61results about How to "Clear outline" patented technology

The invention relates to the field of image segmentation, in particular to a multi-modal nuclear medicine image segmentation method and system and a storage medium. Comprising the steps that image type classification is carried out on multi-modal medical examination images, focus area positioning is carried out, and CT (computed tomography) focus images and PET (positron emission tomography) focus images are obtained respectively; carrying out lesion geometric mutation form prediction on the CT fault lesion image, and carrying out multi-modal image fusion boundary correction on the CT fault lesion image and the PET lesion image to obtain multi-modal lesion image fusion boundary correction data; according to the multi-modal lesion image fusion boundary correction data, performing multi-modal lesion region segmentation combination optimization on the CT image and the PET image to obtain a lesion region segmentation combination optimization strategy; and carrying out image segmentation model construction on the lesion region segmentation combination optimization strategy based on a strategy gradient algorithm to obtain a lesion image segmentation model. According to the method, the image segmentation technology is optimized, so that the image segmentation technology is more perfect.

The invention relates to the technical field of image processing, in particular to a training method and system based on a circuit board defect detection model. The method comprises the following steps: acquiring an automatic optical monitoring image of the circuit board, and carrying out circuit board surface defect detection on the automatic optical monitoring image of the circuit board so as to obtain surface defect data of the circuit board; marking a circuit board defect area according to the circuit board surface defect data so as to obtain circuit board defect area data; carrying out welding spot three-dimensional contour imaging according to the automatic optical monitoring image of the circuit board so as to obtain welding spot three-dimensional contour data, and carrying out circuit board pseudo soldering analysis according to the welding spot three-dimensional contour data so as to obtain circuit board pseudo soldering data; and performing electrical connection defect analysis according to the circuit board defect area data so as to obtain electrical connection defect data. Based on the computer vision technology, the accuracy of the circuit board defect detection model is improved.

The invention relates to a monocular vision tower span measurement method based on RTK correction, and belongs to the technical field of space distance measurement. Comprising the following steps: acquiring ambient light intensity and quality in real time based on an environment where a power transmission and distribution tower is located, and obtaining ambient light adaptation parameters by analyzing ambient light data and adjusting ISO sensitivity and shutter speed of a camera. According to the method, real-time environment light data analysis and camera parameter automatic adjustment are introduced in the monocular vision tower span measurement process, the image quality is effectively improved, tower recognition is more accurate, background interference is reduced, the geographic position and the shooting angle of a shooting point are corrected through the RTK technology, and the measurement accuracy is improved. And perspective transformation correction is carried out on the image in cooperation with a perspective projection theory, and the accuracy of distance measurement data is improved to centimeter level.

The invention belongs to the technical field of oil pipe monitoring, and discloses a cruise ship oil pipe oil spill monitoring system and method based on machine learning, and the system comprises a data obtaining module which is used for obtaining cruise ship oil pipe state monitoring data; the data processing module is used for preprocessing the acquired cruise ship oil pipe state monitoring data to obtain an oil pipe state comprehensive feature data set; the oil spill risk prediction module is used for training according to the oil pipe state comprehensive feature data set to obtain an oil spill risk assessment model, and predicting an oil pipe oil spill risk rate based on the oil spill risk assessment model; judging whether the cruise ship oil pipe has an oil spilling risk or not according to the oil pipe oil spilling risk rate; if the cruise ship oil pipe has the oil spilling risk, the oil spilling early warning module carries out graded early warning on the oil spilling risk and triggers a corresponding alarm instruction; the oil spilling source tracking module is used for acquiring oil pipe space position data and positioning an oil spilling position in combination with oil pipe video monitoring data; and comprehensive monitoring and efficient management of the cruise ship oil pipe state are realized.

The present invention discloses an image positioning method, device and related equipment, which relate to the field of image positioning, wherein the image positioning method comprises the following steps: obtaining an image to be tested with respect to a positioning mark; obtaining feature points to be tested; matching the template image with respect to the positioning mark and the image to be tested according to the template feature points and the feature points to be tested; when the matching fails, taking the position of the center point of the circumscribed rectangle of the first connected domain as the positioning position; and controlling the movement of the visual field of the visual system according to the deviation between the positioning position and the center position of the visual field of the visual system. The image positioning method of the present application can solve the problem that the local area of ​​the positioning mark in the image to be tested may be blocked or the positioning mark may not appear completely in the visual field, resulting in the positioning mark being unable to be fully identified, causing the template matching to fail, and then causing the image positioning to fail, thereby achieving positioning when the local area of ​​the positioning mark is blocked.

The invention provides an unfavorable weather-oriented automatic driving multi-sensor fusion method, relates to the field of unmanned driving assistance in a closed scene, and provides an unmanned vehicle auxiliary sensing system depending on 5G communication, and the auxiliary sensing system comprises an unmanned vehicle, a millimeter wave radar, a camera sensing sensor, a laser radar sensor and a CAN communication system. According to the method, the communication transmission speed is high, the calculated amount is accurate, the obstacle information and distance in front of the autonomous vehicle in adverse weather can be accurately predicted, and efficient and accurate data fusion between the unmanned vehicle and sensor equipment is achieved. According to the invention, stable and efficient operation of the unmanned vehicle can be effectively guaranteed.

The invention relates to a digital PCR liquid drop identification method and system based on an artificial intelligence algorithm, and the method comprises the steps: generating liquid drops through a micro-fluidic chip, and placing the micro-fluidic chip in PCR equipment for PCR reaction circulation; after the PCR reaction circulation is finished, placing the micro-fluidic chip under a microscope for observation so as to capture a PCR liquid drop image; and preprocessing the PCR liquid drop image, inputting the preprocessed PCR liquid drop image into a pre-constructed liquid drop identification model, and outputting to obtain a PCR liquid drop detection result. Compared with the prior art, on one hand, the micro-fluidic chip is designed, liquid drops with stable structures and consistent sizes can be generated, on the other hand, by introducing the pre-trained artificial intelligence model, efficient identification of the number of the liquid drops and intelligent judgment of a threshold value are achieved, background noise can be effectively reduced, and meanwhile the detection accuracy is improved. And the accuracy of liquid drop identification is obviously improved.

The invention discloses a three-way valve pipe pump production quality evaluation system, relates to the technical field of production quality evaluation, and solves the problem that the production quality parameters and product appearance quality parameters of a three-way valve pipe pump are difficult to calculate to obtain corresponding test values. And whether the production quality parameters are abnormal or not is difficult to judge according to the comparison result of the production quality coefficients. The production quality parameter acquisition module is used for dividing a specific monitoring area into a plurality of monitoring sub-areas and collecting production quality parameters including rotating speed, pressure and flow data from the sub-areas; the component appearance quality detection module is used for calculating product appearance quality parameters, including chromaticity, area and perimeter data, of the component; the production quality parameter testing module is used for acquiring an appearance testing value, a rotating speed testing value, a pressure testing value and a flow testing value; and the production quality parameter abnormity evaluation module is used for judging whether the production quality parameters are abnormal or not according to the comparison result of the comprehensive production quality coefficients.

The embodiment of the invention relates to the photovoltaic field, and provides a photovoltaic module, which comprises a back contact solar cell, and the back contact solar cell comprises a first collection region and a second collection region which are alternately arranged along a first direction; the first auxiliary grid lines and the second auxiliary grid lines are alternately arranged in the second direction; the first identification point is located on the first auxiliary grid line, and the distance between the first identification point and the second collection area is a first distance; the first identification points and the second identification points are mutually staggered; the insulating layer is positioned at the end part, facing the second collecting region, of the first auxiliary grid line; wherein the insulating layer on the first auxiliary grid line with the first identification point is a first insulating layer, the first insulating layer is disconnected at the first identification point, the distance between the first identification point and the end part of the first insulating layer is a second distance, and the ratio range of the first distance to the second distance is 2-30. According to the photovoltaic module provided by the embodiment of the invention, the yield can be improved.

The invention discloses a high-precision tunnel settlement measuring and modeling method based on laser ranging and an inclination angle. The method comprises the following steps: surveying and mapping to obtain coordinates of initial positions of laser range finders and targets in a plane T; determining a measuring laser range finder and a measured laser range finder; filtering the measurement data to obtain target measurement data of a target between the measurement laser range finder and the adjacent measured laser range finder and compensation amount measurement data of the measurement laser range finder and the measured laser range finder; and calculating the coordinates of the target in one measurement period, and comparing the difference between the coordinates of the target and the coordinates of the target at the initial position to obtain the settling volume of the target. According to the method, the high-precision tunnel section can be obtained, the more the sampling points are, the clearer the contour of the tunnel section is, and the higher the modeling precision is. A measuring instrument with higher precision is adopted, the precision of the outline of the tunnel is higher when a larger number of sampling points are arranged, and the method is suitable for various tasks such as subway tunnel construction, measurement, settlement monitoring and the like.

The invention discloses a moisture-absorbing breathable fabric preparation method, which comprises the following steps: laying a functional adhesive material on a positioning film to form a functional adhesive layer, carrying out laser engraving to obtain a functional adhesive layer with a set shape, retaining the functional adhesive layer with the set shape on the positioning film, removing the rest of the functional adhesive layer to complete waste discharge, and then, carrying out heat preservation on the positioning film to obtain the moisture-absorbing breathable fabric. The functional adhesive layer and the positioning film are composited on the fabric base layer in a hot-pressing mode to form a composite body, on the basis of the composite body, a kerf is cut in the fabric base layer through laser, and the kerf is in a non-closed curve shape and penetrates through the fabric base layer in the thickness direction of the fabric base layer, so that a movable page is correspondingly formed on the fabric base layer, and after cutting is completed, the movable page is formed. And removing the positioning film to obtain the moisture-absorbing breathable fabric. According to the moisture-absorbing breathable fabric, the functional adhesive layer is uniform in thickness, clear in outline, smooth in adhesive surface, free of mutual adhesion, good in appearance, high in position accuracy and less in conditions of kerf position deviation, kerf shape deviation and the like.

The invention discloses a grinding wheel abrasive particle image segmentation method based on machine vision, and the method comprises the following steps: inputting a grinding wheel abrasive particle sample image, converting the sample image into a gray-scale image, and carrying out the preprocessing of image enhancement on the gray-scale image; performing operation on the gray-scale map line by line and column by column by two-dimensional Gaussian filtering; calculating the partial derivative of each pixel point in the x-axis direction and the y-axis direction, and obtaining the gradient of each pixel point according to the partial derivative; performing non-maximum suppression according to the gradient; acquiring a global threshold by using an Otsu algorithm, and introducing the global threshold into an adaptive function for setting image segmentation by high and low thresholds of a Canny algorithm to realize edge connection; lag compensation is carried out, and middle edges are accepted and rejected; and morphologically processing irrelevant areas and filling holes. According to the method, edge connection is achieved by setting the adaptive function of image threshold segmentation, the problem of noise interference caused by the grinding wheel base body area and the environment is effectively solved, the boundary of the grinding wheel abrasive particle image contour can be accurately divided, and good flexibility is achieved.

The invention discloses a ram base sand mold 3D printing modeling method. The method comprises the following steps that A, a casting process scheme is designed; b, designing a corresponding hollow sand mold structure according to the geometrical shape, the casting performance and the process scheme of the casting; c, making a model; d, the molten iron contact surfaces of all the sand molds are subjected to coating brushing treatment; e, box distribution; and F, box assembling and pouring. According to the invention, modeling-free modeling is realized, the molding cost can be saved by 450,000 yuan, meanwhile, the production period is obviously shortened, and the production efficiency is greatly improved. The 3D printer is adopted to print the sand mold, the size precision is high and can reach 0.3 mm, the gap is small during core assembly, positioning is accurate, and the quality of the mold cavity is guaranteed. And the sand mold design adopts a shape following design, so that the sand consumption is reduced, and the sand mold strength is ensured. The weight of each sand mold is small, the weight of the sand molds is reduced, the material cost is saved, operation is convenient, large hoisting equipment is not needed, the requirement for the equipment capacity is low, and the molding labor intensity is small.

The invention discloses an image positioning method and device and related equipment, and relates to the field of image positioning, and the image positioning method comprises the following steps: obtaining a to-be-detected image related to a positioning mark; obtaining a to-be-detected feature point; according to the template feature points and the to-be-detected feature points, matching a template image related to the positioning mark with the to-be-detected image; when the matching fails, taking the central point position of the external rectangle of the first connected domain as a positioning position; and controlling the visual field movement of the visual system according to the deviation between the positioning position and the visual field center position of the visual system. According to the image positioning method provided by the invention, the problem that the local area of the positioning mark in the to-be-detected image may be shielded or the positioning mark may not completely appear in the visual field, so that the positioning mark cannot be completely identified, the template matching fails, and the image positioning fails can be solved; therefore, positioning can be realized under the condition that the local area of the positioning mark is shielded.

The invention relates to a calligraphy font data enhancement method and device, a terminal and a storage medium. The calligraphy font data enhancement method comprises the steps of obtaining an original calligraphy font image for a subsequent neural network training set; the acquired calligraphy font image is optimized, so that the font contour of the image is more obvious; training the data training set by using a neural network; and an optimization model is obtained through comparison according to the size of iteration values in the training process. The neural network training obtains the optimization model and generates a generator model and a discriminator model at the same time, the generator model simulates writing according to the fonts of the training set, and the discriminator model judges the similarity between the simulated writing fonts of the generator model and the original fonts, so that the accuracy of the neural network training model is further improved. The calligraphy work authenticity detection method and system can automatically detect the authenticity of the calligraphy work and improve the detection efficiency and accuracy. Therefore, an intelligent and high-efficiency calligraphy and painting calligraphy work authenticity detection function is realized, and the market requirements of calligraphy works are met.

The invention discloses a light-weight image fusion method based on a Mamb-KAN structure, and the method comprises the following steps: obtaining a registration source image, dividing the registration source image into overlapped image blocks, and constructing a Sheaf Laplacian matrix according to an overlapping relation and limited mapping; decomposing the Laplacian spectrum matrix, and projecting image block features into a Sheaf coefficient sequence; a Mama-KAN network is constructed, a Mama branch receives the coefficient sequence to extract fusion features, and a KAN branch calculates a block-level fusion weight according to the coefficient sequence and the fusion features; constructing a loss training network by using the Sheaf consistency energy and the reconstruction error; a lightweight network is obtained according to contribution pruning and quantification of the Mama channel and the KAN base unit to the consistent energy; in the fusion stage, a Sheaf coefficient sequence is generated and input into the lightweight network, and a source image is weighted according to a fusion weight to generate a fusion image. According to the invention, high-quality and low-overhead image fusion is realized.

The application discloses a kind of based on optimization's guiding filter image fusion change detection method and device, method includes: by extreme minimum scale difference operator, pixel value difference value is to the picture of same scene different phase, obtains difference map;Using the way of guiding filter, difference map is fused on global scale, to obtain the optimal difference map;Mean filter is used to phase map I1 and I2, and the base layer difference map corresponding to each difference map is obtained, and the optimized brightness saliency map F1 and F2 are obtained by pca fusion as the image of generating saliency map, according to the principle of maximum saliency to determine weight map;Weight map is regularized for double-scale difference map reconstruction, and the final difference map is obtained;In clustering segmentation stage, by introducing soft threshold function, the final difference map is further processed, to suppress existing abnormal noise.The device includes: processor and memory.

The invention discloses a quality detection method and detection device for safflower Xiaoyao tablets, and belongs to the technical field of quality detection of traditional Chinese medicine preparations, and the quality detection method comprises the following steps: identifying angelica sinensis and mint in the safflower Xiaoyao tablets, identifying liquorice and radix paeoniae alba in the safflower Xiaoyao tablets, and identifying bupleurum chinense in the safflower Xiaoyao tablets; according to the method for identifying the radix angelicae sinensis, the herba menthae, the radix paeoniae alba, the radix glycyrrhizae and the radix bupleuri marginate, the prior art is simplified and integrated, consumption of samples and organic solvents is reduced, compared with the prior art, the method is simpler, more convenient, rapider, economical and reasonable, and by comparing and optimizing the method conditions, the identification efficiency of the radix bupleuri marginate is greatly improved. Spots with clearer outlines and more enriched colors can be obtained, the overall quality detection effect is greatly improved, and the actual application effect of the overall method is improved; the detection device enables the whole operation process to be more efficient and safer, facilitates the improvement of the experiment efficiency and the detection effect, and guarantees the health and safety of personnel.

The utility model discloses a rubber product forming die which comprises an operation table, a die table and a feeding table, the feeding table, the die table and the operation table are fixedly connected in sequence from left to right, and baffles are fixedly connected to the two sides of the feeding table, the two sides of the die table and the two sides of the operation table respectively. Two pulley bearings are fixedly connected between the top sides of the baffles, the two pulley bearings penetrate through and are rotationally connected with a first pulley and a second pulley correspondingly, a transmission rope is connected between the first pulley and the second pulley in an engaged mode, one end of the transmission rope is fixedly connected with a fixing disc, and the fixing disc is fixedly connected with a rotating shaft. A rolling column is arranged and rolled at the other end of the transmission rope; according to the utility model, rubber raw materials can be pre-processed, so that the processing efficiency is higher in the rubber pressing production and processing process.

The present invention discloses an online blast furnace feeding belt material particle size visual detection method and device, including obtaining the original image of the production raw material on the blast furnace feeding conveyor belt through a camera; performing guided filtering processing on the original image to obtain a filtered image; performing binarization processing on the filtered image to obtain a binary image; optimizing the binary image using a morphological processing method and an area filtering method to obtain an optimized image; performing distance transformation on the optimized image to obtain a distance image; obtaining points with distance values ​​greater than a preset value from the distance image, performing watershed transformation on the filtered image with the points as starting seed points to obtain a watershed segmentation result; marking and area statistics on the watershed segmentation result to obtain the particle size data of the production raw material. The present invention can automatically and accurately detect the particle size of the production raw material, and improves the timeliness and accuracy of the production raw material particle size detection.

The invention discloses a retaining ring gluing image enhancement detection method based on a CycleGAN model. Comprising the steps of collecting an original gluing image; carrying out VGG16 neural network identification and classification; enhancing the image by using the improved CycleGAN network model; and in the gluing area, the gluing state is judged. According to the method, the low-contrast part of the glue area can be effectively enhanced, the detection precision is improved, the edge information of the glue image is enriched, and a more accurate gluing state image can be obtained. The final detection success rate of the image obtained through the method can reach 95%, more accurate information support can be provided for the gluing process of the industrial robot, the working stability between the retaining ring and the polishing head and between the retaining ring and the wafer is guaranteed, the yield in the chip manufacturing process is improved, and the method has actual production significance.

The utility model discloses an adjustable face recognition terminal, which belongs to the technical field of face recognition terminals and comprises a terminal body, a camera recognition module is arranged on one side of the terminal body, light supplementing assemblies are arranged on the two sides of the camera recognition module, a universal support is fixedly connected to one side of the terminal body, and the universal support is fixedly connected to the other side of the terminal body. The bottom of the universal support is fixedly connected with an installation stabilizing assembly. According to the utility model, through the arrangement of the light supplementing assembly, if a person is at a backlight angle, the driving motor drives the first lead screw seat to move through the adjusting lead screw, and the first lead screw seat drives the angle adjustment of the light supplementing mirror through the connecting seat and the connecting plate, so that the light supplementing mirror reflects a light source at a proper angle, and the reflected light source hits the face of the person; therefore, the face contour of the person is clearer, the situation that the recognition effect is affected by insufficient light in face recognition is avoided, and the face recognition effect of the terminal is improved.

This invention discloses an aroma fitter for fenugreek tincture based on key aroma components and synergistic aroma characteristics, and its applications. Based on analytical studies of the aroma components and aroma characteristics of high-quality fenugreek tincture, the aroma fitter identifies key aroma characteristics such as caramel sweetness, freshness, fruitiness, nutty aroma, roasting aroma, and sourness, and determines the contributing characteristic compounds and their synergistic proportions within each aroma characteristic. The composition contains key components such as acetic acid, trans-2-pentenal, propyl butyrate, phenethyl acetate, 2-hexanone, ethyl palmitate, benzaldehyde, 2,5-dimethylpyrazine, and 3-hydroxy-4,5-dimethyl-2(5H)furanone, which are precisely formulated to achieve a high degree of consistency with natural fenugreek tincture in aroma structure and olfactory characteristics. This invention not only provides a realistic and layered aroma fitter formulation but can also be applied to the food and daily chemical industries, providing stable and harmonious fenugreek characteristic aromas, thus possessing significant practical application value.

The application provides a tunnel lining concrete evaluation method and system, and belongs to the technical field of tunnel lining quality detection. The method comprises the following steps: a data acquisition and matrix construction step: obtaining full polarization data and establishing a complex domain scattering matrix of each sampling point; a spatial phase locking step: constructing a spatial phase locking loop, tracking the spatial phase of the steel bar in real time, determining the locking state according to the phase difference and determining the steel bar high-weight prediction area; a polarization feature calculation step: in the steel bar high-weight prediction area, performing eigenvalue decomposition on the local covariance matrix, calculating the polarization entropy and the average scattering angle; an adaptive projection stripping step: generating an adaptive gain factor and adjusting the projection strength of the projection matrix, performing projection transformation on the original polarization vector to obtain a residual signal; and an evaluation step: reconstructing a defect signal based on the residual signal to evaluate the quality of the tunnel concrete lining. The scheme can improve the accuracy of tunnel concrete lining quality evaluation.

The invention discloses a high-precision and high-efficiency automobile part detection system which comprises an automobile part image acquisition platform, a distortion image vision measurement correction system, a vision image flange plate positioning hole detection system and flange plate positioning hole detection system software. Even micron-sized objects can be detected, detection analysis is completed, and the purpose of precise measurement is achieved; the circumferential position of the positioning hole is determined by detecting the coordinates of the center position of the positioning hole in the flange plate image, direct contact with the surface of a part is avoided, compared with traditional detection, the efficiency is greatly improved, a software system can detect the position information of the positioning hole of the flange plate through an accurate measurement method, the quality of the flange plate is distinguished, and the detection accuracy is improved. The balance of the automobile transmission shaft is improved, key influences caused by friction and abrasion during shaft movement are reduced, and the automobile part detection scheme is high in precision, high in efficiency and low in consumption.

The application belongs to the technical field of terminal processing, in particular to a terminal secondary stamping device, which comprises a pushing component, a pressing component, a pressure receiving component, a pushing component and a transfer component, the pushing component is arranged on the left side of the pressure receiving component, the transfer component is arranged on the right side of the pressure receiving component, and the pressing component is arranged at the bottom of the pushing component; the pushing component comprises a counterweight pressing plate, a storage top plate and a tension column. The device cuts off most of the material in advance and eliminates edge micro-cracks and residual stress through rough stamping blanking, thereby providing a high-quality blank with uniform organization and accurate positioning for subsequent processes. Then, during fine stamping, the device uses ultra-high pressure to force the material to flow plastically in depth, fill the corners of the mold and eliminate springback, thereby obtaining a high-precision shape with clear contours and no corner collapse, avoiding the problems of excessive corner collapse of the terminal after stamping, too small contact surface, poor contact of the connector and easy leakage of the terminal sealing glue.

The invention provides an automatic station searching method for a monocular vision robot, the robot is provided with a camera and an excitation light source, the camera is provided with an optical filter, a workstation is provided with an activatable identifier, and the method comprises the following steps: the robot starts to rotate after navigating to a first position; exciting light is emitted through the exciting light source, the activatable identifier can be activated by the exciting light and emit activation light, and the activation light can pass through the optical filter; the camera receives the activation light and recognizes the activatable identifier, and then rotation is stopped; and the robot can be automatically docked with the work station through the position of the activatable identifier by visual localization. According to the automatic station searching method for the monocular vision robot, on one hand, the robot can identify the activatable identification target more easily, the anti-interference capability is improved, on the other hand, the contrast ratio during imaging is enhanced, the contour and internal details of the activatable identification are clearer, and then the precision of the robot in the monocular vision positioning and docking process is improved.

The invention provides a training method of a neural network model for image processing, an image recognition method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of image recognition. The neural network model comprises a first sub-model and a second sub-model, and the training method of the first sub-model comprises the following steps: acquiring a first sample image, and marking a real coordinate value of a region of interest in the first sample image; inputting the first sample image into the first sub-model to obtain a first output; adjusting parameters of the first sub-model; the training method of the second sub-model comprises the following steps: acquiring a second sample image, and marking a real threshold value; inputting the second sample image into the first sub-model to obtain a second output of the first sub-model; inputting the second output into the second sub-model, and obtaining a prediction threshold value output by the second sub-model; and adjusting parameters of the second sub-model based on the real threshold value and the prediction threshold value.

The utility model discloses a door frame light supplement lamp capable of lifting adjustment and multi-angle light supplement, which comprises a door frame body, the top of the door frame body is fixedly connected with two first vertical plates, a lifting assembly is arranged between the two first vertical plates, the bottom of the lifting assembly is provided with a displacement plate, and the lifting assembly is used for adjusting the height of the displacement plate. A mounting frame is fixedly connected to the bottom of the displacement plate, a fixing frame is rotatably connected to the bottom of the mounting frame, a light supplementing lamp body is rotatably mounted in the fixing frame, and an adjusting assembly is arranged on one side of the fixing frame and used for adjusting the angle of the light supplementing lamp body. The utility model aims to solve the problems that the heights and angles of people in different vehicle types are different, the light supplementing effect of a fixed light supplementing lamp is reduced, the outline of a shot object cannot be clearly shot, and the shooting quality is reduced.