125 results about "Light perception" patented technology

The invention relates to the technical field of display, and particularly discloses a dynamic ambient light adaptive OLED display optimization method and system, and the method comprises the steps: obtaining an ambient light time sequence data set of an environment where an OLED display screen is located, and synchronously obtaining real-time display parameters and historical brightness adjustment data of the display screen; acquiring ambient light sensing features according to the ambient light time sequence data set; obtaining photo-thermal structure coverage area data of the OLED display screen according to the real-time display parameters; and acquiring preliminary optimization parameters according to the ambient light sensing characteristics and the photo-thermal structure coverage area data. According to the invention, illumination intensity, spectrum drift and contrast change are captured in real time in combination with ambient light perception characteristics, the one-sidedness of adjustment only according to brightness traditionally is solved, reflection can be reduced through photothermal structure deformation under strong light, brightness can be improved to offset interference, and human visual characteristics can be matched under weak light. And the display definition and the visual comfort in different environments are effectively improved.

The invention relates to the technical field of automatic induction, and discloses an automatic induction lamplight angle adjustment control method and device and lighting equipment. The method comprises the following steps: acquiring ambient light parameters in real time to obtain ambient light sensing data; performing multi-scale space division and feature fusion on the ambient light sensing data to obtain a three-dimensional ambient light distribution diagram; inputting the three-dimensional ambient light distribution diagram into a light angle calculation network for light change characteristic analysis to obtain a light optimal angle parameter group; performing smooth transition light sequence calculation according to the light optimal angle parameter group and the current light configuration state to obtain a sectional light adjustment control instruction; and performing motion path planning on the end effector of the lamp based on the sectional light adjustment control instruction to obtain an effector motion instruction set. According to the invention, light change characteristics of different spatial scales can be captured at the same time, and the adjustment accuracy and adaptability of the actuator are improved.

The invention relates to a light sensation self-adaption and white balance cooperative adjustment method and device for an LED display screen, and the method comprises the steps: collecting the illumination value of current ambient light and the spectral distribution of the ambient light, and calculating the color temperature value of the ambient light; according to the color temperature value, inquiring a pre-stored color temperature-gain parameter corresponding relation library to determine a corresponding white balance gain parameter; according to the illumination value, a backlight brightness adjustment amount is calculated through a pre-constructed logarithm compensation model; associating and binding the white balance gain parameter and the backlight brightness adjustment amount, and outputting the white balance gain parameter and the backlight brightness adjustment amount to a pulse width modulation signal generation unit and a digital-to-analog converter through a microcontroller; and outputting the white balance gain parameter to a digital-to-analog converter, outputting the backlight brightness adjustment amount to a pulse width modulation signal generation unit, generating a synchronous adjustment signal to drive an LED display unit, and carrying out cooperative adjustment of backlight brightness and white balance so as to achieve the purpose of unified regulation and control of visual comfort and color rendition authenticity.

The invention discloses a control method of a video monitoring system, which relates to the technical field of video monitoring, and comprises the following steps of: acquiring continuous image frames through the video monitoring system, extracting brightness channels, edge structures, direction gradients and contrast changes of images, constructing a reflective perception vector group, and calculating an included angle change trend by combining a target motion direction vector, determining whether a reflection offset condition consistent with the target direction appears in a picture in a camera attitude control process; after it is determined that the reflection offset condition consistent with the target direction appears in the picture, the inter-frame change tensor of the target area and the reflection area is extracted, and a time sequence track consistency matrix is constructed; according to the invention, the problem of wrong adjustment of the camera caused by misjudgment of light reflection in video monitoring is solved, attitude regulation and control based on image displacement abnormal mode recognition are realized, and the tracking stability and the monitoring accuracy are improved.

The invention discloses a lamp and a method for improving the lighting effect of the lamp, the lamp comprises a shell, a light-transmitting piece, a main supporting frame and a light source device, the light source device comprises a mounting substrate and a light emitting body, the mounting substrate is provided with a mounting base surface used for mounting the light emitting body, and the light emitting body is configured to emit light; the position of the light source device is lifted to the mounting base surface to approach to the upper edge of the shell from bottom to top or upwards exceed the upper edge of the shell, so that the upper edge of the shell is prevented from interfering with lateral light rays emitted by the light source device from the light transmitting part; according to the lamp, light rays of a single light source are laterally diffused, the light spots formed by the lamp are larger and are better in uniformity by being matched with avoiding matching of the shell and the light-transmitting piece, so that the lighting effect is improved, and the light sensation of the whole space is better; according to the method for improving the lighting effect of the lamp, the lighting effect is improved by lifting the light-emitting body, so that the mounting base surface of the light-emitting body is upwards close to the upper edge of the shell or upwards exceeds the upper edge of the shell, and lateral light rays can avoid the shell to be spread outwards.

The invention provides an automatic driving test scene generation method based on real traffic data, and solves the problems of low accident data utilization rate, SIL / HIL test splitting and insufficient boundary coverage in the prior art. Comprising the following steps: acquiring multi-source heterogeneous traffic accident data; cleaning data by adopting a joint interpolation-anomaly detection mechanism; vehicle dynamic sudden change characteristics within 0.5 second before braking are extracted through LSTM and DTW algorithms; constructing a three-dimensional scene pipeline driven by a physical engine, and dynamically associating the pavement slippery coefficient with the rainfall intensity; analyzing the accident text into simulation parameters by using a semantic-physical parameter converter; performing SIL-HIL cooperative verification: performing extreme illumination perception test and narrow road planning verification in an SIL environment, and realizing 1ms step length fault injection test in an HIL environment; positioning failure parameters based on Bayesian optimization; a GAN is adopted to generate a long-tail scene, and a test boundary is expanded by coupling extreme conditions such as rainstorm / low visibility; and outputting a standard scene library containing the collision probability thermodynamic diagram. The safety verification efficiency under the extreme working condition is remarkably improved.

The invention discloses a perception and communication detection platform and method in a complex weak communication environment. According to the detection platform, a high-simulation multi-physical field coupling test environment is constructed by integrating a weak illumination perception mechanism and capability test module, an anti-interference communication mechanism and capability test module, a complex environment detection mechanism and capability test module, a data acquisition and analysis system, a multi-scene coupling controller and a full-experiment-area weak electromagnetic shielding case. The adaptive test efficiency of the unmanned system in weak illumination, strong interference and complex terrain environments is remarkably improved, the method can be widely applied to the fields of underground exploration, emergency rescue and intelligent inspection, and the field test cost and risk are reduced.

The invention relates to the technical field of large-scale structure measurement, and discloses a robot laser vision three-dimensional scanning measurement system for a large-scale structural member. The system comprises a robot motion platform, a laser vision sensing module, an ambient light sensing module, a point cloud processing module and a motion control module, wherein the laser vision sensing module is arranged at the tail end of the robot motion platform. The ambient light sensing module collects ambient light intensity distribution data in real time, and the motion control module combines the data with three-dimensional model data of the large-scale structural member to be measured to generate a multi-view dynamic scanning path instruction. The robot motion platform executes an instruction to drive the laser vision sensing module to move, the module projects laser stripes to the surface of a to-be-measured structural member and synchronously collects an image, the point cloud processing module performs adaptive filtering processing on the image and then generates three-dimensional point cloud data, and the requirement for efficient and accurate measurement of a large structural member in a complex industrial environment can be met.

The invention relates to the technical field of screen display adjustment and visual health protection, and discloses a screen color temperature intelligent adjustment method and system, and the method comprises the steps: obtaining a user face image sequence and ambient light perception data; according to the face image sequence, eye features are extracted, a dynamic change trend is analyzed, blinking frequency and eyelid closing duration data are calculated, and a visual fatigue evaluation value is obtained; according to the ambient light sensing data and the visual fatigue evaluation value, correcting the fatigue degree and classifying fatigue stages to obtain color temperature and brightness adjustment parameters; and transmitting the adjustment parameter to a screen display driver for gradual change processing to obtain a final screen display configuration. According to the method, personalized accurate adjustment of the screen parameters is realized, visual fatigue is effectively relieved, and the use experience and the visual health protection effect are improved.

The invention discloses a liquid crystal display brightness adjusting system and method based on ambient light perception, and the system comprises a high-precision ambient light sensor which obtains the ambient light illuminance and color temperature data in real time; the analog-to-digital converter is used for converting the analog optical signal into a digital signal; an embedded microcontroller; the temperature sensor is tightly attached to the liquid crystal panel backlight unit; and the control input end of the liquid crystal driving chip is connected with the driving signal output end of the embedded microcontroller through a serial peripheral interface bus. The technical normal form of a liquid crystal display dimming system is fundamentally reconstructed: in a physical layer, photoelectric signals and human eye spectral response offset are corrected through a spectral separation mechanism, a carrier recombination effect is inhibited based on a thermodynamic equation, and the physical authenticity of brightness output is ensured; in a control layer, a motion state compensation model and a spatial topology perception algorithm are constructed, and brightness space-time consistency control in a dynamic scene is realized.

The invention discloses an HDR image reconstruction method based on progressive feature alignment and quality guide fusion, and the method comprises the steps: inputting a to-be-processed LDR image sequence into a trained progressive quality guide image reconstruction model, and obtaining an image reconstruction result; according to the model, after an input LDR image sequence is linearized, a progressive variable feature alignment module aligns non-reference frame features through a multi-scale pyramid and cascade deformable convolution, and multi-scale features are output through exposure perception modulation; the quality guide motion compensation module iteratively optimizes an optical flow field and a confidence coefficient mask through a cascade optical flow quality refining structure block; and the structure maintenance fusion module aligns the HDR sequence by using the optical flow field, performs dynamic weighted fusion in combination with a confidence mask, and finally enhances details through a Laplace attention mechanism and outputs a ghosting-free HDR image. According to the method, through progressive alignment and fusion of quality perception, the balance problem of ghosting and detail loss in dynamic HDR imaging is solved.

Disclosed are methods, systems, and computer program products that present, by a spatial computing system, an extended reality presentation to a user, wherein the extended reality presentation comprises virtual object(s) generated by a spatial computing system and transmitted to one or both eyes of the user and a physical environment that includes a first physical object and a second physical object and is perceived by the user via light reflected from the physical environment. The extended-reality representation is rendered for an object interaction between the first physical object and the first virtual object or the user. A physics-based effect on the first physical object by the object interaction is determined by using at least a stereoscopic model for the first physical object based at least in part upon the object interaction. The extended reality presentation into an undated extended reality presentation based at least in part upon the physics-based effect.

The invention relates to the technical field of candid photographing identification, and discloses a candid photographing equipment positioning and alarming method combined with ambient light perception. The method comprises the following steps: arranging a sensor array, a signal receiving node and an image acquisition device in a target area, acquiring real-time ambient light intensity and color distribution change data, and generating a change trend of the real-time ambient light intensity and color distribution change data; adopting statistical analysis to identify abnormal ambient light changes, and outputting coordinates and features of the abnormal light changes; corresponding images are obtained and preprocessed, secret photographing equipment features are extracted through an image algorithm, verification is carried out in combination with a rule base, and candidate positions are determined; accurate position coordinates are obtained through a triangulation positioning method; and if ambient light abnormity and candid shooting characteristics exist at the coordinate at the same time, the candid shooting device is judged, and the alarm system receives the coordinate and triggers alarm and interference measures. According to the invention, candid photographing identification precision and positioning capability in a complex scene are improved.

The invention provides an automobile atmosphere lamp illumination uniformity detection method and system, detection points of a simulated automobile cabin are determined, detection parameters of the detection points are set, and simulated human eye light sensation visual detection in the automobile cabin is realized by setting the detection points; by means of illumination detection data of all detection points on atmosphere light, global illumination distribution of a vehicle cabin is constructed, a non-uniform illumination area in the global illumination distribution is determined, and non-uniform illumination space distribution formed under the current atmosphere light illumination condition is accurately positioned; a target atmosphere lamp suitable for eliminating the non-uniform illumination area is determined in combination with the spatial relationship between the non-uniform illumination area and the atmosphere lamp layout, illumination change information of the target atmosphere lamp is determined, it is ensured that global atmosphere lamp uniformity illumination detection is implemented for the specific cabin environment in the design stage, and by changing the light emitting illumination state of the atmosphere lamp, the uniformity of the atmosphere lamp is improved. The overall lighting quality of the cabin is improved.

The invention relates to a light and shadow adjusting device for a biological rhythm synchronous child toy, and aims at solving the problems that an existing toy is fixed or random in light effect, cannot adapt to the physiological rhythm of a child and is prone to causing visual fatigue. The device comprises a light sensation acquisition unit, a rhythm identification unit, a parameter generation unit and a lighting effect driving unit. The light sensing acquisition unit is used for acquiring environment illumination intensity and generating illumination sensing data; the rhythm recognition unit combines the illumination perception data with the current time information, generates target rhythm state data according to a preset physiological rhythm model, and is used for judging the current activity cycle stage of the child; a parameter generation unit generates a corresponding light and shadow adjustment parameter set according to the rhythm state data; the lighting effect driving unit controls the light-emitting assembly according to the parameter set and outputs light and shadow effects matched with the physiological rhythm of the child, such as stimulation enhancement in the daytime and soft transition at night, so that sensory requirements of different time periods are dynamically met, attention is effectively improved, and visual burden is reduced.

The invention discloses a fine-grained feature matching vehicle re-identification method for a license plate shielding scene, and the method comprises a vehicle detection stage based on illumination perception and adaptive prediction, and a fine-grained Transform feature matching stage based on implicit semantic prototype perception. Comprising an illumination sensing module and an adaptive prediction module. The illumination sensing module is used for realizing image adaptive enhancement under different illumination conditions; the adaptive prediction module suppresses a redundant prediction frame through a self-attention weight mechanism; in the fine-grained Transform feature matching stage based on implicit semantic prototype perception, an implicit semantic prototype learning module and a fine-grained Transform matching module are included; the implicit semantic prototype learning module unsupervised decouples vehicle structural components through a group of learnable semantic prototypes to generate a soft semantic distribution diagram; and the fine-grained Transform matching module is used for introducing semantic affinity bias in cross attention. According to the method, the accuracy and stability of vehicle detection and identity matching in a complex environment can be improved.

The invention discloses a lighting system for industrial robot navigation, a control unit and a method, and relates to the field of intelligent robots. The problems that a traditional robot is single in illumination, insufficient in environment perception and low in data interaction and processing efficiency are solved. The system comprises an intelligent lighting module, an ambient light detection module, a positioning module, a data processing module, a navigation control module and a central control module. According to the system, through linkage of multi-thread data processing, dynamic path planning and an intelligent lighting strategy, closed-loop control of ambient light perception-navigation planning-lighting adjustment is realized; through cooperation of multiple modules, deep fusion of intelligent illumination and precise navigation is realized, and the environmental adaptability and operation reliability of the robot in a complex environment are remarkably improved.

The invention discloses an all-weather unmanned aerial vehicle target detection method and system based on reflectivity guidance. The method comprises the following steps: extracting an RGB feature set and an IR feature set from input data; using a reflectivity characteristic with a dark light resistance characteristic as a reference characteristic to align the infrared characteristic, and then using the aligned infrared characteristic as the reference characteristic to further align the reflectivity and the visible light characteristic; the aligned visible light features, the aligned infrared features and the aligned reflectivity features are input into an illumination perception selective fusion module, feature interaction is carried out in a hidden state space, and corresponding complementary features are generated; and adding the alignment characteristic and the complementary characteristic to obtain an enhanced characteristic, then directly adding the enhanced characteristics of the RGB and IR modes to obtain a fusion characteristic, and sending the fusion characteristics of the last several stages to the neck and the head of the detection network to generate a final detection result. According to the invention, effective cross-modal fusion is realized to adapt to different degrees of darkness and illumination changes.

The invention discloses a low-light image enhancement method and system based on a learnable YUV space, and the method comprises the following steps: S1, obtaining an original RGB image collected in a low-light environment, and carrying out the preprocessing of the original RGB image; s2, mapping the preprocessed RGB image to a learnable YUV color space, and decoupling to obtain a brightness component and a chrominance component; s3, obtaining an enhanced brightness feature by using the brightness component and introducing an illumination perception position coding mechanism; s4, performing multi-branch parallel denoising and pixel-level dynamic fusion on the chrominance component to obtain a purified chrominance component; s5, fusing the enhanced brightness component and the purified chrominance component, and performing color correction; and S6, the corrected YUV image is inversely converted into an enhanced RGB image. According to the method, the image is mapped to the learnable YUV space and is decoupled, and multiple enhancement and correction mechanisms are combined, so that brightness enhancement, color correction and quality improvement of the low-illumination image are realized.

The invention relates to the technical field of image processing, discloses an image display method and device of a display screen, a vehicle, a medium and a program product, and realizes multi-dimensional light perception of a complex environment by acquiring environment data of an environment where the display screen is located and multi-dimensional light data in multiple different directions and / or different types. And performing comprehensive analysis based on the environment data and the multi-dimensional light data, determining an image display parameter corresponding to at least one object type in the to-be-displayed image, and further performing partition adjustment on the to-be-displayed image to obtain a target display image. Therefore, the display screen is prevented from being too bright or too dark, the display effect of the objects associated with different object types in the target display image can be matched with the actual visual demand of a driver, and the driving safety and the user experience are improved.

The application relates to an adaptive control system for dynamic sensitivity adjustment of a photoelectric sensor, comprising: a photoelectric sensor, the sensitivity parameter of which can be adjusted online, used for collecting and outputting an image sequence; a target detection and feedback unit, used for carrying out target detection on the image sequence output by the photoelectric sensor, obtaining a boundary box of the target, a detection confidence and a local signal-to-noise ratio expectation value of the target area; an ambient light sensing unit, used for acquiring an ambient light intensity and generating a predicted ambient light intensity; a prediction model unit, used for predicting a scene displacement amplitude of a next frame based on a motion vector of a current image frame; and a parameter solving unit, which is internally provided with a sensor response model and a motion blur probability model, and is used for constructing a cost function with the sensitivity parameter as a variable; the application can realize better adaptive control.

This application relates to the field of autonomous driving technology, specifically providing a traffic light perception method, a device control method, a device, and a medium, aiming to solve the problem of accurately perceiving the state of traffic lights. To this end, the method provided in this application includes acquiring an environmental image collected by a smart device, the environmental image containing traffic lights; inputting the environmental image into a traffic light perception model for processing to obtain a virtual light corresponding to the environmental image; the virtual light is used by the smart device for driving control, the virtual light including multiple traffic direction indicators and the indication state of each traffic direction, the traffic direction indicators being used to indicate the driving direction of the smart device; the traffic light perception model is trained based on samples of the environmental image and their annotation information, the annotation information including the virtual light corresponding to the sample. Based on the above method, the traffic direction indicators and their indication states at intersections can be accurately obtained.

The present invention relates to the field of image correction and proposes an image correction method, device, system, and storage medium. The method involves synchronously capturing a color image and three-dimensional point cloud data of a target object using an RGB-D sensor, constructing an elastic mesh model (including stiffness attributes), and achieving high-precision surface unfolding based on finite element analysis to generate a geometrically corrected image. Multispectral shadow separation and generative adversarial network (GAN) inpainting techniques are combined to eliminate occluded shadows and generate textures with consistent illumination. Finally, global illumination uniformity is optimized through dynamic compensation based on ambient light perception. This technical solution aims to reduce errors in unfolding correction of non-planar objects, efficiently distinguish between real content and shadow areas, adapt to dynamic ambient light changes in real time, and improve the ability to generate complex textures.

The invention provides an unsupervised thermal imaging video enhancement method based on an event-assisted traffic sign sketch. According to the method, the characteristics of low light perception but texture missing of an infrared camera and low light, high dynamic, noise and incompleteness of event signals are fully combined, a dual lifting mechanism of an infrared frame and the event signals is provided for the traffic semantic reconstruction problem in the driving environment, and high-quality traffic sign sketch drawing without supervision is achieved. According to the method, accurate motion estimation is provided by utilizing infrared signals to serve as a time reference for aligning event signals so as to align incomplete event signals. Event signals are utilized to provide texture details which are usually not perceived by an infrared camera, and event consistency correction is introduced to improve the continuous perception effect between adjacent frames. According to the unsupervised thermal imaging video enhancement method provided by the invention, the applicability of the infrared camera in a low-light traffic environment is improved, and the improvement of the visual task performance in the middle and downstream of automatic driving is facilitated.

The present invention provides an LED display color adjustment system and method based on ambient light perception. The system includes: a signal acquisition module, a color matching module, and a light feedback module. The method includes: detecting the light intensity of the environment around the display screen through a light perception sensor to obtain an analog signal of the light intensity, and converting the analog signal into a digital signal through an analog-to-digital converter, thereby obtaining a light intensity value corresponding to the analog signal; based on the light intensity value, calculating the brightness values of the three primary colors of red, green, and blue that match the light intensity value according to a preset color adjustment strategy; adjusting the colors in the display screen according to the brightness values; and re-detecting the light intensity of the surrounding environment in real time according to the light intensity acquisition period and making adjustments according to the new light intensity value. The present invention can achieve color adjustment based on ambient light perception, making the display effect more adaptable and optimized under different lighting conditions, and can provide a better visual experience.

The application relates to the technical field of large structure measurement, and discloses a robot laser vision three-dimensional scanning measurement system for large structural parts. The system comprises a robot motion platform, a laser vision sensing module, an ambient light sensing module, a point cloud processing module and a motion control module, wherein the laser vision sensing module is arranged at the tail end of the robot motion platform. The ambient light sensing module collects ambient light intensity distribution data in real time, the motion control module generates multi-view dynamic scanning path instructions in combination with the data and three-dimensional model data of the large structural part to be measured, the robot motion platform executes the instructions to drive the laser vision sensing module to move, the module projects a laser stripe to the surface of the structural part to be measured and synchronously collects images, and the point cloud processing module generates three-dimensional point cloud data after adaptive filtering processing of the images, so that the efficient and accurate measurement requirement of the large structural part in a complex industrial environment can be met.

This invention discloses a vision-electrophysiological multimodal eye-tracking zoom control system and zoom glasses, relating to the field of zoom glasses technology. The zoom optical element has at least one control area. The multimodal sensing unit includes a vision detection module, an EOG detection module, and an ambient light sensing module, used to collect the wearer's eye state information, periocular potential information, and ambient light information, respectively, when the glasses are worn. A cross-modal adaptive calibration unit is used to calibrate the eye state information using periocular potential information when the ambient light information does not meet preset lighting conditions. The focus control unit is used to calculate the eye's gaze direction and gaze distance based on the eye state information, determine the target control area based on the gaze direction, generate focus control parameters based on the gaze distance, and drive the target control area to focus using the focus control parameters. This invention improves zoom performance by coordinating visual signals and EOG signals.

The invention discloses a two-dimensional indium selenide optical sensor with a motion trail recognition function and a preparation method thereof. The light sensor device comprises a SiO2 / Si substrate, a gamma-InSe semiconductor light absorption layer located on the substrate and asymmetric Au electrode structures arranged at the two ends of the light absorption layer. A gamma-InSe semiconductor material with a non-centrosymmetric structure is selected, and an asymmetric electrode configuration design is combined, so that the device generates a photo-pyroelectric effect and a photo-thermoelectric effect under the condition of temperature change caused by illumination, and remarkable positive and negative pyroelectric response peak current is formed in a zero-bias self-driven mode. The device can directly analyze and reconstruct the motion trail of an object according to the dynamic behavior of the reverse attenuation current after light removal, does not need to depend on an external calculation unit, and achieves the function of integrating light perception, information storage and motion trail calculation in a single device.

The invention discloses an illumination perception adaptive method and system for night pedestrian re-identification. The method comprises the following steps: S1, obtaining an input image; s2, processing the input image through an illumination perception image preprocessing network, and dynamically generating an enhancement coefficient graph and a noise confidence graph; s3, performing detail enhancement on the input image through an adaptive enhancement branch to obtain an enhanced image; performing noise suppression on the input image through a feature purification module to obtain a purified image; s4, performing feature extraction on the enhanced image and the purified image by using a shared backbone network to obtain enhanced features and purified features respectively; and S5, fusing the enhancement feature and the purification feature through an illumination perception controller to obtain a final identity representation. According to the invention, through end-to-end illumination perception adaptive processing, image enhancement and feature purification are effectively cooperated, and the discrimination capability and robustness of a night pedestrian re-identification model in a low-light environment are significantly improved.

The invention discloses a non-uniform illumination underwater image enhancement method, and belongs to the technical field of image processing. The method mainly comprises the following steps: constructing an illumination-perceived non-uniform illumination underwater image enhancement network, wherein the illumination-perceived non-uniform illumination underwater image enhancement network comprises a trunk enhancement network for outputting a sharp image and an illumination attention map estimation branch network for outputting an expected illumination attention map; training the illumination perceived non-uniform illumination underwater image enhancement network based on the non-uniform illumination underwater image data set; and obtaining a to-be-processed non-uniform illumination underwater image, inputting the to-be-processed non-uniform illumination underwater image into the trained illumination perception non-uniform illumination underwater image enhancement network, and outputting a clear underwater image through the decoder module. According to the method, the detail information of the non-uniform illumination underwater image can be effectively enhanced, the brightness information and the color information are adjusted, and the quality of the underwater image is remarkably improved.