43 results about "Solar azimuth angle" patented technology

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention discloses a radiation correction method and system for an airborne hyperspectral imager. The radiation correction method and system are used for improving the radiation correction precision in complex weather. The method comprises the following steps: calculating a theoretical sun position based on unmanned aerial vehicle initial coordinates, ephemeris data and atmospheric parameters; performing course and differential compensation on a solar azimuth angle by combining IMU course and wind speed and direction data, performing refraction correction on an elevation angle, and outputting a high-precision sun position parameter; hyperspectral images and irradiance data are synchronously acquired, quaternion interpolation is combined with IMU data to realize space-time alignment, and attitude disturbance is eliminated; a hemispherical space irradiance model is constructed based on alignment data, cloud layer modes (clear sky, thin cloud and thick cloud) are divided according to atmospheric optical thickness variance, and Lambert body proportion correction, a discrete longitudinal standard method or a deep convolutional spectral network are respectively adopted for radiation correction. The method remarkably improves the correction precision and generalization ability, supports large-area image splicing, and is suitable for quantitative application of geological exploration, environment monitoring and the like.

The invention discloses an eye protection display control method and system based on ambient light, a medium and a product, and relates to the field of data processing. The method comprises the following steps: acquiring data such as vehicle internal environment illumination, a solar azimuth angle, a driving posture and relative positions of eyes of a driver and a display screen; based on the data, determining an estimated glare area and corresponding intensity within a preset time by analyzing the reflection condition of external illumination on the surface of the display screen; defining a target dimming area from a polymer dispersed liquid crystal dimming layer on the surface of the display screen according to the pre-estimated glare area; determining a driving voltage parameter of the target dimming area according to the estimated glare intensity so as to adjust the scattering degree of the target dimming area; and dynamically optimizing the display effect of the pre-estimated glare area in combination with the environment illumination data, the display content of the glare area and the scattering degree. The problem that the eyesight of a driver and the driving safety are affected due to the fact that a glare area is formed on the surface of the vehicle-mounted display screen by ambient light can be relieved.

A method and a solar panel system (100) are disclosed. Each solar assembly (110) comprises a respective solar panel (200) arranged to rotate, using a hinge assembly (203) connecting to a horizontal rotation axis (HR) of said each solar assembly (110), from a predefined angular position of the solar panel (200) about the horizontal rotation axis (HR) due to wind. The system (100) vertically tracks (A110) the position of the sun by adjusting a tracking azimuth of the solar assembly (110) based on a solar azimuth. The system (100) obtains (A120) a measure of wind in proximity of the solar panel system (100).

The invention discloses a method for establishing a temperature gradient of a double-layer steel truss girder under solar radiation, which comprises the following steps of: S1, calculating a solar elevation angle alpha s (t) and a solar azimuth angle gamma (t) according to the latitude and longitude of a bridge site, an hour angle and a solar declination; projecting the solar ray vector to the cross section of the main beam according to the included angle xi between the axis of the main beam and the east-west direction to obtain a solar incident angle theta (t) in the cross section; s2, respectively deducing solar radiation areas of an upper-layer bridge floor, a lower-layer bridge floor and web members on the basis of a solar incident angle theta (t) and geometric parameters of the bridge; s3, establishing a temperature field formula related to the solar radiation duration, the air temperature, the material attribute, the surface direction and the coating; s4, temperature gradients of the upper-layer bridge floor, the lower-layer bridge floor and the web members are calculated according to the solar radiation area and a temperature field formula, and the most unfavorable temperature gradient and the corresponding moment are determined; according to the scheme, a reliable temperature working condition basis is provided for temperature effect analysis, stress evaluation and structural design of the double-layer steel truss girder.

This invention discloses a geological disaster early warning method based on remote sensing technology, belonging to the field of geological disaster early warning technology. The method includes: acquiring remote sensing image data with at least two different imaging principles within the same geographic unit and the same observation time window; performing geometric correction on the remote sensing image data under a unified coordinate system; and converting the remote sensing image data into corresponding physical quantity data and completing scale consistency processing through sensor response conversion and radiometric calibration; using the remote sensing image data and digital elevation data under the unified coordinate system, calculating the slope and aspect of each pixel, and constructing the light propagation path based on the solar altitude angle and solar azimuth angle. This invention models the influence range of environmental factors from the perspective of propagation structure by constructing light propagation paths and heat diffusion propagation paths under a unified coordinate system and calculating the direction vector field formed by the gravity direction of the slope. This allows anomaly identification to be based not only on numerical changes but also on the analysis of propagation mechanisms.

The utility model relates to the technical field of solar energy, and discloses a solar energy storage steering device which comprises a fixed table, a servo motor arranged in the fixed table, a rotating plate arranged on the top surface of the fixed table and connected with the servo motor, a rotating table arranged on the rotating plate, and a rotary solar panel assembly arranged on the front side of the rotating table. Fixing frames attached to the outer side of the rotating table are arranged on the left side and the right side of the fixing table and extend to the top face of the rotating table, photosensitive plates are arranged on the top faces of the fixing frames, and four photosensitive sensors are arranged on the photosensitive plates in a cross shape. Through the arrangement of the rotating plate, the solar panel can rotate left and right, and under the cooperation of the rotating type solar panel assembly, the solar panel can also rotate in the vertical direction to track the path of the sun more accurately; the four photosensitive sensors are arranged on the photosensitive plate along the cross shape, so that the light intensity difference in different directions can be compared in real time, and the change of the azimuth angle and the elevation angle of the sun can be accurately judged, thereby driving the solar panel to realize accurate tracking.

The invention relates to an intelligent automatic building construction drawing generation method and device, equipment and a medium. The method comprises the following steps: acquiring grid coordinate data, terrain elevation data and sunlight characteristic data of a planning area; the sunlight characteristic data comprises solar azimuth data, solar altitude data and solar radiation intensity data; the grid coordinate data comprises coordinate data of grid points in the planning area; calculating a sunlight thermodynamic diagram of the planning area based on the grid coordinate data, the terrain elevation data and the sunlight characteristic data; the sunlight thermodynamic diagram is used for representing sunlight intensity distribution of a planning area; on the basis of the sunshine thermodynamic diagram and the grid coordinate data, calculating structural parameters of a building located in the planning area, and generating a building construction drawing on the basis of the structural parameters; the structure parameters at least comprise building optimal orientation parameters and building optimal windowing size parameters. By adopting the method, the building design efficiency can be improved.

The invention discloses a multi-tower-limb steel-concrete combined bridge tower temperature gradient establishing method which comprises the following steps: S1, calculating a solar azimuth angle and a solar elevation angle according to the solar declination, the regional latitude and the hour angle at a bridge site; s2, based on the solar azimuth angle, the solar elevation angle, the bridge trend and the geometric parameters of the tower limbs, radiation areas under the self-shielding state of the tower wall, the mutual shielding state of the tower limbs and the external shielding state are calculated; s3, the atmospheric temperature is calculated according to the meteorological data, and heat conduction calculation is conducted in combination with the tower wall comprehensive temperature; s4, temperature gradient models in the tower wall self-shielding state, the tower limb mutual shielding state and the outside shielding state are established; and S5, based on the temperature gradient model, temperature gradient modes of the steel tower column section, the concrete tower column section, the concrete tower wall and the steel-concrete combined section are established respectively, and the scheme can provide complete technical support for temperature effect analysis and design of the multi-tower-limb steel-concrete combined bridge tower.

To provide a weed control device for rice paddies that further improves power generation efficiency and prevents a decrease in work efficiency caused by power shortages. [Solution] A weeding device for paddy fields 100 is configured to automatically travel across a field, comprising a float body 101 with a solar panel 102 positioned on its upper part, a screw propulsion mechanism 103 equipped with a screw positioned on its lower part, and further comprising a positioning device s1 for acquiring location information and a timing unit s4 for acquiring timing information, It is equipped with a solar azimuth calculation unit C1 that calculates the sun's azimuth and elevation angle based on acquired location information and timing information. The solar panel 102 is installed at an angle to the float body 101. The above problem is solved by a paddy field weeding device 100 that controls the direction of travel so that the azimuth of the sun SN calculated by the solar azimuth calculation unit C1 and the elevation direction Fg of the solar panel 102 are facing the same direction during automatic driving.

The invention relates to the technical field of solar heat collectors, in particular to a solar heat collector which comprises a heat collecting body with heat collecting capacity, the heat collecting body is in a notch ring shape, and a notch of the notch ring shape is located under the heat collecting body. A closed flow channel for a heat transfer working medium to flow is designed in the heat collecting body; the outer ring surface and the inner ring surface of the heat collecting body are heat collecting surfaces; the included angle sector formed by the notches accounts for 30-40% of the annular shape; the assembling bracket is used for fixing the heat collecting body, and the top end of the assembling bracket penetrates through the notch to fix the heat collecting body; the light guide assembly is installed on the assembling support and can guide sunlight into the inner ring face of the heat collecting body, through cooperation of the notch annular heat collecting body and the hollow glass heat preservation body, passive tracking of the solar azimuth angle is achieved, and the heat collecting time is prolonged; the inner and outer wall linkage cleaning system guarantees the light transmittance, and the adjustable light guide mirror improves the heat collection density.

The height measurement method based on building shadow recovery relates to the technical field of optical remote sensing image processing, and solves the problem of improving the building height measurement accuracy in high-resolution remote sensing images. The method comprises the following steps: extracting the building shadow in the remote sensing image through a semantic segmentation network, rotating the remote sensing image and the building shadow according to the sun azimuth so that the shadow line is perpendicular to the horizontal direction; dividing the rotated building shadow into a region adjacent to the top of the building, a region adjacent to the side of the building, and a region adjacent to the bottom of the building; recovering the building shadow in the divided regions to obtain the actual length of the recovered shadow; obtaining the actual length sequence of the recovered shadow along the horizontal direction, calculating the height sequence of the building; and calculating the height of the building according to the height sequence of the building. The present application realizes more accurate building height measurement.

The invention discloses an ultra-short-term photovoltaic power prediction method, system, equipment and medium based on a multi-source cloud picture and convolutional vision Transform, and the method comprises the following steps: collecting meteorological information data, photovoltaic unit data, and foundation cloud picture and satellite cloud picture data, and carrying out the preprocessing of numerical input data; carrying out distortion correction on the foundation cloud picture, reconstructing satellite cloud picture space information in combination with a geometric correction technology, determining a satellite cloud picture concern area based on a solar azimuth angle and a cloud cluster motion vector, and carrying out resampling processing and gray scale standardization conversion; analyzing a motion vector field of adjacent time sequence cloud image pixel points to generate an optical flow graph; the continuous multi-source optical flow graph is coded through a convolutional vision Transform, and cloud graph features representing cloud cluster information are extracted; and fusing the multi-source cloud picture features, the meteorological data and the photovoltaic unit data, constructing a photovoltaic power prediction model based on DLinear, and performing photovoltaic power generation power prediction.

The invention discloses a slope photovoltaic system and a construction method thereof, and mainly solves the problems of slope instability, low power generation efficiency and no energy storage function in the prior art. The system comprises a pre-stressed anchor cable, a honeycomb lattice beam, a concrete base and a photovoltaic unit. Wherein the lattice girder is poured by adopting self-healing concrete containing bacillus, and the crack repair rate reaches 80%-90%; a solid-state battery and a phase-change material are arranged in the concrete base, so that energy storage and heat dissipation are realized; the photovoltaic unit is linked with the piezoelectric ceramic promoter through the photonic crystal sensor to dynamically track the solar azimuth angle; a bidirectional sliding rail and a high-damping rubber cushion layer are arranged at the bottom of the base, precise displacement adjustment is supported, and vibration transmission is restrained. And during construction, an eta total efficiency model is adopted for real-time monitoring. The slope stability, the power generation efficiency and the construction convenience are comprehensively improved, and the method is suitable for road slopes and other scenes.

The application relates to the technical field of data processing, and discloses an irregular site photovoltaic module arrangement optimization method and system, which comprises the following steps: obtaining a plurality of grids and their slope direction angles and slope angles of a target region through GIS software, and recording the solar azimuth angles of the grids at a plurality of representative time points within one year; obtaining the light receiving loss coefficients of the grids based on the differences between the slope direction angles of the grids and the solar azimuth angles at the representative time points; obtaining the terrain continuity degrees of the grids; obtaining the priority scores of the grids; performing region growing based on the priority scores of the grids to obtain a plurality of installation clusters; obtaining the comprehensive cluster layout scores of the installation clusters; and performing photovoltaic module installation layout in combination with the slope direction angles of the internal grids. The application aims to solve the problem that the irregular site photovoltaic module arrangement does not consider the terrain restriction, resulting in scattered distribution and complex maintenance.

The invention discloses a short-term photovoltaic power prediction method and system based on data mechanism combined driving. The method comprises the following steps: acquiring the geographic latitude, the solar declination angle and the solar hour angle of a photovoltaic power station to be predicted; calculating a solar elevation angle according to the geographic latitude, the solar declination angle and the solar hour angle, and determining the projection direction of the sun in the horizontal plane to obtain a solar azimuth angle; calculating the ideal irradiance of a photovoltaic panel plane based on the solar elevation angle and the solar azimuth angle in combination with the photovoltaic panel arrangement parameters of the photovoltaic power station to be predicted; introducing ideal irradiance of a photovoltaic panel plane to establish a photovoltaic power prediction probability neural network PNN model; and constructing a photovoltaic power prediction neural network PVFNN model by combining a long short-term memory network LSTM on the PNN model, and realizing short-term photovoltaic power prediction by using the PVFNN model. According to the method, the irradiance model in ideal weather is organically embedded into the neural network, learning in a data driving process is constrained, and a predication result with interpretability can be obtained.

The embodiment of the invention discloses a map construction method, a route recommendation method and a related device, the sun height and the sun azimuth angle are used for describing the position of the sun relative to a to-be-constructed road or a target tree, the crown diameter can influence the shadow length of a tree shadow, and the trunk height can influence the distance between the tree shadow and the tree. Determining the shadow length of the target tree at the target moment based on the solar elevation angle and the crown diameter, determining the shadow position of the target tree at the target moment based on the solar elevation angle, the solar azimuth angle, the crown diameter and the trunk height, and determining the shadow position of the target tree at the target moment based on the shadow length and the shadow position. And determining a tree shadow range of the target tree for the to-be-constructed road at the target moment, and further obtaining a tree shadow range of each tree for each to-be-constructed road at each moment, namely obtaining a shadow map. Through the tree shadow range, the richness of the electronic map is improved, the follow-up recommended route can better conform to the environment, and the user experience is improved.

The application provides a kind of unmanned aerial vehicle path planning method and system based on adaptive dynamic programming. Wherein, the method comprises: calculating the sun azimuth according to the atmospheric polarization mode, and using the sun azimuth to compensate the heading drift of visual odometry, to generate the corrected unmanned aerial vehicle position information; according to the illumination invariance edge information, combined with convolutional neural network, the key landmarks in texture enhanced image are segmented, bidirectional rapid random tree is used to generate semantic navigation landmark point sequence in the constraint space of key landmarks; a model predictive controller is constructed according to the semantic navigation landmark point sequence; through the corrected position information, the flight path of the unmanned aerial vehicle is optimized by adaptive dynamic programming under the constraint of dynamic window, and the field of view angle and exposure parameter of the dual-band imaging unit are adjusted. The application improves the autonomous navigation accuracy and semantic understanding ability of the unmanned aerial vehicle in complex lighting environment, and realizes the anti-interference, high-precision autonomous path planning and flight control.

The invention discloses an underwater polarized light navigation method and device for removing occlusion based on an improved Segment Anything image segmentation algorithm, and relates to the field of underwater navigation. The problem that interference is generated on extraction of orientation information in a polarization distribution diagram in an existing shielding environment is solved, the method comprises the steps that a Segment Anything model comprises an image encoder, a prompt encoder and a mask decoder, the mask decoder generates a plurality of candidate masks in parallel, and the candidate masks are matched with the image encoder; each mask has two key scores: an IoU score is used for measuring the contact ratio of a prediction area and ideal segmentation, and a stability score is used for evaluating the sensitivity of the mask to input disturbance; carrying out extraction and binarization processing on the generated mask according to a polarized light course calculation method, and generating a sky light polarization distribution diagram without shielding; calculating a solar azimuth angle and a course angle of the sky under the navigation system, calculating a root-mean-square error and a maximum error, and verifying a polarized light course measurement algorithm of a solar vector. And the method is also suitable for polarization heading calculation of different scenes.

The application discloses a method for monitoring urban green land carbon sink based on multi-source remote sensing data. The method comprises the following steps: obtaining spectral data, solar azimuth and elevation angle corresponding to the spectral data, meteorological data and vegetation state data; processing the spectral data by using a double-channel convolution model to obtain a vegetation parameter vector; processing the spectral data and the solar azimuth and elevation angle corresponding to the spectral data by using a photosynthetically active radiation dynamic model to obtain photosynthetically active radiation; and calculating carbon sink intensity by using a double-time-scale LSTM network according to the meteorological data, the photosynthetically active radiation, the vegetation state data and the vegetation parameter vector. The method has strong timeliness and high calculation accuracy.

The application discloses an airborne hyperspectral imager radiation correction method and system, which is used for improving the radiation correction accuracy under complex weather. The method comprises the following steps: calculating the theoretical sun position based on the initial coordinates of the unmanned aerial vehicle, ephemeris data and atmospheric parameters; combining the IMU heading and wind speed and direction data to perform heading and differential compensation on the sun azimuth angle, and performing refraction correction on the elevation angle, and outputting high-precision sun position parameters; synchronously collecting hyperspectral images and irradiance data, using quaternion interpolation combined with IMU data to realize space-time alignment and eliminate attitude disturbance; constructing a hemispherical space irradiance model based on the aligned data, dividing the cloud layer mode (clear sky, thin cloud and thick cloud) according to the atmospheric optical thickness variance, and respectively adopting Lambert body proportional correction, discrete longitudinal scale method or deep convolution spectral network for radiation correction. The application significantly improves the correction accuracy and generalization ability, supports large-area image splicing, and is suitable for quantitative applications such as geological exploration and environmental monitoring.

A method of configuring a shade automation show for controlling a motorized window treatment installed on a façade of a building may be disclosed herein. The method may comprise determining to adjust at least one of a first façade limit angle or a second façade limit angle of a direct-sun range for the façade. The method may further comprise determining an adjustment amount for adjusting the first or second façade limit angle; determining a time direction for adjusting the first or second façade limit angle; and adjusting the first or second façade limit angle based on the determined adjustment amount and the determined time direction. The motorized window treatment may be controlled to a direct-sun state when a solar azimuth angle of the sun is within the first and second façade limit angles direct-sun range.

The invention relates to the technical field of photovoltaic panel adjusting supports, in particular to an anti-typhoon distributed ocean photovoltaic support angle self-adaptive adjusting device and an angle self-adaptive adjusting method. The device comprises a controller, a connecting base, an electric control rotating disc, a bearing plate, a lead screw assembly, a sliding base, a mounting frame, a photovoltaic panel, a rotating base and an L-shaped rod, the electric control rotating disc drives the bearing plate to achieve azimuth angle adjustment, and a driving motor on the bearing plate drives two lead screws to rotate synchronously through belt transmission, so that the sliding base moves along a sliding groove; the L-shaped rod is matched to drive the mounting rack and the photovoltaic panel to complete inclination angle adjustment; according to the adjusting method, the solar azimuth angle, the elevation angle, the illumination intensity and device state parameters are collected through the sensor and compared with a preset threshold value after data processing, the controller calculates a target angle according to a comparison result, solar parameters and device limiting, the azimuth angle and the inclination angle are sequentially adjusted, deviation is corrected, and data are stored after iterative optimization.

The invention discloses a land reclamation ecological effect quantitative analysis method based on an agricultural function recovery degree, and relates to the technical field of land reclamation, and the method comprises the steps: calculating a normal phase invasion distance of a target farmland based on the shadow length, the solar elevation angle and the solar azimuth angle of a farmland protection forest belt; calculating a resonance index of the forest belt shadow between the normal direction of the target farmland and the field crop row spacing based on the normal phase invasion distance and the field crop row spacing of the target farmland; and generating a resonance analysis layer based on the normal phase intrusion distance, and performing resonance candidate marking on pixels of the resonance analysis layer to obtain resonance candidate pixels. According to the invention, the accuracy of land reclamation resource allocation and governance decision is improved.

The invention provides a multi-sensor tracking control system and method for a solar cell high-altitude calibration device, and relates to the technical field of solar cell calibration, and the system comprises a calibration test board (100), a solar cell tool (110) installed on the calibration test board (100), a solar cell measurement module (120), an electronic compass (130) and a main sensor (140). Wherein the solar cell tool (110) and the solar cell measurement module (120) are both provided with a solar cell (150) to be measured, the solar cell measurement module (120) is also provided with a slave sensor (160), and the master sensor (140) and the slave sensor (160) are both used for measuring a solar altitude angle and a solar azimuth angle; the system further comprises a sun tracking controller which is used for controlling the motor to move according to measurement data of the master sensor and / or the slave sensor, and sun tracking is achieved.

The utility model discloses a solar mobile lighting lighthouse, including movable base, the upper portion of base is installed with fixed box, two groups of solar panels are symmetrically installed to the both sides of fixed box, and the middle portion of fixed box is installed with the adjusting assembly of drive solar panel rotation, the adjusting assembly includes the screw rod of through installation in the middle portion of fixed box, the lower portion of screw rod is installed with the servo motor of drive driving cone wheel rotation, and the middle portion of screw rod is installed with the driven cone wheel of meshing with driving cone wheel, and the both ends of screw rod are located the both sides of fixed box and are installed with the connecting block of being connected with solar panel. Through setting up by servo motor, screw rod and the adjusting assembly of bevel gear set composition, can drive both sides solar panel synchronous adjustment deflection angle, realizes to solar azimuth angle and height angle active tracking to increase effective light receiving time and perpendicular light receiving rate to improve light energy absorption efficiency and power generation capacity greatly, prolongs the continuation of navigation time of illumination.

The invention provides a multi-aircraft combined real-time bidirectional reflectance distribution function modeling system and method, and the method comprises the steps: planning the flight height and spatial distribution of a multi-aircraft formation relative to a target, controlling the formation to synchronously collect the multi-angle spectral radiance of the target, the sun downlink irradiance, and the solar zenith angle and solar azimuth data, and calculating and outputting the BRDF model of the target in real time by using the data. According to the method, on-board real-time measurement is carried out on the sun downlink irradiance, so that the BRDF modeling precision is effectively improved. Meanwhile, multi-angle data can be synchronously acquired by adopting multiple unmanned aerial vehicles and air-ground collaborative observation and a single flight task, a traditional ground point distribution mode is replaced, the data acquisition efficiency is greatly improved, and the manpower and time cost is greatly reduced.

This invention provides a method and system for ultra-short-term power prediction of photovoltaic power plants based on solar trajectory process propagation, relating to the field of photovoltaic power generation prediction technology. The method includes: collecting real-time meteorological data, ground-based cloud map data, and historical operating power data of the photovoltaic power plant; calculating solar trajectory process parameters, including continuously changing solar altitude angle and solar azimuth angle, based on the geographical latitude and longitude of the photovoltaic power plant and the prediction time window; generating an initial power prediction curve using a basic prediction model; executing a correction process based on solar trajectory process propagation, constructing a solar ray projection channel model, calculating the additional projection velocity caused by the apparent solar motion by combining the rate of change of the solar trajectory process parameters, superimposing the geometric projection velocity of the cloud movement vector on the ground with the additional projection velocity to obtain a slip velocity vector, using the vector to calculate the propagation time delay parameters of cloud shadows reaching each subarray, and dynamically calibrating the time axis of the initial power prediction curve by translation.

The invention relates to a solar azimuth estimation method and system based on multichannel feature enhancement and regional perception attention, and belongs to the technical field of intelligent navigation of a low-altitude economic unmanned system. In order to solve the problem that the precision of solar azimuth estimation based on a polarization image is reduced under the condition of complex cloud layer coverage, the invention provides a deep learning framework fusing multi-channel features and direction perception attention. The method comprises the following steps: firstly, constructing a three-channel composite input feature consisting of a polarization intensity graph, a self-adaptive threshold gradient graph and high-frequency residual information based on polarization light field information acquired by a polarization beam splitting focal plane camera; secondly, a ResNet backbone network of an embedded compression excitation mechanism is adopted, a direction perception polarization attention module is introduced, and adaptive fusion of multi-scale features is realized through brightness guidance, depth feature enhancement and gradient edge branches; thirdly, dynamic fusion of multi-branch features is achieved through the learnable Softmax weight, and a direction constraint mechanism is introduced into an output layer to explicitly optimize estimation results of the solar azimuth angle and the solar elevation angle; and finally, in combination with a solar triangulation module based on a physical model, high-precision solar azimuth inversion is realized. According to the invention, the sun direction information can be stably extracted in a cloud layer interference environment, the robustness and precision of sun direction estimation are obviously improved, and the method has the advantages of compact structure, strong generalization, suitability for autonomous navigation and positioning in a GPS-free environment and the like.

The invention relates to the technical field of measurement engineering, and particularly provides a true north direction measurement method and system based on solar azimuth solution, the true north direction measurement method is suitable for a measurement system equipped with a total station and a data processing terminal, and the measurement system is used for true north direction measurement. Comprising the following steps: manually positioning a solar facula by adopting the total station, and after the positioning is completed, enabling a horizontal dial of the total station to be in an observation locking state; calculating a solar azimuth angle at an observation moment on the basis of a sun position algorithm at a data processing terminal, wherein the observation moment is the observation time recorded when the total station completes positioning; and after the horizontal dial reversely rotates the dial reading by the degree of the solar azimuth angle, determining that the pointing direction of the collimation axis of the total station is the true north reference. According to the method, high-precision measurement of the geographical due north direction is realized through solar azimuth calculation, and the precision requirement of precise engineering such as a concentrating solar photo-thermal project on due north reference is met.