the exposure time, the gamma enable, the external light source and the automatic gain.
As an improvement of the above scheme, the step of adjusting the exposure time in real time comprises: closing the automatic exposure; acquiring an upper exposure time limit and a lower exposure time limit; and adjusting the exposure time according to the illumination brightness state, wherein when the illumination brightness state is bright, a reduction interval of the exposure time is set, and whether the exposure time reaches an exposure time lower limit is judged, if not, the exposure time is reduced according to the reduction interval, if yes, the exposure time is kept, when the illumination brightness state is dark, an increase interval of the exposure time is set, whether the exposure time reaches an exposure time upper limit is judged, if not, the exposure time is increased according to the increase interval, and if yes, the exposure time is kept.
As an improvement of the above, the step of adjusting the gamma enable in real time comprises: starting gamma enabling; acquiring an upper gamma limit and a lower gamma limit of the gamma-enabled gamma value; and adjusting the gamma value according to the illumination brightness state, wherein when the illumination brightness state is bright, whether the gamma value reaches an upper gamma limit is judged, when the illumination brightness state is not bright, the gamma value is increased, when the illumination brightness state is yes, the gamma value is maintained, when the illumination brightness state is dark, whether the gamma value reaches a lower gamma limit is judged, when the illumination brightness state is not dark, the gamma value is reduced, and when the illumination brightness state is yes, the gamma value is maintained.
As an improvement of the above scheme, the step of adjusting the automatic gain in real time comprises: and adjusting the automatic gain according to the illumination brightness state, wherein when the illumination brightness state is bright, the automatic gain is closed and whether the gain value is 1 or not is judged, when the illumination brightness state is not bright, the gain value is reduced by 1, when the illumination brightness state is yes, the reduction of the gain value is stopped, and when the illumination brightness state is dark, the automatic gain is opened and kept until the gain value reaches the maximum value.
As an improvement of the above scheme, the step of adjusting the external light source in real time comprises: acquiring a voltage minimum value and a voltage maximum value of a power supply voltage of the external light source; dividing the suppliable voltage into a plurality of levels of supply voltages according to the voltage minimum and maximum; and adjusting the external light source according to the illumination brightness state, wherein when the illumination brightness state is bright, whether the power supply voltage reaches a voltage minimum value is judged, when the illumination brightness state is not bright, the power supply voltage of the external light source is reduced according to the multi-stage power supply voltage, when the illumination brightness state is dark, the power supply voltage is maintained, when the illumination brightness state is dark, whether the power supply voltage reaches a voltage maximum value is judged, when the illumination brightness state is not dark, the power supply voltage of the external light source is increased according to the multi-stage power supply voltage, and when the illumination brightness state is yes, the power supply voltage is maintained.
Correspondingly, the invention also provides a full-automatic light supplementing device based on the warp knitting machine flaw detection system, which comprises: the image acquisition module is used for acquiring frame images according to the detection intervals; the brightness detection module is used for detecting the illumination brightness of the frame image so as to identify the illumination brightness state of the frame image; the detection processing module is used for adjusting the detection interval to be an initial detection interval when the illumination brightness state of the frame image is bright or dark, adjusting exposure time, gamma enabling, automatic gain and an external light source state in real time to automatically supplement light, constructing a detection interval and tracking the illumination brightness state of the frame image in the detection interval when the illumination brightness state of the frame image is normal, and increasing the detection interval if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times is greater than a threshold value.
As an improvement of the above scheme, the full-automatic light supplementing device based on the warp knitting machine flaw detection system further comprises: and the spot check detection module is used for randomly extracting the frame images in the non-detection interval according to the spot check interval, detecting the illumination brightness of the randomly extracted frame images to identify the illumination brightness state of the frame images, increasing the spot check interval if the illumination brightness state of all the randomly extracted frame images is normal, and adjusting the spot check interval to be the initial spot check interval if the illumination brightness state of the frame images is bright or dark.
The implementation of the invention has the following beneficial effects:
according to the invention, through an automatic light supplementing mode, the problems are solved, the hardware cost is reduced, the consumption is reduced, and the detection speed is not influenced; meanwhile, the detection interval is automatically adjusted, so that the reading and writing times of the camera and the use of memory resources are greatly reduced, and the detection performance is greatly improved.
In addition, the invention considers the mutual restriction among a plurality of factors and forms a perfect adjusting system by combining the exposure time, the gamma enabling, the automatic gain and the external light source state.
Furthermore, the invention introduces a spot check mechanism to carry out targeted random spot check on the frame image, so that the search is more comprehensive and reliable; meanwhile, by adjusting the spot check interval, the reading and writing times of the camera and the use of memory resources are greatly reduced, and the detection performance is greatly improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a full-automatic light supplementing method based on a warp knitting machine flaw detection system;
FIG. 2 is a flowchart of an embodiment of constructing a detection interval and tracking an illumination brightness state of a frame image in the detection interval, wherein if a mode of the illumination brightness state of the frame image in the detection interval is normal and a normal number of times is greater than a threshold, a detection interval is increased;
FIG. 3 is a flow chart of another embodiment of the fully automatic light supplement method based on the warp knitting machine flaw detection system according to the present invention;
FIG. 4 is a flow chart of an embodiment of adjusting exposure time in real time according to the present invention;
FIG. 5 is a flow diagram of an embodiment of the present invention for real-time adjustment of gamma enable;
FIG. 6 is a flow chart of an embodiment of the present invention for adjusting the automatic gain in real time;
FIG. 7 is a flow chart of an embodiment of the present invention for real-time adjustment of an external light source;
FIG. 8 is a schematic structural diagram of a full-automatic light supplement device based on a warp knitting machine flaw detection system according to a first embodiment of the present invention;
fig. 9 is a schematic structural diagram of a full-automatic light supplement device based on a warp knitting machine flaw detection system according to a second embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of a full-automatic light supplement method based on a warp knitting machine flaw detection system according to the present invention, which includes:
and S101, acquiring frame images according to the detection interval.
The detection distance can be preset by an operator, and the system adjusts the detection distance in real time according to the actual illumination brightness detection result.
S102, carrying out illumination brightness detection on the frame image to identify the illumination brightness state of the frame image.
Specifically, the step of performing illumination brightness detection on the frame image to identify the illumination brightness state of the frame image includes:
(1) extracting a Region Of Interest (ROI) from the frame image;
(2) according to the pixel information of the region of interest;
(3) and detecting the illumination brightness of the frame image according to the pixel information so as to identify the illumination brightness state of the frame image.
In the invention, the illumination brightness detection can be realized by carrying out pixel statistics on the frame image. Before detection, the pixels can be roughly divided into three sections (such as a bright section, a dark section and a normal section) in advance, and the corresponding indexes are 1-3 respectively; the pixel can also be divided into five regions (e.g., too-dark non-processing region, especially-dark marginal processing region, normal region, especially-bright marginal processing region, and too-bright non-processing region), where the too-dark non-processing region and the especially-dark marginal processing region can be collectively referred to as dark region, and the especially-bright marginal processing region and the too-bright non-processing region can be collectively referred to as bright region), and the corresponding indexes are 1-5.
It should be noted that the range of each interval is adjustable, and the most reasonable set of parameters can be obtained by modifying the adjustment for many times. By dividing the pixel into intervals and then performing pixel statistics on the cut regions of interest, the section in which the pixel falls most obtains the corresponding index, and the indexes are respectively processed according to the obtained indexes.
For example, regions of interest a1, a2, a3, a4 and a5 are extracted from the frame image a, wherein if a1 is a bright section and a2, a3, a4 and a5 are normal sections, the frame image a is normal brightness, and the corresponding index is 3.
And S103, when the illumination brightness state of the frame image is bright or dark, adjusting the detection interval to be an initial detection interval, and adjusting the exposure time, the gamma enable, the automatic gain and the external light source state in real time to perform automatic light supplement.
Specifically, the step of adjusting the exposure time, the gamma enable, the automatic gain and the external light source state in real time according to the illumination brightness state to perform automatic light supplement comprises the following steps:
(1) when the illumination brightness state is bright, the external light source, the automatic gain, the gamma enable and the exposure time are adjusted in sequence.
When the illumination brightness state of the frame image is detected to be bright, the brightness of the frame image can be restored to a normal state through automatic parameter adjustment. Specifically, the adjustment sequence of the over-lighting process is: the brightness of an external light source is adjusted down through electronic equipment such as a PLC (programmable logic controller), then the automatic gain is closed and is reduced to 0, then the automatic gain is adjusted up within a certain range, the automatic gain is closed to a limit value, and finally the exposure time is adjusted down.
(2) When the illumination brightness state is dark, the exposure time, the gamma enable, the automatic gain and the external light source are adjusted in sequence, or the exposure time, the gamma enable, the external light source and the automatic gain are adjusted in sequence.
When the illumination brightness state of the frame image is detected to be dark, the brightness of the frame image can be restored to a normal state through automatically adjusting the parameters. In general, the order of the adjustment of the over-dark treatment is: the exposure time is adjusted firstly, then the gamma enabling is adjusted, then the automatic gain is adjusted, and finally the power supply voltage of an external light source (namely, an external light supplement lamp) is changed through electronic equipment such as a PLC (programmable logic controller) so as to change the brightness of the external light source. Accordingly, the adjustment order of the automatic gain and the brightness of the external light source can be interchanged as required; if the noise has little influence on the processing, the automatic gain can be adjusted firstly, so that the over-brightness of the external light source can be avoided, and the service life of the external light source is effectively prolonged; if the influence of noise reduction is considered, the brightness of the external light source can be adjusted in advance, so that the automatic gain does not need to be greatly increased, too much noise is not brought, and the quality of an image can be ensured.
In addition, the exposure time adjustment is limited, the speed of the equipment can be acquired through the PLC, the corresponding maximum exposure time can be calculated, the exposure time does not exceed the exposure time in the increasing process, and when the exposure time is set, whether the automatic exposure is in a closed state or not is judged, otherwise, the modification operation cannot be carried out. Meanwhile, the gamma enable is to perform the decreasing process in a small monotone interval, which is roughly in the range of 0.2-0.7, wherein the smaller the corresponding code adding value is, the brighter the brightness is. The automatic gain is self-increased by opening, and the efficiency is higher.
It should be noted that, each time the illumination brightness detection is performed, the corresponding parameter change is performed until the illumination brightness of the frame image is detected to be normal.
And S104, when the illumination brightness state of the frame image is normal, constructing a detection interval and tracking the illumination brightness state of the frame image in the detection interval, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, increasing the detection interval.
When the illumination brightness state of the frame image is detected to be normal, parameters do not need to be adjusted, the normal state and the index value thereof are recorded in the database every time, and the system can carry out state evaluation according to the number of times of occurrence of the normal state in a period of time.
For example, the detection interval of the frame image is 1 second, and if the illumination brightness state of the frame image corresponding to the 1 st second is bright, the system starts to perform automatic light supplement; because the automatic light supplement cannot be completed immediately, the illumination brightness state of the frame image corresponding to the next 2 to 5 seconds is still bright, and the automatic light supplement still needs to be carried out; after the automatic light supplement is completed, the illumination brightness state of the frame image corresponding to the 6 th second is normal, automatic light supplement is not needed at the moment, a detection interval can be established (if the detection interval is 6-15 seconds and the threshold is 8), and new frame images are collected continuously; if the next 7 th to 14 th seconds are still normal, the mode of the illumination brightness state of the frame image in the detection interval is normal, and the normal times are greater than a threshold value, the detection interval is increased; if the next 7 th to 12 th seconds are still normal, but the 13 th second is bright, the detection interval is not adjusted, automatic light supplement is carried out again, and only when the illumination brightness state of the frame image is detected to be normal again, the detection interval is reconstructed.
Therefore, the invention greatly reduces the reading and writing times of the camera and the use of memory resources by automatically adjusting the detection interval, and greatly improves the detection performance; meanwhile, the invention also ensures the problems to be solved, reduces the hardware cost and the consumption by an automatic light supplementing mode, and does not influence the detection speed.
Referring to fig. 2, fig. 2 shows a flowchart of an embodiment of constructing a detection interval and tracking an illumination brightness state of a frame image in the detection interval, where if a mode of the illumination brightness state of the frame image in the detection interval is normal and a normal number of times is greater than a threshold, a detection interval is increased, and the flowchart includes:
s201, acquiring a detection interval.
S202, carrying out illumination brightness detection on all frame images in the detection interval so as to identify the illumination brightness state of the frame images.
S203, acquiring the detection times that the illumination brightness state of the frame image in the detection interval is normal.
S204, judging whether the detection frequency is larger than the threshold value, if so, entering the step S205, if not, acquiring a new detection interval and returning to the step S202, wherein the new detection interval is adjacent to the original detection interval and has the same length.
S205, acquiring the current frame number and the translation interval of the counter.
It should be noted that the translation interval is the amount of translation of the current detection interval relative to the original detection interval. The invention can count the translation amount of the translation interval through the counter.
The invention can calculate the total times corresponding to the parameter change to the upper limit according to the specific light supplement process, including the total times of the exposure time increasing from the minimum value to the maximum value, the total times of the gamma enable change, the total times of the automatic gain change, and the total times of the PLC external voltage setting. The light supplement is performed only if the counter is within the calculated range (from the counter 0 to the total number of times). When the counter reaches another specified interval, the counter is set to 0.
And S206, increasing the current frame number of the counter.
S207, judging whether the current frame number reaches the translation section, if yes, the step S208 is entered, and if no, the step S206 is returned.
S208, carrying out illumination brightness detection on the frame image in the translation interval to identify the illumination brightness state of the frame image.
S209, acquiring the translation times of the frame image in the translation interval with the illumination brightness state being normal.
S210, judging whether the translation times are larger than a threshold value, if so, doubling the translation amount of the interval to increase the detection interval, increasing the current frame number of the counter, returning to the step S207, and if not, acquiring a new translation interval and returning to the step S208, wherein the new translation interval is adjacent to the original translation interval and has the same length.
In the invention, the condition of light supplement of each frame needs to be recorded, the mode from the detection normal to the detection length tail result is counted, if the detection times included in the mode are too few, the next detection of the adjacent frame interval is carried out again, and the result of the next detection is taken as the standard. If the detection result is normal, stopping brightness detection, then waiting for the set initial interval to carry out next detection, if the detection result is normal, increasing the interval, if the detection result is abnormal, enabling the counter and the interval to return to 0, and carrying out bright or dark processing again at the abnormal position.
In addition, the warp knitting machine flaw detection system can detect the startup and shutdown state, and the counter can be cleared and detected again in the startup state and the shutdown state. Because the cloth is changed when the machine is stopped, resources can be well utilized, frequent read-write operation of the camera is not needed to be worried, a detection memory is not occupied, brightness detection is carried out only in a fragmentary time, and the operation efficiency of the system is not influenced.
Referring to fig. 3, fig. 3 shows that the full-automatic light supplement method based on the warp knitting machine flaw detection system of the present invention further includes:
s301, a non-detection interval is obtained.
The non-detection interval refers to a time period between two adjacent detections, if the detection interval is 5 detections every 10 minutes, 5 frame images are continuously detected again every 10 minutes after 5 frame images are continuously detected, and the 10-minute interval is a non-detection interval and the 5 continuous frame images are detection intervals.
S302, the non-detection section is divided into a plurality of subintervals.
And S303, allocating a random index to each subinterval.
S304, sequentially carrying out illumination brightness detection on the frame image corresponding to each random index so as to identify the illumination brightness state of the frame image.
S305, when the illumination brightness states of the frame images corresponding to all the random indexes are normal, increasing the sampling interval.
S306, when the illumination brightness state of the frame image corresponding to the random index is bright or dark, the spot check interval is adjusted to be the initial spot check interval.
It should be noted that, if the illumination brightness of the current frame image is normal, and after the distance from the next detection interval is calculated, a random index is generated in the detection interval to perform a preset spot check on the corresponding frame image, and a corresponding brightness sample check is performed, so as to avoid an abnormality between intermediate detection intervals (i.e., between two adjacent detections). The characteristic of the existence of the abnormity is that if the abnormity exists in a certain frame image, the abnormity exists in the frame images behind the certain frame image with high probability. Therefore, a section of non-detection interval can be divided into a plurality of sub-intervals to independently search for random frame images, so that the search is more comprehensive and reliable, the read-write times of a camera and the use of memory resources are greatly reduced, and the detection performance is greatly improved.
Accordingly, the records of the spot checks are saved, and the more normal the spot check records are, the more the spot check interval is enlarged, the longer the detection of the image brightness is not performed, and then the higher the possibility that the image brightness is not detected for a long time, thereby reducing the spot check interval. However, if a problem occurs in the process of spot check, the counter is cleared, the subsequent preset operation is abandoned from the beginning, the corresponding interval translation variable is reinitialized, the re-detection interval is reduced, the important detection is performed near the risk area, and the spot check frequency is gradually reduced again until the illumination is restored to be normal.
Referring to fig. 4, fig. 4 shows a flowchart of an embodiment of adjusting the exposure time in real time according to the present invention, which includes:
s401, closing the automatic exposure.
S402, acquiring an upper exposure time limit and a lower exposure time limit.
Specifically, the speed of the device can be obtained by the PLC, and thus the corresponding maximum exposure time (i.e., the upper exposure time limit) is calculated.
And S403, adjusting the exposure time according to the illumination brightness state.
S404, when the illumination brightness state is bright, setting the decreasing interval of the exposure time and judging whether the exposure time reaches the lower limit of the exposure time, if not, decreasing the exposure time according to the decreasing interval, if so, keeping the exposure time.
S405, when the illumination brightness state is dark, setting an increasing interval of the exposure time and judging whether the exposure time reaches the upper limit of the exposure time, if not, increasing the exposure time according to the increasing interval, and if so, keeping the exposure time.
It should be noted that the exposure time adjustment is limited, the exposure time cannot exceed the exposure time during the increase/decrease, and when the exposure time is set, it is determined whether the automatic exposure is in the off state, otherwise, the modification operation cannot be performed.
Referring to fig. 5, fig. 5 shows a flow chart of an embodiment of the present invention for adjusting gamma enable in real time, which includes:
s501, gamma enabling is started.
S502, an upper gamma limit and a lower gamma limit of the gamma-enabled gamma value are obtained.
S503, adjusting the gamma value according to the illumination brightness state.
S504, when the illumination brightness state is bright, whether the gamma value reaches the gamma upper limit is judged, if not, the gamma value is increased, and if yes, the gamma value is maintained.
And S505, when the illumination brightness state is dark, judging whether the gamma value reaches the lower gamma limit, if not, reducing the gamma value, and if so, keeping the gamma value.
It should be noted that the gamma enable is to perform the decreasing process in a small monotone interval, which is roughly in the range of 0.2-0.7, wherein the smaller the corresponding code value is, the brighter the brightness is.
Referring to fig. 6, fig. 6 shows a flow chart of an embodiment of adjusting the automatic gain in real time according to the present invention, which includes:
s601, adjusting automatic gain according to the illumination brightness state.
S602, when the illumination brightness state is bright, the automatic gain is closed and whether the gain value is 1 or not is judged, if not, the gain value is reduced by 1, and if yes, the gain value is stopped to be reduced.
S603, when the illumination brightness state is dark, turning on the automatic gain and maintaining the automatic gain until the gain value reaches a maximum value.
It should be noted that the automatic gain is turned on to increase itself, because most industrial cameras have this function and are relatively efficient.
Referring to fig. 7, fig. 7 is a flow chart of an embodiment of adjusting the external light source in real time according to the present invention, which includes:
s701, acquiring the minimum voltage value and the maximum voltage value of the power supply voltage of the external light source.
S702, the available power supply voltage is divided into a plurality of stages of power supply voltages according to the minimum voltage value and the maximum voltage value.
And S703, adjusting the external light source according to the illumination brightness state.
S704, when the illumination brightness state is bright, judging whether the power supply voltage reaches the minimum voltage value, if not, reducing the power supply voltage of the external light source according to the multistage power supply voltage, and if so, keeping the power supply voltage.
S705, when the illumination brightness state is dark, judging whether the power supply voltage reaches the maximum voltage value, if not, increasing the power supply voltage of the external light source according to the multistage power supply voltage, and if so, keeping the power supply voltage.
Therefore, the brightness of the frame image can be flexibly adjusted in a mode of adjusting the brightness of the external light source in real time, and the flexibility is strong.
In summary, the invention considers the mutual restriction among various factors, and forms a perfect adjusting system by combining the exposure time, the gamma enable, the automatic gain and the external light source state.
Further, the size of the aperture is according to the actual requirement; if the requirement on the depth of field is higher, a small aperture and a brighter light source are adopted; if there is no requirement for depth of field, it is generally set to the maximum aperture.
Referring to fig. 8, fig. 8 shows a first embodiment of a fully automatic light supplement device 100 based on a warp knitting machine flaw detection system of the present invention, which comprises:
and the image acquisition module 1 is used for acquiring frame images according to the detection intervals. The detection distance can be preset by an operator, and the system adjusts the detection distance in real time according to an actual illumination brightness detection result. Specifically, the image acquisition module includes camera, camera lens, fixed bolster, switch, light source, but power supply type net twine, light filling lamp, PLC board speed acquisition module etc..
And the brightness detection module 2 is used for detecting the illumination brightness of the frame image so as to identify the illumination brightness state of the frame image. Specifically, the brightness detection module extracts a Region Of Interest (ROI) from the frame image, and performs illumination brightness detection on the frame image according to pixel information Of the Region Of Interest and the pixel information to identify an illumination brightness state Of the frame image.
The detection processing module 3 is configured to adjust the detection interval to be an initial detection interval when the illumination brightness state of the frame image is bright or dark, adjust exposure time, gamma enable, automatic gain, and an external light source state in real time to perform automatic light supplement, construct a detection interval and track the illumination brightness state of the frame image in the detection interval when the illumination brightness state of the frame image is normal, and increase the detection interval if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value.
When the illumination brightness state is bright, the detection processing module 3 sequentially adjusts the external light source, the automatic gain, the gamma enable and the exposure time. It should be noted that, when the illumination brightness state of the frame image is detected to be bright, the brightness of the frame image can be restored to the normal state by automatically adjusting the parameters. Specifically, the adjustment sequence of the over-lighting process is: the brightness of an external light source is adjusted down through electronic equipment such as a PLC (programmable logic controller), then the automatic gain is closed and is reduced to 0, then the automatic gain is adjusted up within a certain range, the automatic gain is closed to a limit value, and finally the exposure time is adjusted down.
When the illumination brightness state is dark, the detection processing module 3 sequentially adjusts the exposure time, the gamma enable, the automatic gain and the external light source, or sequentially adjusts the exposure time, the gamma enable, the external light source and the automatic gain. It should be noted that, when the illumination brightness state of the frame image is detected to be dark, the brightness of the frame image can be restored to the normal state by automatically adjusting the parameters. In general, the order of the adjustment of the over-darkening treatment is: the exposure time is adjusted firstly, then the gamma enabling is adjusted, then the automatic gain is adjusted, and finally the power supply voltage of an external light source (namely, an external light supplement lamp) is changed through electronic equipment such as a PLC (programmable logic controller) so as to change the brightness of the external light source. Accordingly, the adjustment order of the automatic gain and the brightness of the external light source can be interchanged as required; if the noise has little influence on the processing, the automatic gain can be adjusted firstly, so that the over-brightness of the external light source can be avoided, and the service life of the external light source is effectively prolonged; if the influence of noise reduction is considered, the brightness of the external light source can be adjusted in advance, so that the automatic gain does not need to be greatly increased, too much noise is not brought, and the quality of an image can be ensured.
When the illumination brightness state of the frame image is normal, the detection processing module 3 constructs a detection interval and tracks the illumination brightness state of the frame image in the detection interval, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, the detection interval is increased. It should be noted that, when the illumination brightness state of the frame image is detected to be normal, the parameter does not need to be adjusted, and each normal state and the index value thereof are recorded in the database, and the system performs state evaluation according to the number of times of occurrence of the normal state in a period of time.
Further, the detection processing module 3 constructs a detection interval and tracks the illumination brightness state of the frame image in the detection interval, and if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than the threshold, the specific mode of increasing the detection interval is as follows: s201, acquiring a detection interval. S202, carrying out illumination brightness detection on all frame images in the detection interval so as to identify the illumination brightness state of the frame images. S203, acquiring the detection times that the illumination brightness state of the frame image in the detection interval is normal. S204, judging whether the detection frequency is larger than the threshold value, if so, entering the step S205, if not, acquiring a new detection interval and returning to the step S202, wherein the new detection interval is adjacent to the original detection interval and has the same length. S205, acquiring the current frame number and the translation interval of the counter. S206, increasing the current frame number of the counter. S207, judging whether the current frame number reaches the translation section, if yes, the step S208 is entered, and if no, the step S206 is returned. S208, detecting the illumination brightness of the frame image in the translation interval to identify the illumination brightness state of the frame image. S209, acquiring the translation times of the frame image in the translation interval with the illumination brightness state being normal. S210, judging whether the translation times is larger than a threshold value, if so, doubling the translation amount of the interval to increase the detection interval, increasing the current frame number of the counter, returning to the step S207, and if not, acquiring a new translation interval and returning to the step S208, wherein the new translation interval is adjacent to the original translation interval and has the same length.
It should be noted that the translation interval is the amount of translation of the current detection interval relative to the original detection interval. The invention can count the translation amount of the translation interval through the counter.
In the invention, the condition of light supplement of each frame needs to be recorded, the mode from the detection normal to the detection length tail result is counted, if the detection times included in the mode are too few, the next detection of the adjacent frame interval is carried out again, and the result of the next detection is taken as the standard. If the detection result is normal, stopping brightness detection, then waiting for the set initial interval to carry out next detection, if the detection result is normal, increasing the interval, if the detection result is abnormal, enabling the counter and the interval to return to 0, and carrying out bright or dark processing again at the abnormal position. In addition, the warp knitting machine flaw detection system can detect the startup and shutdown state, and the counter can be cleared and detected again in the startup state and the shutdown state. Because the cloth is changed when the machine is stopped, resources can be well utilized, frequent read-write operation of the camera is not needed to be worried, a detection memory is not occupied, brightness detection is carried out only in a fragmentary time, and the operation efficiency of the system is not influenced.
Specifically, the detection processing module 3 includes an exposure time adjusting unit, a gamma enable adjusting unit, an automatic gain adjusting unit, and an external light source adjusting unit, wherein:
an exposure time adjusting unit for turning off the automatic exposure; acquiring an upper exposure time limit and a lower exposure time limit; adjusting the exposure time according to the illumination brightness state; when the illumination brightness state is bright, setting a reduction interval of the exposure time and judging whether the exposure time reaches the lower limit of the exposure time, if not, reducing the exposure time according to the reduction interval, and if so, keeping the exposure time; and when the illumination brightness state is dark, setting an increasing interval of the exposure time and judging whether the exposure time reaches the upper limit of the exposure time, if not, increasing the exposure time according to the increasing interval, and if so, keeping the exposure time. It should be noted that the exposure time adjustment is limited, the exposure time cannot exceed the exposure time during the increase/decrease, and when the exposure time is set, it is determined whether the automatic exposure is in the off state, otherwise, the modification operation cannot be performed.
A gamma enable adjusting unit for turning on gamma enable; acquiring an upper gamma limit and a lower gamma limit of a gamma value of gamma enabling; adjusting the gamma value according to the illumination brightness state; when the illumination brightness state is bright, judging whether the gamma value reaches the upper gamma limit, increasing the gamma value when the gamma value does not reach the upper gamma limit, and keeping the gamma value when the gamma value does not reach the upper gamma limit; when the illumination brightness state is dark, judging whether the gamma value reaches a lower gamma limit, reducing the gamma value when the gamma value does not reach the lower gamma limit, and keeping the gamma value when the gamma value does not reach the lower gamma limit; the gamma enable is a reduction process performed in a small monotonic interval, generally ranging from 0.2 to 0.7, wherein the smaller the corresponding addend value, the brighter the brightness.
The automatic gain adjusting unit is used for adjusting automatic gain according to the illumination brightness state; when the illumination brightness state is bright, closing the automatic gain and judging whether the gain value is 1, if not, subtracting 1 from the gain value, and if so, stopping decreasing the gain value; when the illumination brightness state is dark, the automatic gain is turned on and maintained until the gain value reaches a maximum value.
The external light source adjusting unit is used for acquiring the voltage minimum value and the voltage maximum value of the power supply voltage of the external light source; dividing the available supply voltage into a plurality of stages of supply voltages according to the minimum voltage value and the maximum voltage value; adjusting an external light source according to the illumination brightness state; when the illumination brightness state is bright, judging whether the power supply voltage reaches the minimum voltage value, if not, reducing the power supply voltage of an external light source according to the multi-stage power supply voltage, and if so, keeping the power supply voltage; and when the illumination brightness state is dark, judging whether the power supply voltage reaches the maximum voltage value, increasing the power supply voltage of the external light source according to the multi-stage power supply voltage when the power supply voltage does not reach the maximum voltage value, and keeping the power supply voltage when the power supply voltage is judged to be yes.
Therefore, by combining the exposure time adjusting unit, the gamma enable adjusting unit, the automatic gain adjusting unit, and the external light source adjusting unit, a complete adjusting system can be formed.
Referring to fig. 9, fig. 9 shows a second embodiment of the full-automatic light supplement device 100 based on a warp knitting machine defect detection system of the present invention, which is different from the first embodiment shown in fig. 8, in this embodiment, the full-automatic light supplement device 100 based on a warp knitting machine defect detection system further includes a spot check detection module 4.
The spot check detection module 4 is configured to randomly extract frame images in the non-detection interval according to the spot check interval, perform illumination brightness detection on the randomly extracted frame images to identify an illumination brightness state of the frame images, increase the spot check interval if the illumination brightness states of all the randomly extracted frame images are normal, and adjust the spot check interval to the initial spot check interval if the illumination brightness state of the frame images is bright or dark.
It should be noted that, if the illumination brightness of the current frame image is normal, and after the distance from the next detection interval is calculated, a random index is generated in the detection interval to perform a preset spot check on the corresponding frame image, and a corresponding brightness sample check is performed, so as to avoid an abnormality between intermediate detection intervals (i.e., between two adjacent detections). The characteristic of the existence of the abnormity is that if the abnormity exists in a certain frame image, the abnormity exists in the frame images behind the certain frame image with high probability. Therefore, a section of non-detection interval can be divided into a plurality of subintervals to independently search for random frame images in the subintervals, so that the search is more comprehensive and reliable, the read-write times of the camera and the use of memory resources are greatly reduced, and the detection performance is greatly improved.
Accordingly, the records of the spot checks are saved, and the more normal the spot check records are, the more the spot check interval is enlarged, the longer the detection of the image brightness is not performed, and then the higher the possibility that the image brightness is not detected for a long time, thereby reducing the spot check interval. However, if a problem occurs in the process of spot check, the counter is cleared, the subsequent preset operation is abandoned from the beginning, the corresponding interval translation variable is reinitialized, the re-detection interval is reduced, the important detection is performed near the risk area, and the spot check frequency is gradually reduced again until the illumination is restored to be normal.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A full-automatic light supplementing method based on a warp knitting machine flaw detection system is characterized by comprising the following steps:
collecting frame images according to the detection interval;
carrying out illumination brightness detection on the frame image to identify the illumination brightness state of the frame image;
when the illumination brightness state of the frame image is bright or dark, the detection interval is adjusted to be an initial detection interval, and the exposure time, the gamma enable, the automatic gain and the external light source state are adjusted in real time to perform automatic light supplement,
when the illumination brightness state of the frame image is normal, a detection interval is constructed and the illumination brightness state of the frame image in the detection interval is tracked, if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, the detection interval is increased, and if the illumination brightness state mode is normal, namely the number of interested areas in the normal interval in the frame image is greater than the total number of the interested areas.
2. The method according to claim 1, wherein the step of constructing a detection interval and tracking the illumination brightness state of the frame images in the detection interval, and if the illumination brightness state mode of the frame images in the detection interval is normal and the number of times of normal is greater than a threshold value, the step of increasing the detection interval comprises:
s1, acquiring a detection interval;
s2, carrying out illumination brightness detection on all frame images in the detection interval to identify the illumination brightness state of the frame images;
s3, acquiring the detection times that the illumination brightness state of the frame image in the detection interval is normal;
s4, judging whether the detection times are larger than a threshold value,
if the judgment result is yes, the flow proceeds to step S5,
if not, acquiring a new detection interval which is adjacent to the original detection interval and has the same length, and returning to the step S2;
s5, acquiring the current frame number and the translation interval of the counter;
s6, increasing the current frame number of the counter;
s7, judging whether the current frame number reaches the translation section, if yes, entering the step S8, if no, returning to the step S6;
s8, carrying out illumination brightness detection on the frame image in the translation interval to identify the illumination brightness state of the frame image;
s9, acquiring the translation times that the illumination brightness state of the frame image in the translation interval is normal;
s10, judging whether the translation times are larger than a threshold value,
if yes, the block shift amount is doubled to increase the detection interval, the current number of frames of the counter is increased, and the process returns to step S7,
if not, a new translation section is acquired, and the length of the new translation section is equal to that of the original translation section, and the process returns to the step S8.
3. The full-automatic supplementary lighting method based on the warp knitting machine flaw detection system as claimed in claim 1, further comprising:
acquiring a non-detection interval, wherein the non-detection interval refers to a time period between two adjacent detections;
dividing the non-detection interval into a plurality of subintervals;
allocating a random index to each subinterval;
sequentially carrying out illumination brightness detection on the frame image corresponding to each random index so as to identify the illumination brightness state of the frame image;
when the illumination brightness states of the frame images corresponding to all the random indexes are normal, increasing the spot check interval;
and when the illumination brightness state of the frame image corresponding to the random index is bright or dark, adjusting the spot check interval to be an initial spot check interval.
4. The method as claimed in claim 1, wherein the step of adjusting the exposure time, the gamma enable, the automatic gain, and the external light source status in real time according to the illumination brightness status to perform automatic light supplement comprises:
when the illumination brightness state is bright, sequentially adjusting an external light source, automatic gain, gamma enabling and exposure time;
and when the illumination brightness state is dark, sequentially adjusting the exposure time, the gamma enable, the automatic gain and the external light source, or sequentially adjusting the exposure time, the gamma enable, the external light source and the automatic gain.
5. The method for full-automatic supplementary lighting based on the warp knitting machine flaw detection system as claimed in claim 1 or 4, wherein the step of adjusting the exposure time in real time comprises:
closing the automatic exposure;
acquiring an upper exposure time limit and a lower exposure time limit;
adjusting the exposure time according to the illumination brightness state, wherein,
setting a reduction interval of the exposure time and judging whether the exposure time reaches the lower limit of the exposure time when the illumination brightness state is bright, reducing the exposure time according to the reduction interval when the exposure time does not reach the lower limit of the exposure time, keeping the exposure time when the exposure time is judged to be yes,
and when the illumination brightness state is dark, setting an increase interval of exposure time and judging whether the exposure time reaches an upper limit of the exposure time, if not, increasing the exposure time according to the increase interval, and if so, keeping the exposure time.
6. The method for full-automatic supplementary lighting based on the warp knitting machine flaw detection system as claimed in claim 1 or 4, wherein the step of adjusting the gamma enabling in real time comprises:
starting gamma enabling;
acquiring an upper gamma limit and a lower gamma limit of the gamma-enabled gamma value;
adjusting the gamma value according to the illumination brightness state, wherein,
when the illumination brightness state is bright, judging whether the gamma value reaches an upper gamma limit, increasing the gamma value when the illumination brightness state is not bright, keeping the gamma value when the illumination brightness state is bright,
and when the illumination brightness state is dark, judging whether the gamma value reaches a lower gamma limit, reducing the gamma value when the gamma value does not reach the lower gamma limit, and keeping the gamma value when the gamma value is judged to be yes.
7. The method for full-automatic supplementary lighting based on the warp knitting machine flaw detection system as claimed in claim 1 or 4, wherein the step of adjusting the automatic gain in real time comprises:
adjusting the automatic gain according to the illumination brightness state, wherein,
when the illumination brightness state is bright, closing the automatic gain and judging whether the gain value is 1, if not, subtracting 1 from the gain value, if so, stopping decreasing the gain value,
and when the illumination brightness state is dark, turning on the automatic gain and keeping the automatic gain until the gain value reaches the maximum value.
8. The method for full-automatic supplementary lighting based on the warp knitting machine flaw detection system as claimed in claim 1 or 4, wherein the step of adjusting the external light source in real time comprises:
acquiring a voltage minimum value and a voltage maximum value of a power supply voltage of the external light source;
dividing the suppliable voltage into a plurality of levels of supply voltages according to the voltage minimum and maximum;
adjusting the external light source according to the illumination brightness state, wherein,
when the illumination brightness state is bright, judging whether the power supply voltage reaches the minimum voltage value, if not, reducing the power supply voltage of the external light source according to the multistage power supply voltage, if so, keeping the power supply voltage,
and when the illumination brightness state is dark, judging whether the power supply voltage reaches the maximum voltage value, increasing the power supply voltage of the external light source according to the multistage power supply voltage when the power supply voltage does not reach the maximum voltage value, and keeping the power supply voltage when the power supply voltage is judged to be yes.
9. The utility model provides a full-automatic light filling device based on tricot machine flaw detecting system which characterized in that includes:
the image acquisition module is used for acquiring frame images according to the detection intervals;
the brightness detection module is used for detecting the illumination brightness of the frame image so as to identify the illumination brightness state of the frame image;
the detection processing module is used for adjusting the detection interval to be an initial detection interval when the illumination brightness state of the frame image is bright or dark, adjusting exposure time, gamma enabling, automatic gain and an external light source state in real time to perform automatic light supplement, constructing a detection interval and tracking the illumination brightness state of the frame image in the detection interval when the illumination brightness state of the frame image is normal, and increasing the detection interval if the illumination brightness state mode of the frame image in the detection interval is normal and the normal times are greater than a threshold value, wherein the illumination brightness state mode is normal and means that the number of interested areas in the normal interval in the frame image is larger than the total number of the interested areas.
10. The full-automatic supplementary lighting device based on warp knitting machine flaw detection system of claim 9, characterized by further comprising:
the spot check detection module is used for randomly extracting frame images in a non-detection interval according to a spot check interval, carrying out illumination brightness detection on the randomly extracted frame images to identify the illumination brightness state of the frame images, if the illumination brightness state of all the randomly extracted frame images is normal, increasing the spot check interval, if the illumination brightness state of the frame images is bright or dark, adjusting the spot check interval to be an initial spot check interval, wherein the non-detection interval refers to a time period between two adjacent detections.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636852.1A CN112738412B (en) | 2020-12-31 | 2020-12-31 | Full-automatic light supplementing method and device based on warp knitting machine flaw detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011636852.1A CN112738412B (en) | 2020-12-31 | 2020-12-31 | Full-automatic light supplementing method and device based on warp knitting machine flaw detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112738412A CN112738412A (en) | 2021-04-30 |
| CN112738412B true CN112738412B (en) | 2022-08-16 |
Family
ID=75608651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011636852.1A Active CN112738412B (en) | 2020-12-31 | 2020-12-31 | Full-automatic light supplementing method and device based on warp knitting machine flaw detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112738412B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093015A (en) * | 2022-01-21 | 2022-02-25 | 杭州魔点科技有限公司 | Intelligent light supplementing method for face recognition, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013250A (en) * | 2006-01-30 | 2007-08-08 | 索尼株式会社 | Exposure control apparatus and image pickup apparatus |
| CN109474791A (en) * | 2018-11-20 | 2019-03-15 | 深圳市趣创科技有限公司 | Image shot by camera controls exposure method, device, terminal and storage medium |
| WO2020062749A1 (en) * | 2018-09-30 | 2020-04-02 | 北京微播视界科技有限公司 | Image processing method and apparatus, and electronic device and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101761947B1 (en) * | 2012-12-06 | 2017-07-26 | 삼성전기주식회사 | Device and method for reducing blooming of camera image |
| CN104702849B (en) * | 2014-01-10 | 2018-03-30 | 杭州海康威视数字技术股份有限公司 | A kind of thermal camera and its infrared lamp luminance regulating method |
| US11614322B2 (en) * | 2014-11-04 | 2023-03-28 | Pixart Imaging Inc. | Camera having two exposure modes and imaging system using the same |
| KR20180078361A (en) * | 2016-12-29 | 2018-07-10 | (주)캠시스 | Method and apparatus of noticing objects around a vehicle |
| CN108439109B (en) * | 2018-05-08 | 2019-12-27 | 江苏威尔曼科技有限公司 | Elevator hall outward-arriving indicator lamp device capable of self-adapting to ambient brightness |
-
2020
- 2020-12-31 CN CN202011636852.1A patent/CN112738412B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013250A (en) * | 2006-01-30 | 2007-08-08 | 索尼株式会社 | Exposure control apparatus and image pickup apparatus |
| WO2020062749A1 (en) * | 2018-09-30 | 2020-04-02 | 北京微播视界科技有限公司 | Image processing method and apparatus, and electronic device and storage medium |
| CN109474791A (en) * | 2018-11-20 | 2019-03-15 | 深圳市趣创科技有限公司 | Image shot by camera controls exposure method, device, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112738412A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101287073B (en) | Adaptive acquiring method of lightness stabilized image from machine vision system in variable irradiation surroundings | |
| CN101582991B (en) | Method and device for processing image | |
| CN112837302B (en) | Method and device for monitoring state of die, industrial personal computer, storage medium and system | |
| EP1808018B1 (en) | Image sensor annotation method and apparatus | |
| CN112738412B (en) | Full-automatic light supplementing method and device based on warp knitting machine flaw detection system | |
| CN109344864B (en) | Image processing method and device for dense object | |
| CN112906529A (en) | Face recognition light supplementing method and device, face recognition equipment and face recognition system | |
| CN113870233B (en) | Binding yarn detection method, computer equipment and storage medium | |
| CN111289538A (en) | PCB element detection system and detection method based on machine vision | |
| CN111815623A (en) | Power transmission line cotter pin missing identification method | |
| CN102129689B (en) | Method for modeling background based on camera response function in automatic gain scene | |
| CN109030499A (en) | A kind of device and method preventing defect counts repeat count suitable for target defect continuous on-line detection | |
| CN1327392C (en) | Device and method for image pick-up | |
| CN112560779B (en) | Method and equipment for identifying overflow of feeding port and feeding control system of stirring station | |
| CN114581824A (en) | Method for identifying abnormal behaviors of sorting center based on video detection technology | |
| CN111062379A (en) | Identification error-proofing recognition method, device, storage medium and system | |
| CN116823795A (en) | Defect detection method and device for rubber product, electronic equipment and storage medium | |
| US20140063570A1 (en) | Method for detecting the width and position of documents using image information in a large- format scanner system | |
| CN109255291A (en) | A kind of machining center breaking alarm system | |
| CN111709932B (en) | Method for detecting paper defects from coarse to fine | |
| CN101930591B (en) | Image processing method for removing backgrounds | |
| CN113781407A (en) | Screw detection method, device and computer-readable storage medium | |
| CN102601950A (en) | Method and system for monitoring and detecting target based on fuzzy algorithm | |
| CN111064897B (en) | Exposure evaluation value statistical method and imaging equipment | |
| CN105812622A (en) | Information processing method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |