46results about How to "Maintain clarity" patented technology

The invention relates to the technical field of camera adjustment, in particular to a camera adaptive adjustment method and system and a storage medium. The method comprises the following steps: acquiring a multi-source environment sensing data set and an initial environment image; performing environment feature recognition on the initial environment image according to the multi-source environment sensing data set to obtain a scene environment feature map; performing semantic scene segmentation on the scene environment feature map to obtain a semantic scene macroscopic feature map; performing time sequence attention target tracking on the scene environment feature map to obtain a target vehicle motion feature map; performing feature constraint fusion on the semantic scene macroscopic feature map and the target vehicle motion feature map to obtain a target vehicle-scene motion semantic map; and performing parameter adjustment on the camera according to the target vehicle-scene motion semantic map to obtain a camera parameter adjustment strategy set. According to the invention, the performance and the image quality of the camera in a changeable environment are improved.

The invention discloses a grinding workpiece edge shape detection method and system based on machine learning, and the method comprises the steps: obtaining an original image of a grinding workpiece, and carrying out the preliminary image preprocessing; denoising the image and enhancing edge information by combining image filtering and mathematical morphology image processing; based on a second-order differential operator, edge detection is carried out in combination with the morphological gradient, and a workpiece edge contour is obtained; performing feature extraction on the image by using a convolutional neural network, automatically learning workpiece edge features, and constructing and training an edge detection model; acquiring a workpiece image in real time, inputting the workpiece image into the edge detection model for detection, and dynamically correcting the model; and S6, outputting a final edge detection result. According to the invention, by combining image preprocessing, composite image filtering, second-order differential operator and morphological gradient edge detection and feature extraction and model construction of the convolutional neural network, high-precision and robust detection of the edge of the grinding workpiece is realized.

The invention discloses an intelligent driving method and system for a small-spacing display screen based on a glass substrate, and relates to the technical field of display driving, and the method comprises the steps: building a light source characteristic model of the small-spacing display screen based on the glass substrate according to the current intensity of an input signal and the adjustment parameters of a backlight source; acquiring brightness output at the current moment according to the light source characteristic model, and acquiring operation parameters of the small-spacing display screen based on the glass substrate at the current moment; according to the brightness output and operation parameters at the current moment, multi-dimensional adjustment factors are calculated, and the multi-dimensional adjustment factors comprise a brightness compensation factor, a power optimization factor and a backlight dynamic adjustment factor; and performing threshold judgment according to the multi-dimensional adjustment factor, and when a preset threshold condition is met, performing brightness compensation, power optimization and backlight dynamic adjustment. Through comprehensive application of dynamic brightness adjustment, self-adaptive power optimization and multi-dimensional adjustment factors, stability, energy conservation and adaptive optimization of the display effect under different environmental conditions are realized.

The invention relates to the technical field of projectors, in particular to a projector control method and a projector. The method comprises the following steps: performing image projection signal processing on target projection image data to generate initial projection picture data; performing projection point cloud space-time registration on the initial projection picture data by using the dual laser radar assembly to obtain projection scanning point cloud space data; performing shielding area geometric feature analysis on the projection scanning point cloud spatial data, determining an ideal projection area, and generating ideal rectangular projection area data; performing intelligent projection control parameter processing on the ideal rectangular projection area data to obtain intelligent projection control parameters; and performing projection attitude control instruction processing on the intelligent projection control parameters to obtain projection control optimization effect data. According to the invention, the projection control parameters are automatically adjusted through intelligent identification of the projection surface, so that the projector can maintain a stable projection effect in different environments, and the quality of a projection image is remarkably improved.

The invention provides a voice denoising method and device under a low signal-to-noise ratio, and relates to the technical field of voice denoising. The method comprises the following steps: recording audio through a microphone, and obtaining pure voice data; preprocessing the pure voice data to obtain training voice data; according to the U-net network structure and the Transform model structure, constructing a to-be-trained TFDense-Net voice denoising model, and according to the to-be-trained TFDense-Net voice denoising model; based on a multi-spectrum discriminator, according to the training voice data, an Adam optimizer is used to carry out adversarial iteration training on a to-be-trained TFDense-Net voice denoising model, and the TFDense-Net voice denoising model is obtained; the method comprises the following steps: acquiring voice data to be denoised through a microphone in a low signal-to-noise ratio environment; and inputting the voice data to be denoised into the TFDense-Net voice denoising model to obtain denoised voice data. The invention relates to a high-efficiency and clear voice denoising method under a low signal-to-noise ratio, which combines an improved dense block and a video converter.

The invention belongs to the technical field of electronic information and communication, and discloses a self-adaptive signal transmission path optimization system of a chip, which comprises a data acquisition module used for acquiring monitoring video data, chip internal parameter data and chip transmission environment data; the data processing module is used for preprocessing the acquired monitoring video data, chip internal parameter data and chip transmission environment data to obtain a video feature data set, a chip internal parameter feature data set and a chip transmission environment feature data set; analyzing the influence of the chip transmission environment feature data set on the video feature data set and the chip internal parameter feature data set to obtain a transmission influence feature data set; the transmission error analysis module is used for training and obtaining a transmission error prediction model according to the transmission influence feature data set, and obtaining errors generated in the chip internal transmission process of the monitoring video signals based on the transmission error prediction model; the reliability of signal transmission is improved, and the chip resource allocation is more efficient.

The invention discloses an anti-shake method for an image transmission video of an unmanned aerial vehicle. The anti-shake method comprises the following steps: step 1, data acquisition; step 2, multi-frame optical flow analysis; step 3, feature extraction and jitter judgment; step 4, generating a jitter-free frame by the generative adversarial network; and step 5, post-treatment and synthesis. And step 6, performing real-time feedback and optimization. Through combination of multi-frame optical flow analysis and deep learning feature extraction, different types of jitters can be accurately identified. The accurate jitter judgment not only improves the reliability of detection, but also provides an important basis for subsequent processing, so that the video quality can be effectively guaranteed in practical application no matter in a complex environment or in a rapid movement condition, and the scheme can remarkably improve the video quality on the premise of keeping details and definition. The visual effect of the image is further enhanced through subsequent color correction and sharpening processing, so that the finally output video is smooth and has higher watching value.

The invention discloses a weak supervision defogging method based on uncertainty driving, and the method employs a weak supervision defogging network of a U-Net architecture, and the weak supervision defogging network comprises a regional dynamic attention module RDAM, a lower sampling layer, a multi-scale feature fusion module MSFFM, and an upper sampling layer. The RDAM is used for processing an input image or the output of a previous layer of RDAM, constructing a dynamic convolutional layer and obtaining a regional dynamic attention feature map through the dynamic convolutional layer; the down-sampling layer is used for down-sampling the output of the RDAM and reducing the spatial resolution; the MSFFM is used for processing input features through a window multi-head self-attention mechanism so as to capture a long-distance dependency relationship between pixels and performing multi-scale feature extraction and fusion; the upper sampling layer is used for recovering the feature map output by the MSFFM to the resolution ratio of the feature map output by the MSFFM of the upper layer and performing feature splicing with the feature map output by the MSFFM of the upper layer; and enabling the up-sampled feature map to sequentially pass through a 3 * 3 convolutional layer, a ReLU activation function and a 1 * 1 convolutional layer, and finally outputting a defogged image.

The invention relates to the technical field of machine vision detection, in particular to an angle detection device based on machine vision. Comprising a detection device body, a film pasting mechanism and a film feeding mechanism, the detection device body comprises a detection camera, a mounting frame and a dustproof glass cover, the detection camera is fixedly mounted on the mounting frame, the dustproof glass cover is arranged on the outer side of the detection end of the detection camera in a sleeving mode, and the dustproof glass cover is fixedly mounted on the mounting frame; and the film pasting mechanism comprises a first pushing assembly, a film uncovering assembly, a cleaning assembly and a pasting assembly, the first pushing assembly is installed on the installation frame, and the allowance automatic detection assembly is installed on the film feeding assembly. According to the invention, the continuous use duration of the detection camera can be greatly improved, the definition and precision of visual detection are maintained while continuous work is carried out, the application range is wide, an operator does not need to frequently enter a working area with high dust content to carry out wiping, replacement and other operations, and the working safety is improved.

The invention discloses a movement lens motor out-of-step processing method and device, electronic equipment and a storage medium. The method comprises the following steps: controlling a movement lens to zoom according to the position of a reference zoom motor under the current object distance; detecting an actual zoom motor position when the zoom of the movement lens is completed to trigger automatic focusing and enable a lens picture to meet the target focusing definition, wherein the actual zoom motor position is determined based on a field angle of the lens picture when the movement lens meets the target focusing definition; determining out-of-step state information of the zoom motor of the movement lens according to the actual zoom motor position and the reference zoom motor position; and controlling the zoom motor of the movement lens to perform out-of-step compensation according to the out-of-step state information of the zoom motor of the movement lens. According to the scheme, the problem that whether the movement lens is out of step or not cannot be rapidly detected and compensated can be solved on the premise that the definition and smoothness of a lens picture are kept and the user experience is not influenced.

The utility model relates to the technical field of monitoring cameras, in particular to an explosion-proof monitoring camera with a wireless communication function, which comprises a camera body, the surface of the camera body is rotatably connected with a rotating frame, the surface of the rotating frame is fixedly connected with a mounting seat, the surface of the camera body is provided with a cleaning device, and the cleaning device is provided with a wireless communication module. The cleaning device comprises a fixing frame, the fixing frame is fixedly connected with the camera, the surface of the fixing frame is fixedly connected with a collecting box, the surface of the collecting box is detachably provided with a filter plate, the surface of the collecting box is fixedly communicated with a water pump, and the surface of the water pump is fixedly communicated with a pipe. And one end of the pipe is fixedly connected with a spray head, and the surface of the fixing frame is fixedly connected with a servo motor. According to the utility model, the problem that the definition and the quality of a monitored picture are influenced due to the fact that the lenses of most cameras cannot be cleaned and are difficult to clean by working personnel at present is solved.

The invention discloses a printing method, device and equipment for any-fold ink quantity output and a storage medium, and relates to the technical field of ink-jet printing. The method comprises the steps that the reciprocating scanning frequency, initial stepping information and ink amount adjusting information of a to-be-printed task are obtained; actual printing stepping information is obtained according to the reciprocating scanning times and the ink amount adjusting information; processing the to-be-printed data corresponding to each type of to-be-adjusted ink according to the reciprocating scanning times and the ink amount adjustment multiple to obtain actual printing data; and controlling a printing nozzle and a printing medium to move relative to each other according to the actual printing stepping information, and performing ink jetting in the moving process according to the actual printing data. The technical problem that an existing printing method cannot conveniently and accurately output the doubled ink amount with any multiple can be solved.

The traffic signboard with the cleaning structure comprises a supporting column and a signboard body, the signboard body is located on one side of the supporting column, a sliding block is arranged at one end of the signboard body, the signboard body is in sliding fit with the supporting column through the sliding block, and a fixing frame is arranged on the outer surface of one end of the supporting column. A first cleaning roller and a second cleaning roller are arranged in the fixing frame, driven gears are arranged at one end of the first cleaning roller and one end of the second cleaning roller respectively, the first cleaning roller and the second cleaning roller are movably connected with the signboard, and the first cleaning roller and the second cleaning roller are symmetrically distributed about the center point of the signboard. According to the traffic signboard with the cleaning structure, the visibility and quality of the signboard can be improved, the time and cost of cleaning work are reduced, and better driving experience and traffic mobility are provided.

The present application relates to the field of noise reduction technology, in particular to a kind of adaptive noise reduction method, system and equipment, wherein the method comprises: obtaining mixed audio signal and dividing into short-time segment, after normalizing short-time segment, the normalized short-time energy and normalized change intensity of short-time segment are calculated, the short-time segment after normalization is converted into spectrogram and input into light time-frequency feature extraction network, and noise state feature set is output by extraction network;The comprehensive score of short-time segment in noise state feature set is calculated, the starting segment of change, the change influence range and the change type are determined, and the state change description of noise is constructed;The normalized processing intensity of state change description is calculated, noise reduction execution item is constructed, noise reduction execution scheme is generated by sorting noise reduction execution item;For each noise reduction execution item in noise reduction execution scheme, time-domain audio is overlapped and spliced according to the original time sequence of short-time segment, and noise reduction output signal is output.

The invention relates to the technical field of scanning devices, in particular to a quick response X-ray scanning device based on a micro-electro-mechanical chip, which comprises a detection table, a photoelectric sensor is arranged in the detection table, a plurality of positioning blocks are arranged on the detection table, and a table top of the detection table is used for bearing an object to be imaged; the X-ray source is arranged above the detection table and can emit X-rays to the direction of the detection table, and the X-ray source is connected with a movable support capable of driving the X-ray source to move; the detector is connected with the detection table and can receive the X-rays penetrating through the object to be imaged and convert the X-rays into digital signals; the detection table fixes the position of an object to be imaged through the positioning block, the image acquisition module acquires an image of the detection table, and the control module adjusts the position of the X-ray source according to the position of the object to be imaged on the image so as to completely scan the object to be imaged. By accurately positioning the position of the object to be imaged and standardizing the image of the object to be imaged, the accuracy and reliability of the whole scanning process are improved, and the scanning efficiency and the imaging quality are improved.

The utility model discloses sound-insulation, heat-insulation and anti-smashing tempered hollow glass, and relates to the technical field of hollow glass. The sound-insulation, heat-insulation and anti-smashing tempered hollow glass comprises a supporting frame, the interior of the supporting frame is of a hollow structure, a notch is formed in the center of the supporting frame in a penetrating mode, a controller is installed on the front face of the supporting frame, and a plurality of connecting plates are fixedly connected to the notch of the supporting frame; and a demisting mechanism is arranged in the supporting frame. The driving motors transversely and longitudinally arranged in the supporting frame operate to drive the main gear to rotate, so that the synchronous belt assembly rotates, the threaded rods on the two sides are driven to rotate at the same time, the connecting blocks move on the threaded rods, and the sponge blocks can move transversely and longitudinally; therefore, water vapor on the inner wall of the single-layer glass is cleaned, glass surface pollution caused by water vapor corrosion can be avoided, the service life of the hollow glass is prolonged, and good performance and functions of the hollow glass are kept.

The utility model relates to the technical field of legal consultation service, and discloses an automatic legal consultation server which comprises a fixed base, a fixed base assembly connecting block, a connecting block assembly frame bottom plate, a fixed base assembly motor, a motor assembly first gear, a frame bottom plate assembly first rack and a second rack. The first rack is provided with a rear wheel connecting rod, the rear wheel connecting rod is provided with a rear wheel turning rod, the rear wheel turning rod is provided with a driving rear wheel, the frame bottom plate is provided with a second gear, the second gear is provided with a connecting long rod, the second rack is provided with a front wheel connecting rod, the front wheel connecting rod is provided with a front wheel turning rod, and the front wheel turning rod is provided with a driving front wheel. According to the automatic legal consultation server, positioning movement of the automatic legal consultation server is achieved through connection between the gear and the rack in cooperation with the infrared camera, and the problem that an existing legal consultation server is fixedly placed and inconvenient to use is solved.

The invention relates to the technical field of ink mixers, in particular to a high-temperature-resistant UV ink-jet ink and processing mixing device which comprises a mixing body, a mixing barrel and a swing frame and further comprises a mixing rod body arranged on the swing frame and a separation block arranged on the mixing rod body in a sliding mode. The mounting frame is arranged on the outer side of the mixing rod body in a sleeving manner, and the separation block is arranged in the mounting frame in a sliding manner; according to the high-temperature-resistant UV ink-jet ink and processing and mixing device, when a worker produces ink, by means of the arranged scraping unit, when the swing frame swings, the mounting frame and the separation block can be automatically driven to move on the mixing rod body, ink components adhering to the mixing rod body are effectively scraped, and the working efficiency is improved. By observing the relative displacement between the separation block and the mounting frame during each resetting, the mixing condition of the ink is intuitively reflected, and the defect that an operator depends on experience to judge the mixing degree of the ink is overcome.

The invention discloses an efficient self-repairing vehicle-mounted OCA adhesive, a preparation method thereof and an adhesive film, the OCA adhesive is prepared from the following raw materials in parts by weight: 60 parts of 2-ethylhexyl acrylate, 10-20 parts of cyclohexyl acrylate, 15-25 parts of 2-hydroxyethyl acrylate, 5-10 parts of hydroxyethyl dithiodiacrylate, 0.45-1.8 parts of a photoinitiator, 0.5-2 parts of a silane coupling agent, 0.5-2 parts of 1, 2-propylene glycol, 0.5-2 parts of a curing agent, 0.5-2 parts of a curing agent, 0.5-2 parts of a curing agent and 0.5-2 parts of a curing agent. And 0.05 to 0.2 part of 1, 6-hexanediol diacrylate. In the OCA adhesive, a dynamic covalent bond repairing mechanism introduced by dithio diacrylate and a hydrogen bond mechanism of hydroxyethyl acrylate generate a synergistic effect, so that the repairing efficiency is improved in a leap-over manner; and the scratch can be efficiently repaired and the stability and definition of screen display can be maintained under the complex environments of vehicle-mounted high and low temperature, high humidity, strong ultraviolet rays and the like.

This utility model relates to the field of milk refrigerator technology, and more particularly to a milk refrigerator with anti-fog function. It includes a cabinet, with a door connected to one side of the cabinet. The door includes an outer door panel, a sealing strip, an inner door panel, double-layered glass, and an anti-fog drying aluminum strip. The double-layered glass includes an outer glass layer and an inner glass layer. The anti-fog drying aluminum strip is disposed between the outer and inner glass layers, and an intermediate layer is also disposed between the outer and inner glass layers. This utility model has low operating costs. By setting up double-layered glass and incorporating the anti-fog drying aluminum strip within the double-layered glass, it can absorb water vapor within the double-layered glass, preventing water vapor from condensing into fog and avoiding fogging caused by humidity changes. This maintains the clarity and transparency of the double-layered glass, and improves its thermal insulation, sound insulation, and heat insulation performance.

The utility model discloses a light source for a cell imager. The light source comprises a light source shell, a cylindrical light source lamp, an annular light source lamp and a beam splitter prism, the light source shell comprises a bottom plate, the cylindrical light source lamp is arranged above the bottom plate, the annular light source lamp is arranged below the bottom plate, the beam splitter prism is arranged between the bottom plate and the cylindrical light source lamp, and light emitted by the cylindrical light source lamp vertically penetrates through the beam splitter prism and then is converged with light emitted by the annular light source lamp. According to the light source capable of being used for the cell imager disclosed by the utility model, when light rays emitted by the cylindrical light source lamp pass through the beam splitter prism, the beam splitter prism can effectively control diffraction of the light rays and reduce or avoid unnecessary light ray diffusion and interference, so that the definition and the accuracy of imaging are kept; and the beam splitter prism can reflect and refract the incident light according to a specific angle, so that the light cannot be greatly lost, the high efficiency of light path transmission is maintained, the light energy loss is favorably reduced, and the light path transmission efficiency is improved.

The invention belongs to the technical field of power equipment, and particularly provides a power safety warning system and method, a terminal and a storage medium, and the system comprises a control module, a plurality of power safety warning devices, and a power module. The electric power safety warning device comprises a safety warning box, a microprocessor is arranged in the safety warning box, a displayer is arranged on the front surface of the safety warning box, a distance sensing unit and an alarm unit are arranged on the side surface of the safety warning box, and a rain cover is arranged at the top end of the safety warning box. A cleaning mechanism used for cleaning the displayer and a driving mechanism used for driving the cleaning mechanism to work are further arranged at the position, where the displayer is installed, of the safety warning box. Through communication connection with a D5000 system, intelligent and automatic management of safety warning of a power system is realized, dust and stains on the display can be automatically cleaned through the equipped cleaning mechanism, the definition and readability of the display are kept, and the user experience is improved.

The invention discloses an intelligent coding and decoding method and system based on video content in a cloud desktop scene, and the method comprises the steps: determining a change region image block and a content type corresponding to the change region image block through an image difference and content recognition technology for a current frame image of a cloud host system desktop; determining a coding mode of the current frame image based on the size, the distribution and the content type of the image blocks in the change area within the coding and decoding capability range of the cloud host system; coding the current frame image based on the coding mode to obtain coded data; and encrypting the coded data, transmitting the obtained encrypted data to a client, and correspondingly decrypting and decoding the obtained encrypted data by the client to obtain an updated complete frame image.

This utility model discloses a drying component for an intelligent water-based ink printing machine, belonging to the field of printing machine technology. The drying component includes a mounting box with multiple support blocks fixedly connected to its bottom. The rear end of the mounting box has an inlet and an outlet. An installation groove is provided inside the mounting box, on which a drying component and a tensioning component are installed. The drying component dries the printed paper, and the tensioning component adjusts the tension of the printed paper. By setting up the drying component, multiple electric heating tubes operate simultaneously, rapidly increasing the temperature inside the mounting box and causing the moisture in the ink on the surface of the printed paper to evaporate quickly. Furthermore, hot air is sprayed from the jet pipe for secondary drying, further accelerating the drying process and significantly shortening the drying time. The tensioning component reduces paper movement and improves print quality.

The utility model provides a novel design drawing display device, and belongs to the technical field of design drawing display. Comprising a display part; the display panel is mounted on the display part; and the adjusting part is detachably mounted on the display part. By arranging the display part, the display panel and the adjusting part, various environment challenges possibly encountered during outdoor use are fully considered, the definition and visibility of images can be kept even in strong light environments such as direct sunlight and the like, the display panel is designed to be capable of automatically or manually adjusting the angle, and the display effect is good. The supporting legs are arranged on the base to adapt to different viewing angles and sunshine conditions, it is ensured that a user can clearly see information from different positions, the adjusting parts can adjust the lengths of the supporting legs according to the flatness and gradient of the ground, and the whole device can be stably placed on various terrains.

The invention discloses an oral cavity digital impression instrument image acquisition method and system, and the method comprises the steps: carrying out the down-sampling of oral cavity images collected by an oral cavity digital impression instrument, and weighting the frequency of a gray value in each down-sampling image according to the size ratio of each down-sampling image to the oral cavity image, the method comprises the following steps of: performing edge detection on an oral cavity image under gray levels of different gray scales, calculating the prominence degree of a pixel point according to gradient amplitudes of the pixel point under different gray scales and the length of an edge to which the pixel point belongs, correcting the weighting frequency of a gray value, obtaining a mapping interval of the gray value according to the correction frequency, and obtaining the mapping interval of the gray value according to the mapping interval; according to the protruding degree of the pixel point and the gray values of other pixel points in the neighborhood of the pixel point, the mapping gray value of the pixel point is determined from the mapping interval of the gray values of the pixel point, and the mapping gray values of all the pixel points in the oral cavity image form an enhanced oral cavity image so as to reconstruct 3D information of teeth. According to the invention, the accuracy and trueness of 3D information reconstruction are improved.

The preparation method comprises the following steps: adding phospholipase into zanthoxylum bungeanum maxim essential oil to obtain preliminarily degummed zanthoxylum bungeanum maxim essential oil; adding an adsorbent into the red pepper essential oil subjected to enzymolysis; carrying out suction filtration through a vacuum pump to filter out colloidal substances and impurities so as to obtain the red pepper essential oil without the colloidal substances; tween 80, glycerol and polyglycerol fatty acid ester are mixed and then added into the red pepper essential oil without gelatinous substances, heating and stirring are conducted, the mixture is mixed to be uniform, and a uniform and consistent oil phase is formed; the uniform oil phase is dropwise added into the deionized water, continuous stirring and uniform mixing are performed to obtain the clear and transparent water-soluble red pepper refined juice, the water-soluble refined juice is prepared by adopting an essential oil emulsification mode, the essential oil content is high, and the stability of the product state can be effectively ensured; the high-content zanthoxylum bungeanum maxim essential oil is guaranteed, and the clarity degree of the product can be kept.

The invention relates to the technical field of positioning instrument image processing, and discloses an image processing method of a positioning instrument, the method adopts an optical filter with an inner and outer ring structure to collect an infrared image, the inner ring is specially designed for a lens, and the outer ring filters an infrared lamp. According to the method, graying processing is carried out on an acquired infrared image, a Sobel operator is used for calculating horizontal and vertical gradients, and then the gradient amplitude and direction are determined. Through comparison with a set threshold value, edge pixel points of the object image are accurately identified, and finally a clear edge image is output. Compared with a traditional method, noise and miscellaneous points are effectively reduced through the inner-ring optical filter and the outer-ring optical filter, the image preprocessing step is simplified, and the calculation complexity is reduced. Meanwhile, due to the clear input image, the Sobel operator does not need to be additionally adjusted during gradient calculation, and the calculation process is further simplified.

The invention discloses a portable cordyceps sinensis detection method, and relates to the technical field of image recognition, and the method comprises the steps: collecting a scene image of a suspected cordyceps sinensis region through a high-definition camera of a portable collection terminal; the scene image is preprocessed, compressed and coded; sending the encoded image to an edge calculation end through wireless communication, decoding the encoded image to obtain a to-be-detected image, carrying out cordyceps target detection, outputting a detection result including a candidate target position, a category and confidence, and returning the detection result to an acquisition terminal for display; the edge calculation end generates an acquisition parameter adjustment instruction based on the detection result, issues the acquisition parameter adjustment instruction to the acquisition terminal, and performs feedback control on at least one of exposure, focusing and acquisition frequency; and caching the image and the detection result, and uploading the image and the detection result to a cloud to establish an index when an uploading condition is met. The end-side collaborative portable rapid detection is realized, gating is carried out through preprocessing configuration marks, closed-loop error parameter adjustment caused by preprocessing switching is inhibited, and the detection stability and traceability are improved.

The invention discloses a projection lamp and a projection adjusting method. The projection lamp comprises a lamp body base, a lamp body telescopic shell, a rotating device, a telescopic moving device, a projection lamp body and an overturning linkage device. The overturning linkage device comprises a telescopic shifting tooth mechanism, a telescopic rack, an overturning gear, an overturning rack and a push-pull rod; according to the projection adjusting method, the rotating device is rotated for rotationally adjusting a projection pattern of the projection lamp body; when the telescopic stirring tooth mechanism rotates, the telescopic stirring tooth mechanism drives the telescopic rack and the telescopic moving device to move in the same direction, meanwhile, the overturning rack stirs the overturning gear to rotate, the overturning gear drives the push-pull rod to move, and the push-pull rod drives the projection lamp body to overturn. According to the projection lamp, through the gear connecting rod combination of the linkage gear and the push-pull rod, the projection lamp body can be stably overturned and telescopically moved at different angles, the projection angle and position deviation can be conveniently adjusted, the stability and accuracy of the projection effect are ensured, and projection inclination deformation is reduced.