Multi-band self-adaptive regional intelligent light-supplementing imaging method and multi-band self-adaptive regional intelligent light-supplementing imaging device

Abstract

The invention provides a multi-band adaptive regional intelligent light supplement imaging method and device. The device comprises a main support, an angle adjusting support, lamp beads of three bands (810 nm, 910 nm and 1060 nm) and corresponding cameras. According to the equipment, twelve groups of lamp beads are arranged in three rows and four columns, each group comprises lamp beads of three wave bands, and the lamp beads are installed at different inclination angles, so that accurate light supplement for different imaging areas is realized. The system detects the brightness of each area of the image in real time, automatically identifies the overexposure area and the reason thereof, and intelligently adjusts the light supplementing wave band and intensity. When the strong correlation light is detected, a non-interference wave band is automatically switched; and when it is detected that the reflected light is too strong, the light supplementing intensity of the corresponding area is reduced. According to the method, the problems of environment light source interference and non-uniform self light supplement reflection are effectively avoided, the imaging quality at night and in a low-visibility environment is greatly improved, and the perception capability and safety of an automatic driving system are remarkably enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent supplementary lighting imaging, and particularly relates to a multi-band adaptive sub-region intelligent supplementary lighting imaging method and a supplementary lighting device, which provide high-quality data for a night driving system and ensure night driving safety. Background Art

[0002] In road traffic, the accident risk of night driving is much higher than that of day driving. Although the traffic flow at night is less, the occurrence probability of major traffic accidents is twice that of the day, and more than one-third of major accidents occur at night. The main safety hazard of night driving comes from the insufficient road lighting conditions. Especially on roads with mixed traffic of people and vehicles, it is crucial to detect pedestrians and obstacles in time. Although improving the headlight illumination can alleviate this problem, strong light may cause the weakening of the eyesight of oncoming vehicles or pedestrians, thus increasing the risk of accidents. Therefore, the application of night driving assistance systems becomes particularly important, especially those based on infrared imaging technology.

[0003] There are two main types of infrared imaging technology: passive infrared imaging and active near-infrared imaging. Passive technology relies on natural radiation and does not require additional light sources, which is suitable for applications with high requirements for equipment. However, its equipment cost is relatively high. Active technology enhances illumination through near-infrared light sources, with lower costs. However, its imaging effect is easily interfered by high-reflectivity materials on the road, and when meeting an oncoming vehicle, the same-band illumination light source of the oncoming vehicle will also interfere with the imaging effect. Therefore, how to solve the above-mentioned light interference problems, especially strong light and reflected light interference, has become the core challenge faced by night driving assistance systems.

[0004] In the prior art, Patent No. ZL200710018954.5 provides a multi-wavelength automatic switching vehicle night driving assistance system, aiming to improve the clarity of night imaging by combining variable-wavelength infrared illumination and a hyperfocal infrared imaging optical system. This system can automatically switch near-infrared light sources of different bands to avoid light source interference when meeting an oncoming vehicle. However, the prior art does not fully consider the interference of reflected light, resulting in problems with imaging quality under complex lighting conditions.

[0005] In addition, Patent No. ZL201210257215.2 proposes a vehicle night driving assistance system, which avoids light interference when meeting an oncoming vehicle through a variable-wavelength near-infrared illumination module and automatic band switching, and cooperates with a hyperfocal imaging optical module and an ECU signal processing module to ensure clear imaging. This system has achieved certain results in solving the interference when meeting an oncoming vehicle, but does not consider the impact of reflected light on imaging quality.

[0006] Patent No. ZL 201110009335.6 introduces an infrared filter switching mechanical device, which uses a stepper motor for driving the switching, reduces the volume of the device, and is applicable to miniaturized lenses. Although the device ensures accurate switching of the filter through a position detector, the mechanical adjustment speed is slow, unable to meet the real-time requirements in driving scenarios, and the impact of reflected light on imaging is not considered.

[0007] To solve the problems of low efficiency, high cost, and complex operation of traditional manual light supplement methods, Patent No. ZL202011636852.1 provides a full-automatic light supplement method and device based on a warp knitting machine defect detection system. This method realizes full-automatic light supplement by collecting frame images and performing light intensity detection, automatically adjusting the exposure time, gamma enable, automatic gain, and external light source status, and dynamically adjusting the detection interval to reduce hardware costs and consumption and improve detection performance.

[0008] Patent No. ZL 201720830972.2 introduces a strong light suppression device, which detects the ambient light intensity through a light intensity sensor and automatically adjusts the light intensity to suppress strong light interference. Although the device can effectively reduce the impact of strong light, the mechanical adjustment speed is slow, unable to adapt to the real-time requirements in night driving, and the light intensity cannot be adjusted in different regions, unable to cope with the problem of strong light interference in local regions affecting imaging.

[0009] To solve the problem of overexposure or underexposure in some regions of imaging, Patent No. ZL201711378137.0 proposes a light supplement method and device. This method uses multiple supplementary lights, divides the shooting area into multiple sub-regions, and separately adjusts the light intensity of the supplementary lights corresponding to each sub-region, so that the difference between the brightness value of each sub-image and the brightness value of the overall image is controlled within a certain range. Although this technology can solve the problem of local overexposure or underexposure caused by its own light intensity, it cannot cope with the direct interference of other light sources in the same band.

[0010] Patent No. ZL202010400682.0 provides a light supplement adjustment method, device, electronic device, and storage medium, which realizes fine adjustment of light supplement by combining the adjustment of exposure parameters and the adjustment of the light intensity value of the supplementary light, greatly improving the shooting effect, especially applicable to night or dim light scenarios. However, this technology can only adjust the overall brightness and darkness of imaging and cannot cope with uneven light scenarios and adjust in different regions.

[0011] In summary, the first three patents (ZL200710018954.5, ZL201210257215.2, and ZL201110009335.6) are limited to solving the interference problem of collinear light sources in the same band, while the latter four patents (ZL202011636852.1, ZL201720830972.2, ZL201711378137.0, and ZL202010400682.0) can only solve the interference problem of non-uniform ambient light. The prior art fails to simultaneously address the impacts of non-uniform light and collinear light sources in the same band on imaging quality. During night driving, the uncertainty of the lighting environment makes vision-based perception difficult. Therefore, providing clear and stable imaging under complex lighting conditions has become an urgent problem for current technologies. Summary of the Invention

[0012] The objective of the present invention is to provide a multi-band adaptive sub-region intelligent light compensation imaging method and a light compensation device, aiming to solve the problem of the combined impact of non-uniform light and collinear light sources in the same band on imaging quality, provide high-quality data for the night driving system, and ensure night driving safety.

[0013] The objective of the present invention is achieved through the following technical solutions.

[0014] A multi-band adaptive sub-region intelligent light compensation imaging device includes: a condenser lens, a lamp panel, an angle adjustment bracket, a main bracket, a controller, a narrow-band 810nm camera, a narrow-band 910nm camera, a narrow-band 1060nm camera, narrow-band 810nm lamp beads, narrow-band 910nm lamp beads, narrow-band 1060nm lamp beads, a driver, and a detector; among them, the narrow-band 810nm camera, the narrow-band 910nm camera, and the narrow-band 1060nm camera are horizontally installed in the middle of the lower part of the main bracket, and their optical axes are parallel to each other and perpendicular to the installation plane of the main bracket; the lamp beads are divided into three rows and four columns, a total of twelve large groups, and are respectively welded on twelve lamp panels, and the optical axis of each lamp bead is perpendicular to the installation plane of the lamp panel; The twelve lamp panels are respectively fixed on twelve angle adjustment brackets, and the angle adjustment brackets at different positions are installed on the main bracket at different inclination angles and are located above the cameras; The four tilt-mounted angle adjustment brackets in the bottom row cause the light axes of the lamp beads thereon to tilt downward, forming an angle of β degrees with the camera optical axis in the vertical plane; the four tilt-mounted angle adjustment brackets in the middle row cause the light axes of the lamp beads thereon to be in the same horizontal plane as the camera optical axis; the four tilt-mounted angle adjustment brackets in the top row cause the light axes of the lamp beads thereon to tilt upward, forming an angle of β degrees with the camera optical axis in the vertical plane; the three tilt-mounted angle adjustment brackets in the leftmost column cause the light axes of the lamp beads thereon to tilt to the left, forming an angle of α1 degrees with the camera optical axis in the horizontal plane; the three tilt-mounted angle adjustment brackets in the second column from the left cause the light axes of the lamp beads thereon to tilt to the left, forming an angle of α2 degrees with the camera optical axis in the horizontal plane; the three tilt-mounted angle adjustment brackets in the third column from the left cause the light axes of the lamp beads thereon to tilt to the right, forming an angle of α2 degrees with the camera optical axis in the horizontal plane; the three tilt-mounted angle adjustment brackets in the rightmost column cause the light axes of the lamp beads thereon to tilt to the right, forming an angle of α1 degrees with the camera optical axis in the horizontal plane; the lamp beads on the same lamp panel include lamp beads of three bands of 810nm, 910nm, and 1060nm. The lamp beads of each band are connected in series into a group, forming three groups; the three-band group lamp beads on the same lamp panel are powered by the same driver at different times. At any moment, only one band group of lamp beads is powered on. The band and intensity are determined by the detector, and the driver is controlled by the controller to achieve the switching of different band group lamp beads and the control of the illumination intensity; a condenser lens is covered on each lamp bead; the condensing angle of the condenser lens is smaller than the imaging view angle of the camera. It converges the light and disperses it to cover the entire imaging area, realizing independent supplementary lighting and light intensity adjustment for different imaging areas.

[0015] Further, for the multi-band adaptive sub-region intelligent supplementary lighting imaging device described above, the emission center bands of the three narrow-band near-infrared lamp beads used are 810nm, 910nm, and 1060nm respectively, and the half-wave width of each is 20nm; the imaging center wavelengths of the three narrow-band near-infrared cameras are 810nm, 910nm, and 1060nm respectively, and the imaging band ranges are all 20nm (i.e., the center wavelength ±10nm); there is a large band interval between the three imaging bands to avoid mutual interference between bands, and it has high luminous efficiency and imaging quantum efficiency, thereby improving the imaging quality.

[0016] Further, for the multi-band adaptive sub-region intelligent supplementary lighting imaging device, the horizontal and vertical field of view angles of the camera are H and V respectively, and H is greater than V. Then, the condensing angle 2γ of the condensing lens is determined according to the field of view angle of the camera, satisfying the formula 2γ = 3V / 5, where γ is the half angle of the light beam divergence of the condensing lens; the included angle α1 in the horizontal plane of the lamp panel is 2(H - 2γ) / 3, the included angle α2 in the horizontal plane is 2(H - 2γ) / 9, and the included angle β in the vertical plane is 3(V - 2γ) / 4; so as to make the imaging area have a progressive light coverage from the center to the edge, ensuring uniform light intensity distribution within the imaging area.

[0017] Further, for the multi-band adaptive sub-region intelligent supplementary lighting imaging device, a driver is composed of two-stage amplifiers of a triode and a MOS tube; a single-chip microcomputer is used as a controller to provide a PWM signal for the base of the triode of the driver to adjust the drive current of each group of lamp beads.

[0018] The multi-band adaptive sub-region intelligent supplementary lighting imaging method includes the following core steps: an imaging device including a narrow-band near-infrared camera with three different bands and narrow-band near-infrared lamp beads corresponding to the bands is used to acquire a scene image; the brightness mean value of the image frame is detected in real time in sub-regions, and the imaging regions of reflected light and opposed light are automatically identified; deep learning technology is used to distinguish different types of light sources, and according to the existence of a strong opposed light illumination region, the band for the next frame of imaging and supplementary lighting is determined to achieve multi-band adaptive intelligent supplementary lighting imaging and solve the interference of opposed light illumination in the same band as imaging; the supplementary lighting intensity of the corresponding region is adjusted according to the brightness mean value of each region to achieve sub-region intelligent supplementary lighting, ensuring uniform supplementary lighting imaging and avoiding local overexposure; where: the central wavelengths of the narrow-band near-infrared camera and narrow-band near-infrared lamp beads with three different bands are 810nm, 910nm, and 1060nm respectively; the imaging device includes multiple groups of lamp beads with three different bands distributed at different spatial positions, and these lamp beads are installed at different angles, capable of providing independent lighting adjustment for each imaging region and switching the imaging band.

[0019] Further, for the multi-band adaptive sub-region intelligent supplementary lighting imaging method, its specific working process is as follows: Step 1: Initialization, set the detector to collect the image of the 810nm band camera; set the controller to control the driver to supply the maximum current to the lamp bead group of this band; sequentially enter Step 2; Step 2: The detector collects a frame of image from the camera of the current working band, and detects the brightness mean value of each region in the image; divide the regions from dark to bright according to the brightness mean value into 5 brightness levels; count the number N of regions with a brightness level exceeding level 3; sequentially enter Step 3; Step 3: The detector determines that N > 0. If it is greater, it indicates the existence of a local strong light imaging area, then proceed to Step 4 to further determine the cause of the strong light imaging area; otherwise, jump to Step 9. Step 4: The detector calls the deep learning model to predict whether the area with a brightness exceeding level 3 is caused by reflected light or counter light imaging; and counts the number M of imaging areas with a brightness exceeding level 3 caused by strong counter light; then sequentially proceed to Step 5. Step 5: The detector determines that M > 0. If it is greater, it indicates the existence of a strong interference light source in the environment with the same wavelength band as the imaging, then jump to Step 10 to switch the imaging and illumination wavelength bands to avoid interference from strong light sources with the same wavelength band on imaging; otherwise, proceed to Step 6. Step 6: Check whether the detector has received a stop signal. If it has, proceed to Step 7; otherwise, jump to Step 11. Step 7: The detector sets to collect camera images in the 810nm wavelength band; sets the controller to control the driver not to supply power to the lamp bead group in this wavelength band; and sends a working wavelength band signal to the controller; then sequentially proceed to Step 8. Step 8: The detector stops detecting. Step 9: The detector sets the working wavelength band to 810nm, sets the maximum current supply for each area's lamp bead group; and sends a working wavelength band signal to the controller; uses the 810nm wavelength band lamp beads and camera to achieve efficient and low - energy - consumption imaging; jump to Step 12. Step 10: The detector automatically selects and switches the working wavelength band to any one of the other two wavelength bands, and sends the working wavelength band signal to the controller; jump to Step 12. Step 11: The detector determines the drive current intensity for each area according to the brightness level of each area and sends it to the controller; among them, the current intensities corresponding to the 5 brightness levels [0, 50), [50, 100), [100, 150), [150, 200), [200, 255) are 2.0A, 1.5A, 1.0A, 0.5A, and 0A respectively. The current intensity is inversely proportional to the brightness, and as the brightness level increases, the set current decreases sequentially; jump to Step 12. Step 12: The controller controls the driver to supply power to the lamp beads in the current working wavelength band according to the working wavelength band and the current intensity of each area; after completing one round of imaging supplementary lighting, return to Step 2.

[0020] Furthermore, the multi-band adaptive sub-region intelligent light compensation imaging method is mainly applied to the fields of security monitoring, autonomous driving, and intelligent transportation in low visibility environments such as at night, in haze, and in heavy rain. By dynamically switching the light compensation and imaging of different bands, it effectively solves the problems of environmental light source interference and uneven illumination, overcomes the technical defects of traditional single-band imaging systems such as local overexposure, overall underexposure, and light source interference under complex lighting conditions, significantly improves the information acquisition ability, contrast, and clarity of images, enhances the target recognition accuracy and real-time perception ability of autonomous driving systems in harsh environments, and thus improves traffic safety.

[0021] Furthermore, the device for implementing the multi-band adaptive sub-region intelligent light compensation imaging method is the above-mentioned multi-band adaptive sub-region intelligent light compensation imaging device; among them, the detector performs the functions of sub-region real-time detection of the average image brightness, automatic identification of the reflected light and the imaging region of the opposing light; the controller performs the functions of determining the next frame of imaging and light compensation band according to the strong opposing region and adjusting the light compensation intensity according to the average brightness; the driver performs the functions of switching different band lamp beads and controlling the light intensity; the narrow-band camera and the narrow-band lamp beads respectively implement multi-band adaptive intelligent light compensation imaging and sub-region intelligent light compensation.

[0022] The present invention proposes a new type of intelligent dimming method and device, which solves the influence of multiple interference factors such as the opposing light source of the same band and the uneven reflection of the environment on its own light source on the imaging quality through intelligent sub-region light compensation and band switching. The specific technologies include: Intelligent band switching: Call the deep learning model to predict whether the high-brightness region is the reflected light or the imaging of the opposing light; in the face of strong opposing light, automatically switch the imaging and illumination bands to avoid overlapping with the interfering environmental light source bands, thereby improving the imaging quality; Sub-region light intensity adjustment: In the face of strong reflected light, by real-time detecting the local exposure intensity of different regions in the imaging picture, automatically identifying the overexposed regions, and intelligently adjusting the light compensation intensity, so as to ensure uniform imaging and avoid overexposure; Intelligent light compensation imaging device: The present invention designs a precise sub-region intelligent light compensation device that can adjust the light compensation intensity in real time according to the light intensity difference of different regions, improve the imaging effect, and support switching the light compensation band.

[0023] Through the above technologies, the present invention not only considers the interference from the environmental opposing light source of the same band, but also solves the problem of uneven reflection of the environment on its own light source. By means of intelligent adjustment and band switching technologies, it effectively reduces the influence of complex lighting on the imaging quality, significantly improves the imaging quality of the night driving assistance system, ensures clear and stable visual information is obtained in complex traffic environments, and thus improves the safety of night driving. Description of the Drawings

[0024] Figure 1 It is the front view of the intelligent fill-light imaging device; Figure 2 It is the top view of the intelligent fill-light imaging device; Figure 3 It is the left view of the intelligent fill-light imaging device; Figure 4 It is the flowchart of the intelligent fill-light imaging method; Figure 5 It is the intelligent fill-light control block diagram.

[0025] Figures 1 - 3 In Fig., 1 is a condenser lens, 2 is a lamp panel, 3 is an angle adjustment bracket, 4 is a main bracket, 5 is a controller, 6 is a narrow-band 810nm camera, 7 is a narrow-band 910nm camera, 8 is a narrow-band 1060nm camera, 9 is a narrow-band 1060nm lamp bead, 10 is a narrow-band 910nm lamp bead, 11 is a narrow-band 810nm lamp bead, 12 is a driver, and 13 is a detector. Specific embodiments

[0026] In order to make the objectives, technical solutions and advantages of the present invention clearer and more definite, the present invention will be further described in detail below with reference to the accompanying drawings and by way of examples.

[0027] A multi-band adaptive sub-region intelligent fill-light imaging method and fill-light device proposed by the present invention include a condenser lens 1, a lamp panel 2, an angle adjustment bracket 3, a main bracket 4, a controller 5, a narrow-band 810nm camera 6, a narrow-band 910nm camera 7, a narrow-band 1060nm camera 8, a 1060nm narrow-band near-infrared lamp bead 9, a 910nm narrow-band near-infrared lamp bead 10, a narrow-band 810nm lamp bead 11, a driver 12 and a detector 13. As Figures 1 - 3As shown in the figure, the horizontal field of view angle and vertical field of view angle of the narrowband 810nm camera 6, narrowband 910nm camera 7, and narrowband 1060nm camera 8 are 30 degrees and 20 degrees respectively. They are installed at the lower center of the main bracket 4. The optical axes of the three-band cameras are parallel to each other and perpendicular to the installation plane of the main bracket 4. The lamp beads are divided into three rows and four columns, a total of twelve large groups, and are respectively welded on twelve lamp panels 2. The optical axis of each lamp bead is perpendicular to the installation plane of the lamp panel 2. The twelve lamp panels 2 are respectively fixed on twelve angle adjustment brackets 3, and the angle adjustment brackets 3 are installed on the main bracket 4 at different inclination angles and are located above the cameras. The four inclined angle adjustment brackets 3 in the bottom row make the optical axes of the lamp beads on them offset downward by β = 6 degrees in the vertical direction relative to the optical axes of the cameras. The four inclined angle adjustment brackets 3 in the middle row make the optical axes of the lamp beads on them offset by 0 degrees in the vertical direction relative to the optical axes of the cameras. The four inclined angle adjustment brackets 3 in the top row make the optical axes of the lamp beads on them offset upward by β = 6 degrees in the vertical direction relative to the optical axes of the cameras. The three inclined angle adjustment brackets 3 in the leftmost column make the optical axes of the lamp beads on them offset to the left by an angle α1 = 12 degrees in the horizontal direction relative to the optical axes of the cameras. The three inclined angle adjustment brackets 3 in the second column from the left make the optical axes of the lamp beads on them offset to the left by α2 = 4 degrees in the horizontal direction relative to the optical axes of the cameras. The three inclined angle adjustment brackets 3 in the third column from the left make the optical axes of the lamp beads on them offset to the right by α2 = 4 degrees in the horizontal direction relative to the optical axes of the cameras. The three inclined angle adjustment brackets 3 in the rightmost column make the optical axes of the lamp beads on them offset to the right by an angle α1 = 12 degrees in the horizontal direction relative to the optical axes of the cameras. A large group of lamp beads on the same lamp panel 2 is further divided into three bands, and the lamp beads of the same band group are connected in series into a small group. The lamp beads of the three band groups on the same lamp panel 2 are powered by the same driver 12 in a time-sharing manner, and at the same time, only one band group of lamp beads is powered on. The controller 5 controls the powered-on band and its intensity to realize the control of the lighting and extinguishing of the three band groups of lamp beads and the light intensity. A condenser lens 1 is covered on each lamp bead. The condensing angle of the condenser lens 1 is less than the imaging view angle of the camera, and in this case, it is taken as 12 degrees, aiming to converge the light and disperse it to cover the entire imaging area to realize independent supplementary lighting and light intensity adjustment for different imaging areas.

[0028] Specifically, the three bands of the narrowband near-infrared lamp beads and cameras are 810nm, 910nm, and 1060nm respectively; the half-wave width of the light emitted by the three kinds of lamp beads is 20nm; the imaging wavelength range of the three narrowband near-infrared cameras is 20nm (i.e., the central wavelength ± 10nm); there is a large wavelength interval between the three imaging bands to avoid mutual interference between the bands, and they have high luminous efficiency and imaging quantum efficiency to ensure imaging quality.

[0029] The present invention also provides another embodiment, a multi-band adaptive sub-region intelligent fill light imaging method. First, the brightness mean value of the imaging picture is detected in real time in sub-regions, and the overexposed or underexposed regions are automatically identified. Then, the fill light intensity of the corresponding region is adjusted according to the brightness mean value of each region to ensure uniform fill light imaging and avoid local overexposure. Finally, according to the brightness mean value of the entire picture, the imaging and fill light bands are automatically switched. The intelligent fill light imaging device cooperates with the intelligent fill light imaging method, which not only avoids interference from strong light sources of the same band in the environment, but also avoids uneven reflection interference of the environment on its own fill light, thereby improving the imaging quality.

[0030] Specifically, the working process is as Figure 4 shown, and its control block diagram is as Figure 5 shown. The specific working process is analyzed as follows: Step 1: Initialization. Set the detector 13 to collect the camera image in the 810nm band; set the controller 5 to control the driver 12 to supply the maximum current (for example, 2.0A) to the lamp bead group of this band. Step 2: The detector 13 collects a frame of image from the camera in the current working band, and detects the brightness mean value of each region in the image; divides the regions into 5 brightness levels from dark to bright according to the brightness mean value; counts the number N of regions with a brightness level exceeding level 3. Based on the collected image, the detector 13 will calculate the brightness mean value of each imaging region. The system divides the brightness mean value into 5 levels: Brightness level 1: [0, 50) (very dark); Brightness level 2: [50, 100) (dark); Brightness level 3: [100, 150) (medium); Brightness level 4: [150, 200) (bright); Brightness level 5: [200, 255] (very bright); Brightness level 1 indicates the weakest light, and level 5 indicates the strongest light. Region division and analysis: According to the brightness grading, different regions in the image will be assigned to different brightness levels. The system will analyze the regions with a brightness level exceeding level 3. Usually, there may be strong light interference in these regions. Step 3: The detector 13 determines that N>0. If it is greater, it indicates that there are local strong light imaging regions, then go to step 4 to further determine the cause of the strong light imaging regions, otherwise jump to step 9. Step 4: The detector 13 calls the deep learning model to predict whether the area with a brightness exceeding level 3 is reflected light or counter light imaging. The model can automatically analyze and identify different lighting types; and count the number M of imaging areas with a brightness exceeding level 3 caused by counter light; then sequentially proceed to Step 5. Through training, this deep learning model can distinguish the reflected light areas (such as ground reflection or object surface reflection) and counter light areas (such as direct light generated by other light sources) in the image. The model receives image data as input and outputs the classification results of the lighting types of each area. Through deep learning analysis, if a strong interference light source (i.e., a strong light source with the same imaging band) in the environment is detected, the system will automatically switch to another band for imaging and supplementary lighting. For example, when a strong interference light source is detected in the 810nm band, the system will switch to the 910nm or 1060nm band to avoid interference; Step 5: The detector 13 determines whether M>0. If it is greater, it indicates that there is a strong interference light source with the same band as the imaging in the environment, then jumps to Step 10 to switch the imaging and lighting bands to avoid interference from strong light sources of the same band during imaging. Otherwise, it proceeds to Step 8; Step 6: Whether the detector 13 receives a stop signal. If it does, it proceeds to Step 7; otherwise, it jumps to Step 11; Step 7: The detector 13 sets to collect the camera image of the 810nm band; sets the controller 5 to control the driver 12 not to supply power to the lamp bead group of this band; and sends a working band signal to the controller 5; Step 8: The detector 13 stops detecting; Step 9: The detector 13 sets the working band to 810nm and sets the maximum current supply for each area lamp bead group; and sends a working band signal to the controller 5. This is because the lamp beads in the 810nm band have the highest luminous efficiency, and the quantum efficiency of the narrowband near-infrared camera in the 810nm band is also the highest. Therefore, its imaging quality at night is the best and the energy consumption is the lowest; Step 10: The detector 13 automatically selects and switches the working band to any one of the other two bands and sends the working band signal to the controller 5; Step 11: The detector 13 determines the driving current intensity of each area according to the high and low brightness levels of each area. There is an inverse relationship between them, and it sends it to the controller 5; The relationship between the current and the brightness is inverse, that is, the higher the brightness, the lower the current intensity. The specific relationship is as follows: Corresponding to brightness level 1 ([0, 50)), the current intensity is 2.0A; Corresponding to brightness level 2 ([50, 100)), the current intensity is 1.5A; Corresponding to brightness level 3 ([100, 150)), the current intensity is 1.0A; Corresponding to brightness level 4 ([150, 200)), the current intensity is 0.5A; Corresponding to brightness level 5 ([200, 255]), the current intensity is 0A (that is, turning off the lamp beads in this area); The controller 5 adjusts the current intensity according to the brightness level. For example, in an area with a brightness level of 1 (very dark), the current is 2.0A to ensure that the area receives sufficient light; while in an area with a brightness level of 5 (very bright), the current is reduced to 0A to avoid overexposure; Step 12: The controller 5 controls the driver 12 to supply power to the lamp beads of the current working band according to the working band and the current intensity of each area; During the entire process, the system continuously adjusts the current, band switching and fill light intensity through real-time feedback from the detector to ensure uniform illumination of the entire imaging area and avoid local overexposure or insufficient light.

[0031] During the nighttime autonomous driving process, the 810nm band lamp beads have high luminous efficiency, can provide clear imaging effects, and have low power consumption. Through the multi-band adaptive intelligent fill light device, the autonomous driving system can cope with complex nighttime lighting conditions, improve environmental perception capabilities, and ensure driving safety.

[0032] In severe weather conditions (such as haze or heavy rain), the system can automatically adjust the fill light intensity to ensure that the camera obtains clear images in low-visibility environments and avoid driving safety affected by insufficient light or reflected light.

[0033] This embodiment describes in detail the specific implementation of the multi-band adaptive sub-region intelligent fill light imaging device, including brightness classification, current adjustment, application of deep learning methods, and band switching. Through these optimizations and controls, the system can achieve efficient imaging fill light and ensure imaging quality under different lighting conditions, which has important application value in autonomous driving and intelligent transportation.

Claims

1. A multi-band adaptive sub-region intelligent supplementary light imaging device, characterized in that Comprising: A condenser lens (1), a lamp panel (2), an angle adjustment bracket (3), a main bracket (4), a controller (5), a narrowband 810 nm camera (6), a narrowband 910 nm camera (7), a narrowband 1060 nm camera (8), narrowband 1060 nm lamp beads (9), narrowband 910 nm lamp beads (10), narrowband 810 nm lamp beads (11), a driver (12), and a detector (13); Among them, the narrowband 810 nm camera (6), the narrowband 910 nm camera (7), and the narrowband 1060 nm camera (8) are horizontally installed in the middle of the lower part of the main bracket (4), and their optical axes are parallel to each other and perpendicular to the installation plane of the main bracket (4); The lamp beads are divided into three rows and four columns, a total of twelve large groups, and are respectively welded on twelve lamp panels (2), and the optical axis of each lamp bead is perpendicular to the installation plane of the lamp panel (2); The twelve lamp panels (2) are respectively fixed on twelve angle adjustment brackets (3), and the angle adjustment brackets (3) at different positions are installed on the main bracket (4) at different inclination angles, located above the camera, so as to realize sub-region intelligent supplementary lighting; The lamp beads welded on the same lamp panel (2) include lamp beads of three wavelength bands with central wavelengths of 810 nm, 910 nm, and 1060 nm. The lamp beads of each wavelength band are connected in series into a small group, forming three small groups, so as to realize multi-band adaptive intelligent imaging; The lamp beads of the three wavelength bands on the same lamp panel (2) are powered by the same driver (12) at different times. At any moment, only one wavelength band group of lamp beads is powered on. The wavelength band and intensity are determined by the detector (13), and the controller (5) controls the driver (12) to realize the switching of different wavelength band groups of lamp beads and the control of the illumination intensity; A condenser lens (1) is covered on each lamp bead; the condensing angle of the condenser lens (1) is smaller than the imaging view angle of the camera, and its converging light is scattered and covers the entire imaging area, so as to realize independent supplementary lighting and light intensity adjustment for different imaging areas.

2. The multi-band adaptive sub-region intelligent supplementary light imaging device according to claim 1, wherein The inclination angles of the twelve angle adjustment brackets (3) installed on the main bracket (4) are set as follows: the four inclined angle adjustment brackets (3) in the bottom row make the optical axes of the lamp beads on them incline downward, forming an angle of β degrees with the optical axis of the camera in the vertical plane; The four inclined angle adjustment brackets (3) in the middle row make the optical axes of the lamp beads on them in the same horizontal plane as the optical axis of the camera; The four inclined angle adjustment brackets (3) in the top row make the optical axes of the lamp beads on them incline upward, forming an angle of β degrees with the optical axis of the camera in the vertical plane; The three inclined angle adjustment brackets (3) in the leftmost column make the optical axes of the lamp beads on them incline to the left, forming an angle of α1 degrees with the optical axis of the camera in the horizontal plane; The three inclined angle adjustment brackets (3) in the second left column make the optical axes of the lamp beads on them incline to the left, forming an angle of α2 degrees with the optical axis of the camera in the horizontal plane; The three inclined angle adjustment brackets (3) in the third left column make the optical axes of the lamp beads on them incline to the right, forming an angle of α2 degrees with the optical axis of the camera in the horizontal plane; The three tilt-mounted angle adjustment brackets (3) in the rightmost column tilt the optical axis of the lamp beads thereon to the right, forming an angle of α1 degrees with the optical axis of the camera in the horizontal plane.

3. The multi-band adaptive sub-region intelligent supplementary light imaging device according to claim 1, wherein The emission center wavelengths of the three narrow-band near-infrared lamp beads are 810nm, 910nm, and 1060nm respectively, and the full width at half maximum is 20nm for all; the imaging center wavelengths of the three narrow-band near-infrared cameras are 810nm, 910nm, and 1060nm respectively, and the imaging band ranges are 20nm for all; there is a large band interval between the three imaging bands to avoid mutual interference between bands, and they have high luminous efficiency and imaging quantum efficiency, thereby improving the imaging quality.

4. The multi-band adaptive sub-region intelligent fill light imaging device according to claim 1, wherein, The horizontal and vertical field of view angles of the camera are H and V respectively, and H is greater than V. Then the condensing angle 2γ of the condensing lens (1) is determined according to the camera field of view angle, satisfying the formula 2γ = 3V / 5, where γ is the half angle of beam divergence of the condensing lens (1); the included angle α1 in the horizontal plane of the lamp panel (2) = 2(H - 2γ) / 3, the included angle α2 in the horizontal plane = 2(H - 2γ) / 9, and the included angle β in the vertical plane = 3(V - 2γ) / 4; to make the imaging area have a progressive light coverage from the center to the edge, ensuring uniform light intensity distribution within the imaging area.

5. The multi-band adaptive sub-region intelligent fill light imaging device according to claim 1, wherein Use a two-stage amplifier composed of a triode and a MOS tube to form a driver (12); use a single-chip microcomputer as a controller (5) to provide a PWM signal to the base of the triode of the driver (12) to adjust the drive current of each group of lamp beads.

6. A multi-band adaptive sub-region intelligent supplementary lighting imaging method, characterized in that, Adopt the multi-band adaptive sub-region intelligent supplementary light imaging device described in any one of claims 1 to 5. The method includes the following core steps: use the narrow-band 810nm camera (6), narrow-band 910nm camera (7), narrow-band 1060nm camera (8) and the corresponding narrow-band 1060nm lamp beads (9), narrow-band 910nm lamp beads (10), narrow-band 810nm lamp beads (11) to obtain scene images; detect the brightness mean value of the image screen in real time in sub-regions, and automatically identify the imaging regions of reflected light and opposed light; according to whether there is a strong opposed light region, determine the band for the next frame of imaging and supplementary light, realize multi-band adaptive intelligent supplementary light imaging, and solve the interference of opposed light illumination in the same band as imaging; adjust the supplementary light intensity of the corresponding region according to the brightness mean value of each region, realize sub-region intelligent supplementary light, ensure uniform supplementary light imaging, and avoid local overexposure phenomenon.

7. The multi-band adaptive sub-region intelligent fill light imaging method according to claim 6, characterized in that The specific working process is as follows: Step 1: Initialize, set the detector (13) to collect 810nm band camera images; set the controller (5) to control the driver (12) to supply the maximum current to the lamp bead group of this band; sequentially enter Step 2; Step 2: The detector (13) collects a frame of image from the camera of the current working band, and detects the brightness mean value of each region in the image; divide the regions from dark to bright according to the brightness mean value into 5 brightness levels; count the number N of regions with a brightness level exceeding level 3; sequentially enter Step 3; Step 3: The detector (13) judges that N > 0. If it is greater, it indicates that there is a local strong light imaging region, then enter Step 4 to further judge the cause of the strong light imaging region, otherwise jump to Step 9; Step 4: The detector (13) calls the deep learning model to predict whether the area with a brightness exceeding level 3 is reflected light or imaging of opposing light. The model can classify and judge the light type based on image features; and count the number M of imaging areas with a brightness exceeding level 3 caused by opposing light; Proceed to Step 5 in sequence; Step 5: The detector (13) determines that M>0. A value greater than 0 indicates that there is a strong interference light source in the environment with the same wavelength band as the imaging. Then, it jumps to Step 10 to switch the imaging and illumination wavelength bands to avoid interference from strong light sources in the same wavelength band during imaging. Otherwise, it proceeds to Step 6; Step 6: The detector (13) determines whether a stop signal is received. If received, it proceeds to Step 7. Otherwise, it jumps to Step 11; Step 7: Set the detector (13) to collect camera images in the 810nm wavelength band; set the controller (5) to control the driver (12) not to supply power to the lamp bead group in this wavelength band; and send a working wavelength band signal to the controller (5); Proceed to Step 8 in sequence; Step 8: The detector (13) stops detection; Step 9: Set the working wavelength band of the detector (13) to 810nm, set the maximum current supply for each area's lamp bead group; and send a working wavelength band signal to the controller (5); Use the 810nm wavelength band lamp beads and camera to achieve efficient and low-energy imaging; Jump to Step 12; Step 10: The detector (13) automatically selects and switches the working wavelength band to any one of the other two wavelength bands and sends the working wavelength band signal to the controller (5); Jump to Step 12; Step 11: The detector (13) determines the driving current intensity for each area based on the brightness level of each area and sends it to the controller (5); Among them, the current intensities corresponding to the 5 brightness levels [0,50), [50,100), [100,150), [150,200), [200,255) are 2.0A, 1.5A, 1.0A, 0.5A, and 0A respectively. The current intensity is inversely proportional to the brightness. As the brightness level increases, the set current decreases in sequence; Jump to Step 12; Step 12: The controller (5) controls the driver (12) to supply power to the lamp beads in the current working wavelength band according to the working wavelength band and the current intensity of each area; After completing one round of imaging supplementary lighting, return to Step 2.

8. The multi-band adaptive sub-region intelligent fill light imaging method according to claim 6, characterized in that, It is mainly applied to the fields of security monitoring, autonomous driving, and intelligent transportation in low visibility environments such as at night, in haze, and in heavy rain.

Images