CN115050082A - Light filling monitoring system based on infrared laser lamp - Google Patents

Light filling monitoring system based on infrared laser lamp Download PDF

Info

Publication number
CN115050082A
CN115050082A CN202210966360.1A CN202210966360A CN115050082A CN 115050082 A CN115050082 A CN 115050082A CN 202210966360 A CN202210966360 A CN 202210966360A CN 115050082 A CN115050082 A CN 115050082A
Authority
CN
China
Prior art keywords
infrared light
lamp
unit
light supplement
module
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.)
Granted
Application number
CN202210966360.1A
Other languages
Chinese (zh)
Other versions
CN115050082B (en
Inventor
章锐华
王养明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen 3km Photoelectric Technology Co ltd
Original Assignee
Shenzhen 3km Photoelectric Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen 3km Photoelectric Technology Co ltd filed Critical Shenzhen 3km Photoelectric Technology Co ltd
Priority to CN202210966360.1A priority Critical patent/CN115050082B/en
Publication of CN115050082A publication Critical patent/CN115050082A/en
Application granted granted Critical
Publication of CN115050082B publication Critical patent/CN115050082B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/10Image acquisition
    • G06V10/12Details of acquisition arrangements; Constructional details thereof
    • G06V10/14Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/141Control of illumination
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40Control techniques providing energy savings, e.g. smart controller or presence detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

The invention relates to the technical field of light supplement lamps, and discloses a light supplement monitoring system based on an infrared laser lamp, which comprises: the system comprises a sampling module, an extraction module, an identification module, a processing module and an infrared light supplementing lamp, wherein the sampling module acquires real-time motion parameters of a monitoring video stream and a target vehicle in the monitoring video stream, and can be used for a subsequent identification module to identify and divide the current front-row face region of the target vehicle.

Description

Light filling monitoring system based on infrared laser lamp
Technical Field
The invention relates to the technical field of supplementary lighting, in particular to a supplementary lighting monitoring system based on an infrared laser lamp.
Background
The light filling lamp is also called as a camera light filling lamp for monitoring, and is mainly used for providing auxiliary light for shooting under the condition of lacking light so as to obtain reasonable pictures, and the monitoring light filling lamp can be widely used for night license plate light filling illumination of a bayonet electronic police snapshot system and can also be used for snapshot in parking lots and the like or systems for detecting license plates.
Some existing camera light supplementing lamps comprise infrared laser light supplementing lamps, video monitoring is conducted at night for auxiliary lighting, video monitoring equipment can obtain clear and exquisite high-quality night vision monitoring pictures in dark environments even under the conditions of full darkness and no light, the camera light supplementing lamps are mainly applied to light supplementing of a license plate recognition monitoring system, successful application of the camera light supplementing lamps in various industries such as intelligent traffic systems, access management systems, public security image frame systems and mobile police systems is achieved, automatic recognition of license plates in 24 hours in all weather is achieved, and images are stable and clear.
Although the infrared ray is the non-visible light wavelength, it has obvious heating effect to human body tissue, so can not directly shine people's eye, and some visible light filling lamps can disturb driver's sight when directly carrying out the light filling to the vehicle in addition, produce danger easily, current light filling monitoring system also can not accomplish automatically to carry out the light filling to the vehicle in addition, and degree of automation is lower.
Disclosure of Invention
The invention aims to provide a light supplement monitoring system based on an infrared laser lamp, which solves the following technical problems:
how to provide a light filling monitoring system that can carry out the light filling to the vehicle automatically and do not hinder people's eye.
The purpose of the invention can be realized by the following technical scheme:
a light filling monitoring system based on infrared laser lamp includes:
the sampling module is used for acquiring the real-time motion parameters of the monitoring video stream and the target vehicle;
the extraction module is used for acquiring a sampling frame according to the monitoring video stream;
the recognition module is used for acquiring the current front-row face area of the target vehicle according to the sampling frame;
the processing module is used for acquiring an estimated front-row face area according to the real-time motion parameters and the current front-row face area;
the infrared light supplement lamp group is connected with the processing module and used for reducing the irradiation power of the pre-estimated front row face area within the preset time;
wherein the surveillance video stream includes at least one of the target vehicles.
According to the technical scheme, the sampling module acquires the real-time motion parameters of the target vehicle in the monitoring video stream, the follow-up recognition module can recognize and divide the current front-row face area of the target vehicle, the target vehicle may have higher motion speed, and the recognition module also needs certain time for recognizing and dividing the current front-row face area, so that the processing module is required to predict the possible position of the front-row face area when the infrared light supplement lamp group irradiates according to the motion speed in the real-time motion parameters, namely, the front-row face area is predicted, and then the irradiation power of the front-row face area is reduced by adjusting the infrared light supplement lamp group, so that the adverse effect on human eyes is reduced to the maximum extent, and humanized light supplement irradiation is achieved.
As a further scheme of the invention: the sampling module comprises a shooting unit and a speed detection unit;
the shooting unit is used for acquiring the monitoring video stream, and the speed detection unit is used for acquiring the real-time motion parameters; the real-time motion parameters include a motion speed and a motion acceleration of the target vehicle.
Through the technical scheme, when the movement speed or the movement acceleration is lower than the preset value, the processing module can stop the calculation of the pre-estimated front row face area, and the calculation resources are saved.
As a further scheme of the invention: the identification module comprises an identification unit and a marking unit;
the identification unit is a trained neural network model and is used for judging whether a judgment result of the target vehicle exists in the sampling frame, if the judgment result does not exist, the work of the speed detection unit is suspended, and if not, the speed detection unit and the marking unit are started;
the marking unit is used for adding a marking contour line in the sampling frame, and the area surrounded by the marking contour line is the current front-row face area.
Through the technical scheme, the neural network model adopted in the invention can adopt a Convolutional Neural Network (CNN), the convolutional neural network is the most popular neural network model for the image classification problem, and the acquisition modes of the training sample and the sampling frame are the same, wherein the difference is that the training sample has one more step of manual labeling compared with the sampling frame; when the target vehicle does not exist, the speed monitoring unit is suspended, so that the calculation force can be saved.
As a further scheme of the invention: the maximum irradiation range of the infrared light supplement lamp group is consistent with the shooting range of the shooting unit;
the processing module comprises:
the picture processing unit is used for carrying out grid division on the sampling frame and distributing a unique identification code to each grid;
the coincidence judgment unit is used for acquiring the unique identification code of the grid through which the mark contour line passes;
the infrared light supplement lamp group comprises a standard infrared light supplement lamp and a driving unit, the standard infrared light supplement lamp comprises a plurality of light emitting units, and each light emitting unit is provided with a driving code associated with the corresponding grid;
and the driving unit drives the light-emitting unit corresponding to the driving code to reduce the irradiation power.
Through the technical scheme, each grid in the sampling frame corresponds to the irradiation area of each light-emitting unit, the one-to-one correspondence between the unique identification code and the drive code can facilitate the drive control of the drive unit, errors can be avoided, and as long as the grids through which the mark contour lines pass need to be reduced in irradiation power, the adverse effect on human eyes can be avoided.
As a further scheme of the invention: the infrared light supplement lamp set comprises a plurality of standby infrared light supplement lamps connected with the driving unit, the standby infrared light supplement lamps are different from the standard infrared light supplement lamps in installation positions, and the standby infrared light supplement lamps are the same as the standard infrared light supplement lamps in maximum irradiation range.
Through the technical scheme, the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are completely identical in structure and driving mode, only the installation position is different from that of the standard infrared light supplementing lamp, but the ground areas irradiated by the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are identical, so that the light emitting unit in the standby infrared light supplementing lamp can be connected with the driving unit in a mode which is the same as that of the standard infrared light supplementing lamp; the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are switched by the driving unit, so that on one hand, the rapid temperature rise and the service life reduction caused by the noise of only one standard infrared light supplementing lamp can be avoided, on the other hand, the standard infrared light supplementing lamp can be defined to be directed to the front windshield of the target vehicle, and on the other hand, the standby infrared light supplementing lamp is arranged on the running side face of the target vehicle;
even the calculation of the specific real position of the current front-row face region is not accurate enough, the influence of the light supplementing lamp on the driver of the target vehicle is not large enough, the standby infrared light supplementing lamp is located on the side face of the target vehicle, the influence on human eyes is small, the effect of supplementing light to the side face of the human face can be achieved, and the shooting quality effect of the features of the human face in the cockpit except for the human eyes is improved.
As a further scheme of the invention: the driving unit is used for randomly switching and driving the standby infrared light supplementing lamp and the standard infrared light supplementing lamp, and the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are guaranteed to be identical in working time within a preset time period.
Through above-mentioned technical scheme, so, can guarantee that the operating duration of reserve infrared light filling lamp and the infrared light filling lamp of standard is the same as far as possible, reduce the operating pressure and the temperature control degree of difficulty of single light filling lamp to improve the whole life-span of infrared light filling banks, reduce use cost.
As a further scheme of the invention: the driving unit sends a switching preparation signal before switching the standby infrared light supplement lamp and the standard infrared light supplement lamp;
the identification module further comprises a statistical unit, when the driving unit sends a switching preparation signal, the statistical unit drives the extraction module to obtain an odd number of sampling frames from the monitoring video stream, and the identification unit outputs a corresponding number of judgment results according to the odd number of sampling frames;
and the statistical unit counts the judgment result with the largest probability as the final judgment result.
Through the technical scheme, the neural network model can have quite high accuracy and recognition accuracy, but depends on the training process, so that the requirement on the number of training samples is high, and the anti-interference capacity of the recognition unit can be improved due to the diversification of the training samples; the infrared light supplementing lamp groups irradiated at different angles can bring different sampling frames, so that the infrared light supplementing lamp groups supplemented with light from different angles can improve the number and diversity of training samples in a training stage, and the identification unit trained on the basis has higher confidence; moreover, the possibility of errors of the final judgment result can be further reduced as much as possible through the odd judgment results obtained by the odd sampling frames extracted by the statistical unit, and the identification accuracy of the judgment of the target vehicle is comprehensively improved.
As a further scheme of the invention: the infrared light supplementing lamp set comprises a temperature control monitoring module, the temperature control monitoring module is used for monitoring the temperature information of the standard infrared light supplementing lamp and the standby infrared light supplementing lamp, when the temperature information is larger than a preset threshold value, the corresponding light supplementing lamps stop working, and the other light supplementing lamps continue to perform switching work.
Through the technical scheme, if the temperature of one of the light supplement lamps is too high, the driving unit can exclude the light supplement lamp when the subsequent random switching is used, the operation is analogized once until no light supplement lamp is available, and at the moment, the external support maintenance can be called through the temperature control monitoring module to cool down, so that the continuous and reliable work of the light supplement lamp is guaranteed.
The invention has the beneficial effects that:
(1) the sampling module acquires real-time motion parameters of a target vehicle in a monitoring video stream and the monitoring video stream, and a subsequent recognition module can recognize and divide a current front-row face region of the target vehicle, and the target vehicle may have a higher motion speed and the recognition module also needs a certain time for recognizing and dividing the current front-row face region, so that a processing module is required to predict the possible position of the front-row face region when an infrared light supplement lamp group irradiates according to the motion speed in the real-time motion parameters, namely, the front-row face region is predicted, and then the irradiation power of the predicted front-row face region is reduced by the adjustment of the infrared light supplement lamp group, so that the adverse effect on human eyes is reduced to the maximum extent, and humanized light supplement irradiation is realized;
(2) each grid in the sampling frame corresponds to the irradiation area of each light-emitting unit, the one-to-one correspondence between the unique identification code and the driving code can facilitate the driving control of the driving unit, errors can be avoided, and the irradiation power needs to be reduced as long as the grids through which the marking contour lines pass, so that the adverse effect on human eyes can be avoided;
(3) the structure and the driving mode of the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are completely the same, only the installation position of the standby infrared light supplementing lamp is different from that of the standard infrared light supplementing lamp, but the ground areas irradiated by the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are the same, so that the light emitting unit in the standby infrared light supplementing lamp can be connected with the driving unit in the same way as the standard infrared light supplementing lamp; the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are switched by the driving unit, so that on one hand, the rapid temperature rise and the service life reduction caused by the noise of only one standard infrared light supplementing lamp can be avoided, on the other hand, the standard infrared light supplementing lamp can be defined to be directed to the front windshield of the target vehicle, and on the other hand, the standby infrared light supplementing lamp is arranged on the running side face of the target vehicle; even if the specific actual position of the current front-row face region is not accurately calculated, the influence of the light supplement lamp on a driver of the target vehicle is not large enough, and the standby infrared light supplement lamp is located on the side face of the target vehicle, so that the influence on eyes is small, the effect of supplementing light to the side face of the face can be achieved, and the shooting quality effect of the features of the face in the cockpit except for the eyes is improved;
(4) therefore, the working time lengths of the standby infrared light supplementing lamp and the standard infrared light supplementing lamp can be ensured to be the same as much as possible, and the working pressure and temperature control difficulty of a single light supplementing lamp are reduced, so that the overall service life of the infrared light supplementing lamp group is prolonged, and the use cost is reduced;
(5) the design is that although the neural network model can have quite high accuracy and recognition accuracy, the neural network model depends on the training process, the requirement on the number of training samples is high, and the anti-interference capability of the recognition unit can be improved due to the diversification of the training samples; the infrared light supplementing lamp groups irradiated at different angles can bring different sampling frames, so that the infrared light supplementing lamp groups supplemented with light from different angles can improve the number and diversity of training samples in a training stage, and the identification unit trained on the basis has higher confidence; moreover, the possibility of errors of the final judgment result can be further reduced as much as possible through the odd judgment results obtained by the odd sampling frames extracted by the statistical unit, and the identification accuracy of the judgment of the target vehicle is comprehensively improved.
Drawings
The invention will be further described with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of module connection of the fill-in light monitoring system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a fill-in light monitoring system based on an infrared laser lamp, including:
the sampling module is used for acquiring the real-time motion parameters of the monitoring video stream and the target vehicle;
the extraction module is used for acquiring a sampling frame according to the monitoring video stream;
the recognition module is used for acquiring the current front-row face area of the target vehicle according to the sampling frame;
the processing module is used for acquiring an estimated front-row face area according to the real-time motion parameters and the current front-row face area;
the infrared light supplement lamp group is connected with the processing module and used for reducing the irradiation power of the pre-estimated front row face area within the preset time;
wherein the surveillance video stream includes at least one of the target vehicles.
According to the technical scheme, the sampling module acquires the real-time motion parameters of the target vehicle in the monitoring video stream, the follow-up recognition module can recognize and divide the current front-row face area of the target vehicle, the target vehicle may have higher motion speed, and the recognition module also needs certain time for recognizing and dividing the current front-row face area, so that the processing module is required to predict the possible position of the front-row face area when the infrared light supplement lamp group irradiates according to the motion speed in the real-time motion parameters, namely, the front-row face area is predicted, and then the irradiation power of the front-row face area is reduced by adjusting the infrared light supplement lamp group, so that the adverse effect on human eyes is reduced to the maximum extent, and humanized light supplement irradiation is achieved.
As a further scheme of the invention: the sampling module comprises a shooting unit and a speed detection unit;
the shooting unit is used for acquiring the monitoring video stream, and the speed detection unit is used for acquiring the real-time motion parameters; the real-time motion parameters include a motion speed and a motion acceleration of the target vehicle.
Through the technical scheme, when the movement speed or the movement acceleration is lower than the preset value, the processing module can stop the calculation of the pre-estimated front row face area, and the calculation resources are saved.
As a further scheme of the invention: the identification module comprises an identification unit and a marking unit;
the identification unit is a trained neural network model and is used for judging whether a judgment result of the target vehicle exists in the sampling frame, if the judgment result does not exist, the work of the speed detection unit is suspended, and if not, the speed detection unit and the marking unit are started;
the marking unit is used for adding a marking contour line in the sampling frame, and the area surrounded by the marking contour line is the current front-row face area.
Through the technical scheme, the neural network model adopted in the invention can adopt a Convolutional Neural Network (CNN), the convolutional neural network is the most popular neural network model for the image classification problem, and the training sample and the sampling frame are required to be obtained in the same way, and the difference is that the training sample has one more step of manual labeling compared with the sampling frame; when the target vehicle does not exist, the speed monitoring unit is suspended, so that the calculation force can be saved.
As a further scheme of the invention: the maximum irradiation range of the infrared light supplement lamp group is consistent with the shooting range of the shooting unit;
the processing module comprises:
the picture processing unit is used for carrying out grid division on the sampling frame and distributing a unique identification code to each grid;
the coincidence judgment unit is used for acquiring the unique identification code of the grid through which the mark contour line passes;
the infrared light supplement lamp group comprises a standard infrared light supplement lamp and a driving unit, the standard infrared light supplement lamp comprises a plurality of light emitting units, and each light emitting unit is provided with a driving code associated with the corresponding grid;
and the driving unit drives the light-emitting unit corresponding to the driving code to reduce the irradiation power.
Through the technical scheme, each grid in the sampling frame corresponds to the irradiation area of each light-emitting unit, the one-to-one correspondence of the unique identification code and the drive code can facilitate the drive control of the drive unit, errors can be avoided, and as long as the grids through which the contour lines pass are marked need to be reduced in irradiation power, adverse effects on human eyes can be avoided.
As a further scheme of the invention: the infrared light supplement lamp set comprises a plurality of standby infrared light supplement lamps connected with the driving unit, the standby infrared light supplement lamps are different from the standard infrared light supplement lamps in installation positions, and the standby infrared light supplement lamps are the same as the standard infrared light supplement lamps in maximum irradiation range.
Through the technical scheme, the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are completely identical in structure and driving mode, only the installation position is different from that of the standard infrared light supplementing lamp, but the ground areas irradiated by the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are identical, so that the light emitting unit in the standby infrared light supplementing lamp can be connected with the driving unit in a mode which is the same as that of the standard infrared light supplementing lamp; the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are switched by the driving unit, so that on one hand, the rapid temperature rise and the service life reduction caused by the noise of only one standard infrared light supplementing lamp can be avoided, on the other hand, the standard infrared light supplementing lamp can be defined to be directed to the front windshield of the target vehicle, and on the other hand, the standby infrared light supplementing lamp is arranged on the running side face of the target vehicle;
even the calculation of the specific real position of the current front-row face region is not accurate enough, the influence of the light supplementing lamp on the driver of the target vehicle is not large enough, the standby infrared light supplementing lamp is located on the side face of the target vehicle, the influence on human eyes is small, the effect of supplementing light to the side face of the human face can be achieved, and the shooting quality effect of the features of the human face in the cockpit except for the human eyes is improved.
As a further scheme of the invention: the driving unit is used for randomly switching and driving the standby infrared light supplementing lamp and the standard infrared light supplementing lamp, and the standby infrared light supplementing lamp and the standard infrared light supplementing lamp are guaranteed to be identical in working time within a preset time period.
Through above-mentioned technical scheme, so, can guarantee that the operating duration of reserve infrared light filling lamp and the infrared light filling lamp of standard is the same as far as possible, reduce the operating pressure and the temperature control degree of difficulty of single light filling lamp to improve the whole life-span of infrared light filling banks, reduce use cost.
As a further scheme of the invention: the driving unit sends a switching preparation signal before switching the standby infrared light supplement lamp and the standard infrared light supplement lamp;
the identification module further comprises a statistical unit, when the driving unit sends a switching preparation signal, the statistical unit drives the extraction module to obtain an odd number of sampling frames from the monitoring video stream, and the identification unit outputs a corresponding number of judgment results according to the odd number of sampling frames;
and the statistical unit counts the judgment result with the largest probability as the final judgment result.
Through the technical scheme, the neural network model can have quite high accuracy and recognition accuracy, but depends on the training process, so that the requirement on the number of training samples is high, and the anti-interference capacity of the recognition unit can be improved due to the diversification of the training samples; the infrared light supplementing lamp groups irradiated at different angles can bring different sampling frames, so that the infrared light supplementing lamp groups supplemented with light from different angles can improve the number and diversity of training samples in a training stage, and the identification unit trained on the basis has higher confidence; moreover, the possibility of errors of the final judgment result can be further reduced as much as possible through the odd judgment results obtained by the odd sampling frames extracted by the statistical unit, and the identification accuracy of the judgment of the target vehicle is comprehensively improved.
As a further scheme of the invention: the infrared light filling lamp set comprises a temperature control monitoring module, the temperature control monitoring module is used for monitoring the temperature information of the standard infrared light filling lamp and the standby infrared light filling lamp, when the temperature information is larger than a preset threshold value, the corresponding light filling lamp stops working, and the switching work is continued by other light filling lamps.
Through the technical scheme, if one of the light supplement lamps has the condition of overhigh temperature, the driving unit can exclude the light supplement lamp when the subsequent random switching is used, the operation can be analogized once until the light supplement lamp is unavailable, at the moment, the external support maintenance can be called through the temperature control monitoring module, the temperature is reduced, and the continuous and reliable work of the light supplement lamp is guaranteed
While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.

Claims (8)

1. The utility model provides a light filling monitoring system based on infrared laser lamp which characterized in that includes:
the sampling module is used for acquiring real-time motion parameters of the monitoring video stream and the target vehicle;
the extraction module is used for acquiring a sampling frame according to the monitoring video stream;
the recognition module is used for acquiring the current front row face area of the target vehicle according to the sampling frame;
the processing module is used for acquiring an estimated front-row face area according to the real-time motion parameters and the current front-row face area;
the infrared light supplement lamp group is connected with the processing module and used for reducing the irradiation power of the pre-estimated front row face area within the preset time;
wherein the surveillance video stream includes at least one of the target vehicles.
2. A fill-in light monitoring system based on an infrared laser lamp as described in claim 1, wherein the sampling module comprises a shooting unit and a speed detection unit;
the shooting unit is used for acquiring the monitoring video stream, and the speed detection unit is used for acquiring the real-time motion parameters; the real-time motion parameters include a motion speed and a motion acceleration of the target vehicle.
3. The infrared laser lamp-based supplementary lighting monitoring system as claimed in claim 2, wherein the identification module comprises an identification unit and a marking unit;
the identification unit is a trained neural network model and is used for judging whether a judgment result of the target vehicle exists in the sampling frame, if the judgment result does not exist, the work of the speed detection unit is suspended, and if not, the speed detection unit and the marking unit are started;
the marking unit is used for adding a marking contour line in the sampling frame, and the area surrounded by the marking contour line is the current front-row face area.
4. A fill-in light monitoring system based on an infrared laser lamp as described in claim 3, wherein a maximum irradiation range of the infrared fill-in light group is consistent with a shooting range of the shooting unit;
the processing module comprises:
the picture processing unit is used for carrying out grid division on the sampling frame and distributing a unique identification code to each grid;
the coincidence judgment unit is used for acquiring the unique identification code of the grid through which the mark contour line passes;
the infrared light supplementing lamp group comprises a standard infrared light supplementing lamp and a driving unit, the standard infrared light supplementing lamp comprises a plurality of light emitting units, and each light emitting unit is provided with a driving code associated with the corresponding grid;
and the driving unit drives the light-emitting unit corresponding to the driving code to reduce the irradiation power.
5. A light supplement monitoring system based on an infrared laser lamp as claimed in claim 4, wherein the infrared light supplement lamp set includes a plurality of standby infrared light supplement lamps connected to the driving unit, the standby infrared light supplement lamps are installed at different positions from the standard infrared light supplement lamps, and the maximum irradiation ranges of the standby infrared light supplement lamps and the standard infrared light supplement lamps are the same.
6. A light supplement monitoring system based on an infrared laser lamp as claimed in claim 5, wherein the driving unit switches and drives the standby infrared light supplement lamp and the standard infrared light supplement lamp randomly, so as to ensure that the standby infrared light supplement lamp and the standard infrared light supplement lamp work at the same time within a preset time period.
7. The infrared laser lamp-based supplementary lighting monitoring system as claimed in claim 6, wherein the driving unit sends a switch preparation signal before switching between the standby infrared supplementary lighting lamp and the standard infrared supplementary lighting lamp;
the identification module further comprises a statistical unit, when the driving unit sends a switching preparation signal, the statistical unit drives the extraction module to obtain an odd number of sampling frames from the monitoring video stream, and the identification unit outputs a corresponding number of judgment results according to the odd number of sampling frames;
and the statistical unit counts the judgment result with the largest probability as the final judgment result.
8. A light supplement monitoring system based on an infrared laser lamp as claimed in claim 6, wherein the infrared light supplement lamp set comprises a temperature control monitoring module, the temperature control monitoring module is used for monitoring temperature information of the standard infrared light supplement lamp and the standby infrared light supplement lamp, when the temperature information is larger than a preset threshold value, the corresponding light supplement lamp stops working, and other light supplement lamps continue to perform switching work.
CN202210966360.1A 2022-08-12 2022-08-12 Light filling monitoring system based on infrared laser lamp Active CN115050082B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210966360.1A CN115050082B (en) 2022-08-12 2022-08-12 Light filling monitoring system based on infrared laser lamp

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210966360.1A CN115050082B (en) 2022-08-12 2022-08-12 Light filling monitoring system based on infrared laser lamp

Publications (2)

Publication Number Publication Date
CN115050082A true CN115050082A (en) 2022-09-13
CN115050082B CN115050082B (en) 2022-12-09

Family

ID=83167453

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210966360.1A Active CN115050082B (en) 2022-08-12 2022-08-12 Light filling monitoring system based on infrared laser lamp

Country Status (1)

Country Link
CN (1) CN115050082B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104394359A (en) * 2014-11-05 2015-03-04 浪潮(北京)电子信息产业有限公司 Security monitoring method and system based on infrared and face recognition technologies
CN104751197A (en) * 2015-04-22 2015-07-01 安徽金赛弗信息技术有限公司 Device and method for recognizing faces of drivers during vehicle running on basis of video analysis
CN106503707A (en) * 2016-10-21 2017-03-15 浙江宇视科技有限公司 Licence plate recognition method and device under the conditions of a kind of infrared light filling
CN108090428A (en) * 2017-12-08 2018-05-29 广西师范大学 A kind of face identification method and its system
CN108764217A (en) * 2018-07-16 2018-11-06 南安市明誓汽配贸易有限公司 A kind of vehicle access mechanism convenient for adjusting based on recognition of face
US20200124842A1 (en) * 2018-10-19 2020-04-23 Getac Technology Corporation License plate capturing device and method for removing target covering license plate capturing device
CN113490316A (en) * 2021-06-30 2021-10-08 浙江大华技术股份有限公司 Light filling system and light filling lamp
CN114859629A (en) * 2022-04-14 2022-08-05 浙江高信技术股份有限公司 Light supplement lamp, light supplement control system and method for vehicle snapshot

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104394359A (en) * 2014-11-05 2015-03-04 浪潮(北京)电子信息产业有限公司 Security monitoring method and system based on infrared and face recognition technologies
CN104751197A (en) * 2015-04-22 2015-07-01 安徽金赛弗信息技术有限公司 Device and method for recognizing faces of drivers during vehicle running on basis of video analysis
CN106503707A (en) * 2016-10-21 2017-03-15 浙江宇视科技有限公司 Licence plate recognition method and device under the conditions of a kind of infrared light filling
CN108090428A (en) * 2017-12-08 2018-05-29 广西师范大学 A kind of face identification method and its system
CN108764217A (en) * 2018-07-16 2018-11-06 南安市明誓汽配贸易有限公司 A kind of vehicle access mechanism convenient for adjusting based on recognition of face
US20200124842A1 (en) * 2018-10-19 2020-04-23 Getac Technology Corporation License plate capturing device and method for removing target covering license plate capturing device
CN113490316A (en) * 2021-06-30 2021-10-08 浙江大华技术股份有限公司 Light filling system and light filling lamp
CN114859629A (en) * 2022-04-14 2022-08-05 浙江高信技术股份有限公司 Light supplement lamp, light supplement control system and method for vehicle snapshot

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
马文龙: "关于动车组受电弓视频监控系统补光灯自动关闭问题的研究以及对策", 《科技创新导报》 *

Also Published As

Publication number Publication date
CN115050082B (en) 2022-12-09

Similar Documents

Publication Publication Date Title
CN102638013B (en) The target image identification power transmission state monitoring system of view-based access control model attention mechanism
US7016518B2 (en) Vehicle license plate imaging and reading system for day and night
CN110730552B (en) Intelligent urban electric power illumination monitoring system and control method thereof
US20130229518A1 (en) Systems and methods that employ object recognition
KR101052803B1 (en) Intelligent lighting control system and accident management system using camera
CN110730531A (en) LED street lamp remote light-changing control system
CN102424016A (en) Automobile headlamp automatic control system based on machine vision
CN109448437A (en) Pedestrains safety street crossing prompt system and method towards driver
CN112533336A (en) Street lamp illumination intelligent regulation system based on thing networking
KR102362304B1 (en) Traffic accidents notification system for accident sensing and secondary traffic accident prevention
CN110944429B (en) In-vehicle light control method and device and vehicle
CN113438779A (en) Method for triggering street lamp illumination intensity adjustment based on image
CN110956813B (en) Intelligent light supplementing vehicle snapshot method based on multi-target tracking radar
CN113490312A (en) Intelligent illumination dimming method and system for expressway tunnel
CN206524010U (en) A kind of motor line is through automatic reminding system during crossing
CN115050082B (en) Light filling monitoring system based on infrared laser lamp
CN108569196A (en) A kind of intelligent vehicle head lamp lighting device based on SFV and DLP
CN114760740A (en) Vehicle headlight automatic regulating system based on singlechip
KR102180916B1 (en) Artificial Intelligence image analysis system and method thereof
CN113112866A (en) Intelligent traffic early warning method and intelligent traffic early warning system
CN111489558B (en) License plate recognition method and system
CN209625456U (en) Tunnel curved road safety suggestion device
CN114867168A (en) Light sensation-based automatic light adjusting method
CN106183964A (en) A kind of new automobile long-and-short distant light intelligent switching system
CN113126653B (en) Tunnel illumination method and system based on unmanned aerial vehicle

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