610 results about "Dark zone" patented technology

The invention discloses a high-precision image processing method and system based on illumination adaptive compensation, and relates to the technical field of computer vision and image processing, and the method comprises the steps: inputting an original image, and dividing the image into a high-frequency edge layer, an intermediate-frequency texture layer and a low-frequency illumination layer through a multi-scale residual network; acquiring illumination intensity, color temperature and scene categories in real time by using an ambient light sensor and a scene semantic segmentation model, and generating dynamic compensation parameters; carrying out dynamic range expansion on a low-frequency illumination layer based on a physical illumination model, and adjusting the weight of highlight suppression and dark area enhancement through a self-adaptive S-shaped exposure curve; a double-branch generative adversarial network is adopted, noise suppression and super-resolution reconstruction are carried out on the high-frequency layer, and texture detail enhancement is carried out on the intermediate-frequency layer; aligning the data of the depth camera and the infrared sensor with the visible light image through a cross-modal fusion module; and performing tone mapping on the fused image based on human visual characteristics, and outputting an enhanced image with a high dynamic range and reserved details.

The invention discloses an image enhancement method and system in a complex coal mine environment, and relates to the technical field of image processing, and the method comprises the steps: carrying out the preprocessing of a collected coal mine image of a target region, and dividing the coal mine image into different semantic regions, including a bright region, a dark region and a dust shielding region, through a deep learning semantic segmentation model; according to semantic region characteristics, a differentiation enhancement strategy is made; a traditional Retinex model is improved, non-local mean filtering is introduced, and an illumination component and a reflection component are decomposed through pixel similarity matching. According to the method, the image is divided into the bright area, the dark area and the dust shielding area through the deep learning semantic segmentation model, differential enhancement strategies are formulated according to different area characteristics, detail distortion caused by global adjustment is avoided, local contrast suppression is adopted in the bright area, illumination compensation is enhanced in the dark area, and the image quality is improved. Noise diffusion of the dust shielding area is inhibited through edge preservation smoothing, the image quality of each area is remarkably improved, and it is ensured that image details in a complex coal mine environment are clear and visible.

The invention provides an intelligent control method for a floodlight illumination system, and the method comprises the steps: obtaining an environment surface roughness coefficient, spectral reflection distribution and spatial geometric change data, determining the wall surface material absorptivity and shielding region coordinates, and obtaining environment reflection characteristics and shielding distribution data; analyzing shielding boundary sharpness and shielding angle distribution according to the spatial geometric change and the coordinates of the shielding area, calculating a luminous flux distribution curve of a local dark area, and judging whether the influence range of the dark area exceeds a preset threshold range or not; calculating the illumination coverage integrity according to the updated light field distribution and polarization reflection characteristics, determining the boundary sharpness of a light beam, and obtaining a light field uniformity parameter; and according to the light field uniformity parameter and the shielding thermal radiation effect, calculating and optimizing light field parameters.

The invention relates to a light spot uniformity optimization method and system for a high-precision VCSEL device, and the method comprises the following steps: carrying out the light field collection of a light-emitting surface of the VCSEL device, obtaining the intensity distribution of original light spots, analyzing the non-uniformity of each light-emitting unit, and extracting the non-uniformity characteristics of the light spots. And carrying out deviation cause analysis based on the characteristics, and identifying device structure deviation parameters. According to the method, an etching process is optimized, a corrected oxidized aperture configuration scheme is obtained, near-field light field simulation is carried out by adopting a finite difference time domain method, and optimized light field distribution is verified and predicted. And finally, adaptive compensation design is carried out on the Bragg reflector structure based on a prediction result, light field regulation and control are realized, target light spot uniformity distribution is finally obtained, and the problem that systematic analysis and feedback control on non-uniformity causes of a light emitting unit layer in a device are lacked in the prior art is solved. And local bright spots or dark areas are caused.

The invention provides a machine vision-based titanium alloy VAR smelting molten pool edge-reaching control method, which comprises the following steps: after calibration and correction by using an industrial camera, collecting the molten pool morphology of a vacuum arc remelting furnace VAR; the obtained molten pool landform picture is processed, and the molten pool topography surface gray level image is divided into a bright area, a gradual change area and a dark area; extracting a sub-pixel edge by using a Canny operator and a Zernike moment, and fitting a molten pool edge by using a least square circle fitting algorithm; subtracting the obtained crucible edge from the molten pool morphology edge, and calculating to obtain the distance from the molten pool edge to the crucible; and comparing the obtained distance from the edge of the molten pool to the crucible with a threshold value, and judging whether the molten pool reaches the edge or not. Visual judgment of operators is replaced with machine vision, dependence on artificial experience is reduced, titanium alloy VAR smelting control is simpler and more convenient, VAR smelting is more intelligent and automatic, product stability is improved, cost is reduced, and product competitiveness is improved.

The invention discloses an additive manufacturing deposition layer morphology measuring device and method based on intelligent image reconstruction. The method comprises the steps that a molten pool area image and vibration data are collected; the collected molten pool area image and vibration data are input into a depth self-encoder to be processed, and a reconstructed image is generated through the depth self-encoder; the quality and the stability of the reconstructed image are evaluated by using the PSNR and the SSIM; if the image quality does not reach the preset standard, the system calculates an optimal illumination angle and a camera position required for improving the image quality; the angles and the positions of the LED light and the camera are adjusted through the hollow shaft motor, it is ensured that a light path evenly covers the surface of the molten pool, and all possible illumination dark areas are captured; and if the image quality reaches a preset standard, outputting a reconstructed image. By combining the improved monitoring equipment and the deep learning technology, the challenge faced by the deposition layer morphology test in the laser additive manufacturing process is effectively solved, and the test quality and reliability are improved.

The invention discloses a nighttime image enhancement method based on multidirectional information extraction and color loss optimization, which comprises the following steps: firstly, collecting nighttime and normal light road scene images, constructing a nighttime road image enhancement model based on deep learning, and adopting an image enhancement framework based on GAN and a superficial layer semantic enhanced U-Net network as a generator; the five-layer convolutional network is used as a discriminator, then horizontal-vertical bidirectional differential convolution is used to extract multi-directional information of the image, a local illumination attention module is used to balance dark area brightness and bright area overexposure, and finally an adaptive color loss function is used to recover original colors of the image. The method can effectively solve the problems of image quality reduction, detail loss, color distortion and the like under the low-illumination condition, and is particularly suitable for night scene visual perception improvement in the field of vehicle-assisted automatic driving.

The invention discloses a heat exchanger welding seam image enhancement processing method, and belongs to the technical field of image processing, and the method comprises the steps: S1, collecting a heat exchanger welding seam original image through a preset collection module, and converting the original image into a grayscale image; s2, a processing module is preset, the gray level image is segmented based on a preset dynamic threshold value, and a welding seam area image and a base metal area image are generated; s3, in the welding seam area image, generating a first enhanced image, a second enhanced image and a third enhanced image through a preset generation module; and S4, extracting a reference edge contour of the weld joint area image from the base metal area image, performing pixel-level fusion on the first enhanced image, the second enhanced image and the third enhanced image, and outputting a weld joint image. According to the method, the weld joint area is divided into the highlight area, the dark area and the middle area to be processed respectively, weld pool texture loss caused by strong reflection is effectively restrained, and the problem that details are lost in a highlight scene in an existing method is solved.

The invention discloses a multi-scale Retinex low-illumination image enhancement method based on modified bilateral filtering, and belongs to the field of digital image processing. Aiming at the problems of insufficient image brightness, detail loss, noise interference and color distortion in a low-illumination environment, the invention provides an improved image enhancement algorithm. First, the RGB image is converted into an HSV color space, and the luminance component (V) is separated for subsequent processing to avoid color distortion caused by direct processing of the RGB channel. And then, a corrected bilateral filtering function is adopted as a center surrounding function of a multi-scale Retinex method, a brightness component is enhanced, a halo phenomenon is suppressed, and meanwhile, detail enhancement of a dark region and excessive suppression of a bright region are realized in combination with an improved Gamma transformation function. And for the reflection component, non-local mean filtering denoising is utilized, and image edge details are enhanced in combination with a Laplace operator. In addition, the color of the enhanced image is ensured to be natural and consistent by adaptively adjusting the saturation component. Experimental results show that the brightness and definition of low-illumination images can be remarkably improved, detail information and visual impressions are improved, and the method is suitable for various scenes such as night monitoring, medical image processing and agricultural monitoring. The method has the advantages of being excellent in enhancement effect, high in halo suppression and small in color distortion.

The invention provides a floor wear resistance detection method and system, is applied to the technical field of floor wear detection, and reflects the wear resistance of a floor coating by obtaining the variation of porosity before and after floor wear. When the porosity after abrasion is obtained, a two-dimensional optical image of a to-be-detected surface is collected through multi-direction illumination, and the image is subjected to alignment processing. By analyzing the light and shade change information and the shadow form information of the dark area in different illumination directions, when the light and shade change information of the dark area changes along with the change of the position of the light source and the shadow form information shows the dynamic change of rotation or movement, it is judged that the hole is the floor hole. The discrimination mechanism based on the illumination dynamic change effectively solves the problem that a two-dimensional optical microscope scheme in the prior art cannot distinguish real pores and shallow scratches, and avoids misjudgment of scratches generated by a large amount of wear as pores, thereby significantly improving the accuracy of porosity calculation after wear.

The invention discloses a method for testing short-circuit current of a solar cell. The method comprises the following steps: acquiring a first corresponding relation between the photoluminescence intensity of a standard cell under standard illumination intensity and the electroluminescence intensity of the standard cell under open-circuit voltage; providing a battery piece to be tested; irradiating partial areas of the first surface of the to-be-measured battery piece through a plurality of light sources with different wavelengths, and measuring to obtain bright area luminous intensity of a light receiving area and dark area luminous intensity of a non-light receiving area under the irradiation of the light sources with different wavelengths; according to the first corresponding relation and the luminous intensity of each bright area, obtaining basic electroluminescence intensity corresponding to the luminous intensity of each bright area; obtaining the equivalent external quantum efficiency under the irradiation of each wavelength light source according to the basic electroluminescence intensity and the dark space luminescence intensity corresponding to each wavelength light source; constructing a wavelength-equivalent external quantum efficiency curve; carrying out integral calculation on the wavelength-equivalent external quantum efficiency curve to obtain short-circuit current density, and calculating the short-circuit current of the battery piece to be measured according to the area of the first surface.

The invention relates to a method for determining a degree of soiling of a surface of a photovoltaic module of a solar installation or of a solar power plant, comprising the following steps: a) selecting and providing a defined dark area, positioning a camera having a plurality of color channels or adjusting the surface of the photovoltaic module in such a way that an image representation of the dark area from the viewpoint of a camera having a plurality of color channels appears on the surface of the photovoltaic module, and illuminating the surface of the photovoltaic module with light, wherein a known or predefined illumination situation is produced, b) capturing image data of the surface of the photovoltaic module using the camera, c) determining regions of one image consisting of the image data or of a plurality of images consisting of the image data which show the reflection of the dark area in the surface of the photovoltaic module, d) determining image channel information from the image data by means of at least one first color channel of the camera which images the red or part of the red color spectrum, or by means of at least one first color channel of the camera which images the green or part of the green color spectrum, wherein the image channel information is used to determine image information of the image data for the regions determined in step c) or partial regions of the regions determined in step c), and e) determining the degree of soiling of the surface of the photovoltaic module from the image information for the regions determined in step c) or the partial regions of the regions determined in step c); wherein the image information is compared with reference values of the degree of soiling in a calibration step.

The invention relates to a low-illumination image enhancement method based on multi-mode classification and brightness feedback, and belongs to the field of image processing. The method comprises the following steps of: firstly, training a network, constructing a multi-modal illumination prior feature of an image, inputting the multi-modal feature and a brightness score of the image into an illumination perception classification network, obtaining a local probability value of image brightness, adaptively selecting a local or global enhancement processing method, and generating a fusion weight; in the local enhancement processing, dark area details are enhanced through a multi-scale parallel and double-attention mechanism, in the global enhancement, the brightness is improved by using a symmetric coding-decoding structure and a residual attention block, and linear fusion is performed after the brightness is enhanced; then, the brightness evaluation value of the image is fed back through the lightweight brightness estimation network, and the brightness of the image is enhanced. And optimizing the training network according to the joint loss function of image processing. The method provided by the invention can enhance image texture details and improve image definition under a non-uniform illumination condition and an extremely low illumination condition.

The invention discloses an intelligent identification monitoring and cooperative emergency system, which comprises a main body case, a double-shaft rotating mechanism, an annular light supplementing assembly, an integrated base and an intelligent analysis module, and is characterized in that the main body case comprises a first rotating device, an imaging module and a second rotating device; the double-shaft rotating mechanism comprises a horizontal rotating shaft and a pitching adjusting shaft; the annular light supplementing assembly comprises a light supplementing lamp array and a honeycomb anti-dazzle cover. The integrated base comprises a communication gateway and an emergency controller; the intelligent analysis module comprises an edge calculation unit and a response priority unit. Therefore, the beam splitter prism fuses visible light and infrared thermal imaging coaxial acquisition, the electromagnetic shielding design of the double-shaft rotating mechanism is combined, the imaging precision and stability are improved, the annular light supplementing assembly, the three-color-temperature LED module and the edge calculation unit cooperate, illumination is dynamically adapted, dark space glare is eliminated, an emergency controller hardware-level linkage device triggers instructions according to priorities, and therefore the imaging accuracy and stability are improved. The response time is shortened.

The invention belongs to the technical field of computer vision and image processing, and discloses a low-light image enhancement method and system based on space-frequency domain feature resolution self-adjustment. According to the enhancement method, a feature splitting and splicing process, a space-frequency domain feature resolution self-adjusting network architecture based on an encoder-decoder framework, and a complete processing process from low-light image input to normal illumination image output are provided. According to the method, a multi-scale feature map is further flattened into a two-dimensional matrix, image restoration is carried out from features of different scales through a linear layer and a feedforward neural network, and the integrity of a receptive field is further kept; besides, after the important spatial features are extracted, frequency restoration is carried out on the important area, the common problem that the dark area is excessively enhanced and details of the bright area are lost is effectively solved, and the color fidelity and the structural integrity in the low-illumination scene are better.

The invention provides a control method and a control system for building an independent acoustic space of an automobile cabin, which are applied to the technical field of sound field control of the automobile cabin, and are used for inputting a multi-channel vibration signal acquired in real time into a deep learning noise prediction model to obtain an in-automobile background noise prediction value at a future moment; the prediction noise is filtered by the secondary path estimation model and then is used as a feedforward reference signal for active noise reduction, and the prediction noise and a residual signal collected by a bright area error microphone are jointly used for weight updating of an adaptive filter; the updated filter generates a reverse-phase noise elimination signal and the reverse-phase noise elimination signal is played by a secondary loudspeaker in real time so as to counteract background noise of the bright area; and closed-loop adjustment of the noise reduction effect is formed based on the sound pressure level contrast ratio of the bright and dark areas, so that the independent acoustic space is kept stable in the time-varying environment of vehicle driving. According to the method, the low noise of the bright area and the isolated sound field of the dark area in the vehicle are realized by fusing deep learning noise prediction and active noise control, and the personalized auditory experience in the vehicle can be remarkably improved.

The invention relates to a loudspeaker array multi-objective optimization method and system for sound field partition control, and the method comprises the steps: dividing a sound field region into a bright region and a dark region according to a hearing expectation; constructing a decision variable vector by taking the loudspeaker arrangement candidate points as decision variables; constructing a multi-objective optimization model of multiple objectives about decision variable vectors; solving the multi-objective optimization model by adopting a multi-objective genetic algorithm to obtain a Pareto optimal solution; constructing a linear weighted target planning model based on the expected values of the multiple targets, target function values of the multiple targets corresponding to the Pareto optimal solutions, and weight coefficients of negative deviation variables and positive deviation variables of the target function values relative to the expected values; and solving the linear weighted target planning model to obtain a Pareto optimal solution corresponding to the target function value when the linear weighted target planning model takes the minimum value, and obtaining the optimal position and number of the loudspeaker array. According to the invention, the optimal balance among multiple targets is realized, and the sound field partitioning effect is further improved.

The embodiment of the invention provides a control method for sound partitions in a space, electronic equipment, a vehicle and a medium, and the method comprises the steps: determining a first sound source pulse response of a target sound field, the first sound source pulse response being a pulse response of a preset sound source in front of the target sound field; and based on an electro-acoustic transfer function of a bright area, the first sound source pulse response, an electro-acoustic transfer function of a dark area and an optimization function, determining a driving signal of each loudspeaker, namely, restraining the first sound source pulse response as a pulse response of a preset sound source in front of the target sound field, and finally, determining a more accurate loudspeaker driving signal through an optimization function. Therefore, it is clear that the sound image position of the replay sound field is right ahead of the listener, and the listening comfort is improved.

Vehicle lighting control system, characterized in that it comprises the following: an image capture device configured to capture image information about a vehicle driving ahead; an electronic control unit of the image acquisition device, configured to determine relevant data of a front object based on the image information, wherein the relevant data includes size, position and speed of movement; a light control system configured to determine the properties of the dark zone corresponding to the object in front, based on the vehicle's driving parameters and relevant data, where the driving parameters include the vehicle speed; a projector drive configured to control a projector to project a white screen and create a dark zone in an area of ​​the foreground object based on the properties of the dark zone.

The invention discloses a line light source generation device, and relates to the technical field of laser equipment. The linear light source generating device comprises a vertical cavity surface emitting laser light source and a light guide column, the two ends of the light guide column are provided with an incidence end face and a reflection end face respectively, the peripheral face of the light guide column comprises a reflection side face and a light emitting side face, and the incidence end face and the reflection end face both incline to the axis of the light guide column. The incident end face of the light guide column is obliquely arranged, so that light beams emitted by the vertical cavity surface emitting laser light source are refracted when entering the light guide column from the incident end face, light rays in the light guide column have a complex and zigzag propagation path, the light emitting uniformity of the light emitting side face can be improved, and dark areas and bright spots are reduced; moreover, light loss can be reduced, and light output power is improved.

The invention relates to the technical field of artificial intelligence, and discloses a low-illumination scene-oriented unmanned aerial vehicle imaging data enhancement method, which comprises the following steps of: S1, acquiring unmanned aerial vehicle imaging data and constructing a training data set; s2, data preprocessing based on illumination partition; s3, constructing and training a data enhancement model; and S4, enhancing the imaging data of the unmanned aerial vehicle. The data preprocessing based on the illumination partition in the step S2 comprises the following steps: generating a low-illumination area mask and a medium-illumination area mask based on the brightness information of the low-illumination image; a Gaussian smooth convolution operation is applied to the low-illuminance region identified by the low-illuminance region mask to suppress noise, and an original value is reserved for the medium-illuminance region identified by the medium-illuminance region mask to generate a pre-processed image. The problems of low-illumination image noise amplification and detail loss are solved by generating low-illumination region masks and medium-illumination region masks and respectively adopting noise reduction and retention strategies, and the balance of dark region noise reduction and bright region detail protection is realized.

The utility model provides a multi-lamp-bead intelligent physical therapy lamp. The multi-lamp-bead intelligent physical therapy lamp comprises a control unit, a heat dissipation substrate and a plurality of illumination units. The lighting units are arranged on the heat dissipation substrate in an array mode. The lighting unit comprises a lens and at least two LED lamp beads with different lighting wavelengths, and the lens covers the at least two LED lamp beads; the control unit is electrically connected with the LED lamp beads; when the physiotherapy lamp illuminates, the control unit respectively sends control signals to the LED lamp beads with the same illumination wavelength. The technical problem that illumination is insufficient due to the fact that a dark area is prone to being generated when an existing physiotherapy lamp controls illumination is solved, and the technical effects that the illumination panel and the lens are fully utilized, and dark-area-free and multi-wavelength illumination control is achieved are achieved.

The invention relates to the technical field of holographic materials, and provides a holographic recording medium and a preparation method thereof, a grating, an optical waveguide and equipment, the holographic recording medium comprises a polymerizable monomer and a nanoparticle, the refractive index of the nanoparticle is lower than that of the polymerizable monomer, and the refractive index of the nanoparticle is lower than that of the polymerizable monomer under exposure. The polymerizable monomer in the coherent dark area is migrated to the coherent bright area to participate in the polymerization reaction, and meanwhile, the nanoparticles in the coherent bright area are migrated to the coherent dark area. According to the embodiment of the invention, the refractive index difference between the coherent bright region and the coherent dark region is increased, so that the grating can obtain higher diffraction efficiency.

The invention relates to the technical field of display, in particular to a volume holographic grating raw material system, a volume holographic grating and a preparation method of the volume holographic grating. The volume holographic grating raw material system comprises a photopolymerizable monomer, a liquid crystal, an organic additive and a photoinitiator, the structural formula of the organic additive is A-B, A is a photopolymerizable monomer affinity group, and B is a liquid crystal affinity group. On the basis of a raw material system composed of a photopolymerizable monomer, liquid crystal and a photoinitiator, a novel organic additive is introduced, and the organic additive is beneficial to good phase separation of a PDLC system and increase of the refractive index difference between a bright area and a dark area, so that the refractive index modulation degree of the volume holographic grating is improved, and the display application in the AR / VR field is met.

The COB lamp strip capable of reducing the light-emitting dark area comprises an FPC circuit board, a bonding pad is welded on the FPC circuit board, a plurality of light-emitting chips are welded on the bonding pad in the linear direction of the bonding pad, the light-emitting chips are covered with fluorescent colloid, the fluorescent colloid is of a spherical protruding structure, and the light-emitting dark area is smaller than the light-emitting dark area. The radius of an arc on the outer side of the fluorescent colloid is 1.2-1.8 mm, and the height of the fluorescent colloid is 1.1-1.5 mm. Compared with the prior art, according to the COB lamp strip capable of reducing the light-emitting dark areas, the COB light source is directly welded to the surface of the flexible circuit board, and the outer side of the light-emitting chip is covered with the layer of arc-shaped fluorescent colloid of the spherical structure; the light-emitting chips are arranged on the lamp strip and matched with the fluorescent colloid, so that the brightness of light emitted by the light-emitting chips is higher, the diffusion effect along the arc face of the colloid is better, the range of the light-emitting angle is enlarged, the overall lighting effect of the lamp strip is improved, and the dark space problem of the lamp strip is solved; and the glue consumption can be saved, and the overall production and manufacturing cost is reduced.

The invention discloses an ocular surface illumination treatment device and method, and belongs to the technical field of ophthalmology medical equipment and treatment. The device comprises an infrared camera module, a computer terminal analysis control module, an optical power detection module, a mechanical adjustment module, a safety switch module and an illumination module. Wherein the infrared camera module comprises an infrared CCD (Charge Coupled Device) camera and a near-infrared light source which are arranged at a preset included angle and can collect eye images and transmit the eye images to the computer terminal, and the highest recording speed of the infrared camera module is not lower than 200 frames per second; and the computer terminal analyzes the image to obtain pupil positions, diameters and distances, and adjusts relative positions of a shielding device and a lens group in the light path of the illumination module, the axis of the light path and the distance between left and right lens cones, so that the central dark area of the annular light spot is matched and overlapped with the pupil. Eye images are collected and processed firstly, then light spots and the lens cone are adjusted, finally phototherapy and real-time monitoring are carried out, light can be prevented from entering the fundus, the treatment safety is improved, and the device is suitable for ocular surface diseases such as xerophthalmia.

The lamp comprises a lamp body and a light source, the interior of the lamp body is hollow, a cavity is formed in the lamp body, the inner wall of the lamp body is provided with a light inlet face and a light outlet face which are used for transmitting light, the inner wall of the lamp body is further provided with a first light reflecting face used for reflecting light, and the light outlet face is located on one side of the light inlet face; the light source is arranged on the lamp body, and the light-out end of the light source is opposite to the light-in face. Wherein at least part of the first light reflecting surface inclines towards the light emitting surface, and light rays emitted by the light source enter the cavity through the light inlet surface and are emitted from the light emitting surface after being reflected by the first light reflecting surface. According to the LED lamp, after light enters the cavity from the light inlet face, part of parallel light is firstly projected to the inclined face and is reflected by the inclined face to the end, away from the light source, of the light outlet face, a dark area appearing at the end, away from the light source, of the light outlet face due to light attenuation is filled, and the light of the light outlet face of the lamp is dispersed more evenly; therefore, a more uniform light emitting effect is obtained.

A device for image processing includes processing circuitry configured to perform black level remapping. To perform black level remapping, the processing circuitry is configured to: determine luminance values for pixels of a first image, wherein the pixels of the first image are based on color values of samples in each color frame of a plurality of color frames of the first image, wherein each color frame is associated with a different color; determine a first threshold based on the luminance values; determine a mapping curve based on the first threshold and a second threshold; apply the mapping curve to color values of a set of the samples in each color frame to generate black level remapped samples for each color frame, the set of the samples having a color value between the first threshold and the second threshold; and generate a second image based on the black level remapped samples.

The embodiment of the invention provides a vehicle bottom detection system and method. The vehicle bottom detection system comprises a first light supplementing lamp unit, an imaging sensor unit and a second light supplementing lamp unit. The first light supplementing lamp unit, the imaging sensor unit and the second light supplementing lamp unit are all arranged on the working surface of the vehicle bottom detection system; the imaging sensor unit and the second light supplementing lamp unit are arranged in the middle of the working surface; the first light supplementing lamp unit comprises two first light supplementing lamp modules, and the two first light supplementing lamp modules are arranged on the two sides of the working face respectively and are symmetrical relative to the imaging sensor unit. According to the technical scheme, the problem that the vehicle bottom detection effect is poor due to the fact that the light source has a visual field dark area in the related technology is solved, and the vehicle bottom detection effect is remarkably improved.

The invention relates to the technical field of display, and discloses a brightness mapping method based on Mini LED backlight and a backlight system.The method comprises the steps that an input image is analyzed, and image features are obtained; according to the image features, adaptively dividing a dimming area; and for each dimming area, realizing conversion from pixel brightness to Mini LED backlight brightness through nonlinear mapping in combination with human visual characteristics. By analyzing the input image to obtain the characteristics, adaptively dividing the dimming area and combining the human eye visual characteristics to carry out nonlinear mapping, the contrast ratio of the display image is effectively improved, the image details are reserved to the maximum extent, the image quality problem caused by dark area detail loss and bright area overexposure is remarkably improved, and the display effect better meets the human eye visual requirements.