56 results about "Variable resolution" patented technology

The invention discloses a bay environment simulation forecasting method and device, relates to the technical field of marine environment forecasting, and aims to solve the problem that in the prior art, forecasting precision and forecasting timeliness cannot be taken into account when environment simulation forecasting is carried out on a bay. The method comprises the following steps: based on coastline data, performing encryption processing on a target sub-region in a target gulf region by adopting a curve orthogonal grid, and generating a variable-resolution refined curve orthogonal grid from an inshore region to an open sea region; based on a refined curve orthogonal grid, according to a model simulation data format requirement, a variable-resolution grid file is manufactured and obtained; determining a model input file based on the water depth topographic data and the variable resolution grid file; and inputting the model input file into a preset three-dimensional oblique pressure ocean numerical model for calculation to obtain simulation forecast data. Therefore, the simulation precision requirements of different bay areas can be met, and the simulation calculation speed and the simulation calculation efficiency of the whole target bay area are ensured.

Camera heads configured to provide digitally articulated images or video, at adjustable resolutions and / or offsets and orientations, to a camera control unit (CCU) or other electronic computing system for display, storage, and / or transmission to other systems are disclosed.

A novel and useful direct time of flight distance measuring device that incorporates smart pixel architecture, real-time in-pixel histogram and intensity acquisition, optical power control, and variable resolution. The device avoids the use of time to digital (TDC) converters by generating in-pixel histograms based on a global high-speed clock that implements per pixel time bin single photon event accumulation using circuitry located under or near the SPAD pixels. Laser events are processed within a smart pixel architecture increasing substantially the data conversion throughput while reducing data movement in the device to achieve high spatial resolution, low power operation, and fast reliable depth capture. The device uses a compact split pseudo-random counter. Each smart pixel operates independently and concurrently, allowing the sensor to operate in global shutter while monitoring the SNR and determining the optimal exposure time for transmitter and receiver power savings. This enables full control of the pixel operation, enable / disable, and optimization.

Apparatuses, systems, and techniques to use one or more neural networks with adjusted resolution information. In at least one embodiment, for example, one or more neural network low resolution encoders are trained to one or more higher resolutions. In at least one embodiment, as another example, a processor is to adjust a resolution of information to be used by one or more neural networks based, at least in part, on one or more performance metrics of one or more neural networks.

The LIDAR system may include a laser emitting unit configured to generate multiple laser beams. The LIDAR system may also include an optical system configured to transmit the multiple laser beams from the laser emitting unit to a common scanning unit. The common scanning unit may be configured to project the multiple laser beams toward a field of view of the LIDAR system to simultaneously scan the field of view along multiple scan lines across the field of view.

The invention discloses neural networks employing variable resolution. Devices, systems, and techniques using one or more neural networks with adjusted resolution information are disclosed. In at least one embodiment, for example, one or more neural network low resolution encoders are trained to one or more higher resolutions. In at least one embodiment, as another example, a processor is to adjust a resolution of information to be used by one or more neural networks based at least in part on one or more performance metrics of the one or more neural networks.

The embodiment of the invention provides a coloring method, electronic equipment and an electronic chip. The method comprises the steps that a first coloring rate texture map for a first image is acquired, the first image is an image generated by variable-resolution coloring rendering according to current image frame data, and the resolution of the first image is lower than the rendering target resolution of an image frame; and performing artificial intelligence super-division on the first image based on the first coloring rate texture map, improving the resolution of the first image, and generating a second image meeting the rendering target resolution. According to the coloring method provided by the embodiment of the invention, image coloring rendering is performed in combination with variable-resolution coloring and artificial intelligence super-resolution, and the fuzzy region in the variable-resolution coloring result is repaired by adopting the artificial intelligence super-resolution, so that the image rendering quality is improved, and the image rendering overhead is reduced.

The invention relates to the field of target signal observation by the compressed sensing observation system, and solves the problems that the existing underdetermined compressed sensing system is sensitive to noise and cannot realize effective signal reconstruction under noise interference. The invention overcomes the problem that the compressed sensing system is sensitive to noise interference and cannot realize effective signal reconstruction. The response of the reconstruction system under variable resolution is subjected to pathological analysis and selection, and the low-resolution high-precision target signal is solved first. The reconstruction of the compressed sensing high-precision target signal is constrained by the low-resolution reconstructed signal, which increases the anti-interference ability of the compressed sensing signal reconstruction system. Without introducing additional environmental conditions, the compressed sensing signal reconstruction that is resistant to noise interference is realized by the system itself.

The invention provides a path planning method, system and equipment based on a mixed satellite A and a medium, and belongs to the technical field of automatic driving path planning. The method comprises the following steps: constructing a variable-resolution grid map according to environment obstacle distribution, adopting a high resolution in an obstacle area, and adopting a low resolution in an open area; performing pose validity verification on the starting point and the target point; dynamically updating map obstacle information based on real-time sensor data; pre-calculating the RS curve connectivity from all discretized vehicle kinematics reachable points to a target point by adopting a parallel calculation mode, and establishing a directly connectable node set; in the process of executing the mixed A star algorithm, when the expansion nodes are located in the directly connectable node set, the pre-calculated RS curve is directly called to complete path planning, and search is terminated. According to the method, through the variable-resolution map and the pre-calculation mechanism, the calculation complexity is remarkably reduced, and the real-time performance and efficiency of path planning are improved.

This invention discloses a variable-resolution compressed sensing hyperspectral computational imaging system and apparatus, comprising: a modulation unit array and a control module; the control module is used to output coded signals to the modulation unit array according to a partitioned identical modulation method; the modulation unit array is used to modulate the light signals emitted by the target scene converging on itself according to the coded signals and then project them onto an area array detector; the partitioned identical modulation method is as follows: according to the actual required image spatial resolution, the modulation unit array is divided into sub-blocks of the same size and non-overlapping; the control module outputs the same coded signal to the modulation units in each sub-block, so that the modulation units in the same sub-block modulate the light signals in the same way, thereby merging all the modulation units in each sub-block into an equivalent modulation unit, realizing the variable modulation resolution of the modulation unit array; using this invention, the flexible variable spatial resolution of hyperspectral imaging can be achieved without changing the hardware structure.

The invention relates to the technical field of welding spot analysis, in particular to a printed circuit board welding spot three-dimensional shape high-precision analysis method, which comprises the following steps: synchronously acquiring three-dimensional shape data and thermal radiation data of a welding spot area through a multi-mode sensing module, dynamically planning a scanning path based on welding spot material characteristics, and carrying out laser scanning by adopting a self-adaptive variable resolution strategy; a welding spot digital twin model is constructed by fusing three-dimensional point cloud and thermodynamic characteristics, a dynamic stress simulation module is embedded in the digital twin model, mechanical vibration and thermal cycle load borne by a welding spot during operation of a circuit board are simulated, and a potential fatigue failure index is generated according to a simulation result. According to the high-precision analysis method for the three-dimensional morphology of the welding spot of the printed circuit board, the three-dimensional morphology data and the thermal radiation data of the welding spot area are synchronously obtained, so that a multi-dimensional complementary information foundation is laid for subsequent analysis, and the accuracy of the three-dimensional morphology of the welding spot is improved. And the comprehensive efficiency of quality detection and reliability evaluation of the welding spots of the printed circuit board is improved.

This invention relates to a membrane electrode design optimization method based on three-dimensional reconstruction of a catalytic layer with variable resolution, comprising the following steps: constructing a numerical reconstruction model of the catalytic layer based on existing experimental characterization results; validating the effectiveness of the numerical reconstruction model of the catalytic layer; if the verification is successful, proceeding to the next step; otherwise, adjusting the growth probability of each phase and returning to the previous step to adjust the numerical reconstruction model of the catalytic layer; adjusting the parameters of the numerical reconstruction model of the catalytic layer, and analyzing the catalyst utilization and transport characteristics within the catalytic layer after parameter adjustment; and determining electrode parameters based on the analysis results to guide the fabrication of the membrane electrode. Compared with existing technologies, this invention has advantages such as reduced membrane electrode fabrication costs and strong method versatility.

Apparatus, systems, and techniques for using one or more neural networks with adjusted resolution information. For example, in at least one embodiment, one or more encoders of a low-resolution neural network are trained to one or more higher resolutions. In at least one embodiment, as another example, a processor adjusts an information resolution to be used by one or more neural networks based at least in part on one or more performance metrics of one or more neural networks.

This disclosure describes devices, systems, and methods that relate to obtaining image frames with variable resolutions in synchronization with a clock source. An example device may include an image sensor, a clock input, and a controller. The controller includes at least one processor and a memory. The at least one processor is operable to execute program instructions stored in the memory so as to carry out operations. The operations include receiving, by the clock input, a clock signal. The clock signal is a periodic signal defining at least one scan interval. The operations also include during the scan interval, causing the image sensor to capture a full resolution image frame. The operations yet further include during the scan interval, causing the image sensor to capture at least one reduced resolution image frame.

This application discloses a multi-scale road surface full-element semantic segmentation method, apparatus, electronic device, and storage medium. The method includes: acquiring image information from a preset scene; obtaining segmentation results from the image information using a pre-trained semantic segmentation model, wherein the semantic segmentation model is trained using multiple sets of data through machine learning, and each set of data includes: image data with variable resolution and a resolution scaling factor corresponding to the image data; and obtaining segmentation results for each element at different resolutions in the preset scene based on the segmentation results. This application achieves multi-scale training and prediction, improving the segmentation effect of objects of different sizes in images of a preset scene.

Computer-implemented systems and method train a generator and a discriminator, through machine learning, where the generator and discriminator are trained in an adversarial relationship using a simulated, multi-player game. The model parameters for the generator and the discriminator can be updated non-simultaneously. Also, the simulated, multi-player game may comprise a two-person, zero-sum game.

This invention relates to a variable-resolution ghost imaging method for axially moving targets, comprising: determining the axial speed and distance of the moving target, as well as the size of the moving target and the distance from the moving target to the optical projection system; setting speckle parameters; generating a human-eye-like non-uniform variable-resolution speckle pattern with high resolution at the fovea, low resolution around the periphery, and a uniformly varying radius of the fovea region based on the speckle parameters, the moving target's motion parameters, and scene information; projecting the human-eye-like non-uniform variable-resolution speckle onto the axially moving target for sampling and measuring the reflected light intensity; and performing a second-order correlation operation between the reflected light intensity and the projected speckle information to obtain the final reconstructed image. This invention utilizes a human-eye-like non-uniform speckle pattern with a varying fovea radius to reconstruct axially moving targets, maintaining a constant proportion of the fovea region occupied by the target during movement, thereby improving the imaging quality of axially moving targets.

The invention discloses a spatial variable-resolution single-pixel imaging sampling and reconstruction method based on a diffusion converter, and solves the problems that a reconstructed target is blurred in a large range due to the fact that a traditional single-pixel imaging method is difficult to effectively extract image features and remove noise at a low measurement rate; and the key position and the shape feature of the target cannot be clearly identified. And applying the learned weight matrix as a progressive measurement matrix to a single photon counting detection system. Through a spatial variable resolution module, limited measurement resources are guided to preferentially capture key information of an image, and the resolution of a key area of the image is ensured under limited measurement times. The problem of image blurring caused by characteristic insufficiency under the extremely low measurement rate is effectively optimized by utilizing the space structure long-range capture capability and generation capability of the diffusion converter, and the target is successfully clear and distinguishable. Therefore, the single-pixel reconstruction effect is remarkably improved at an extremely low measurement rate, and the method has excellent anti-noise performance.

Computer-implemented systems and method train a generator and a discriminator, through machine learning, where the generator and discriminator are trained in an adversarial relationship using a simulated, multi-player game. The model parameters for the generator and the discriminator can be updated non-simultaneously. Also, the simulated, multi-player game may comprise a two-person, zero-sum game.

The embodiment of the invention discloses a sea wave numerical mode second-order space advection method based on an SCVT unstructured grid, and the method comprises the steps: constructing an SCVT unstructured grid system, building an index mapping relation between a unit and an edge, configuring a wave action quantity at the center of the unit, and configuring an advection speed at the midpoint of the edge of the grid; spatial discretization is carried out on geographic space advection items based on a finite volume method; for flux calculation on each discrete grid edge, a second-order windward format is adopted, an upstream unit is determined according to the flow velocity direction, the wave action quantity and gradient of the upstream unit are obtained, and a high-precision wave action quantity value at the midpoint of the grid edge is obtained through linear reconstruction; and finally, combining spectrum space advection and a source convergence item to finish time integration and sea wave forecasting. According to the method, sea wave advection calculation of the second-order windward format is achieved in the SCVT grid, the precision of sea wave simulation is remarkably improved, numerical dissipation is effectively restrained, meanwhile, variable-resolution grid configuration is supported, and the calculation efficiency is improved on the premise that the simulation precision of key areas such as a near-shore area is guaranteed.

The present invention discloses an underwater image enhancement method and device based on multi-resolution diffusion and color correction, belonging to the technical field of image processing, including: using the inverse diffusion process of the diffusion model to reconstruct the denoised image with the underwater image as the guiding condition, adopting a variable-resolution sampling scheme for the image during the denoising process of the full diffusion period to gradually improve the image resolution, and at the same time, in each time step, using a global color corrector to correct the color of the denoised reconstructed image to correct the global degradation color deviation phenomenon of the image during the denoising process. The color-corrected reconstructed image is used as the input for the next time step. In this way, through the variable-resolution sampling scheme in the full diffusion period combined with the global color correction in each diffusion time step, the technical problem that it is difficult to balance the global color consistency and local detail fidelity when processing images in different water environments is solved, and at the same time, the relationship between the calculation efficiency and the recovery quality can be balanced.

The present invention provides a system and method for capturing images during review of a microscope slide. In certain embodiments, such system and method allow for the capture of images and construction of a composited microscope mosaic image within the workflow of the slide reviewer, such as a pathologist reviewing a tissue sample. In certain embodiments, said mosaic images are whole slide images constructed by and capable of being viewed at variable resolutions and magnifications corresponding to the review of the original microscope slide by the slide reviewer.

The present invention provides a video encoding / decoding method, electronic device, and non-temporary computer-readable medium that support variable resolution and / or efficiently handle region-based packing. [Solution] The video decoding method includes decoding a flag from the bitstream of encoded video data that indicates whether reference picture resampling is possible and whether the reference picture has parameters that can differ from the corresponding parameters of the current picture; determining, based on the flag, that reference picture resampling is possible and that the parameters of the reference picture are different from the corresponding parameters of the current picture; resampling a portion of the reference picture to generate a resampled portion of the reference picture; and predicting the current picture using the resampled portion of the reference picture.

The application belongs to the technical field of robot mapping, and discloses a multi-resolution multi-level map information structure, a dynamic updating system and a construction method for autonomous exploration. In the aspect of map information construction, a multi-level map structure is adopted to distinguish different information amount areas in the environment, and a high-efficiency hash mapping data structure is combined to realize accurate and efficient expression of environment voxel information. In the map incremental updating process, a ray projection method is introduced to perceive environment changes, and a variable resolution strategy is combined to focus on processing environment details with high depth change rate, thereby improving the adaptability and detail performance of map updating. The method provides a map construction and updating solution with higher precision and better efficiency for a robot autonomous exploration system, and provides strong support for exploration tasks in a complex unknown environment.

The application discloses a bio-3D printer nozzle structure and a printing method for decoupling control of filament height and filament width, and the nozzle structure comprises a rotating barrel structure, a rotating barrel, a rectangular opening nozzle connected to the bottom end of the rotating barrel, the rotating barrel rotates to drive the rectangular opening nozzle to rotate at a set deflection angle, the top end of the rotating barrel is sealed and slidably penetrates a push rod structure, an extrusion shaft screw module provides axial extrusion force to printing material through the push rod structure to extrude microfilaments, a nozzle support seat is used for supporting the extrusion shaft screw module and the rotating barrel structure, and a control part is used for adjusting the deflection angle, scanning speed and printing height of the rectangular opening nozzle to decouple and control the cross-sectional height and width of the microfilaments. The application can dynamically control the cross-sectional height and width of the extruded microfilaments, realize variable resolution and rapid printing of gradient heterogeneous structures, and meet the requirements of multi-material printing.

This disclosure describes devices, systems, and methods for obtaining image frames with variable resolutions in synchronization with a clock source. An example device may include an image sensor, a clock input, and a controller. The controller includes at least one processor and memory. The at least one processor is operable to execute program instructions stored in the memory to perform operations. The operations include receiving a clock signal via the clock input. The clock signal is a periodic signal that defines at least one scanning interval. The operations also include causing the image sensor to capture a full-resolution image frame during the scanning interval. The operations also include causing the image sensor to capture at least one reduced-resolution image frame during the scanning interval.

A road pedestrian traffic risk prediction method for vehicle active safety, comprising: acquiring a video frame sequence and a first frame pedestrian bounding box; constructing a prediction model comprising a variable resolution image block mapping module, a multi-modal large language model and a spatial suppression enhancement strategy module connected in series; the spatial suppression enhancement strategy module comprises a positioning branch, a prediction branch, a classification branch and a generation branch connected in parallel; training with the video frame sequence and the first frame pedestrian bounding box as input and the crossing behavior label as output. In the inference stage, the generation branch directly outputs the natural language prediction result of "crossing" or "not crossing", discards the traditional multi-model cascade pipeline, does not require external equipment, only requires the original video frame sequence and the first frame pedestrian bounding box, and completes the prediction end to end in the model to directly output the natural language prediction result of "crossing" or "not crossing", greatly reduces the system complexity and deployment cost, and is suitable for practical application scenarios with limited vehicle-mounted computing resources.

The application discloses an AOA-assisted direct wave TOF super-resolution estimation method in a multipath environment. First, radar data is collected, phase offsets are introduced between different channels and subcarriers through AOA and TOF, a wideband array signal model is established, then an estimation grid is divided within the AOA and TOF estimation range, a sparse constraint optimization model is constructed according to the sparsity of the real AOA-TOF compared with the estimation grid, electromagnetic waves penetrating through a building environment are effectively estimated through a variable resolution estimation method, variable resolution solving is completed, finally, based on the difference between the direct wave and the multipath in the AOA-TOF spectrum, the direct wave signal is extracted from all the paths estimated according to the direct wave AOA being equal to 0, and the direct wave TOF estimation is completed. The method can realize super-resolution estimation of the direct wave signal in the electromagnetic wave propagation path in a complex unknown scene, has the advantages of high resolution, small calculation amount, high direct wave separation accuracy and the like, and can be directly applied to CT building layout, wall-penetrating radar and other equipment.

The application discloses a dynamic power quality disturbance signal detection method, device and medium, and the method steps comprise the following steps: S01, acquiring a dynamic power quality disturbance signal to be detected; S02, dividing a signal frequency band, and performing time-frequency analysis on the dynamic power quality disturbance signal by using an improved variable resolution S transform method; the improved variable resolution S transform method is an S transform based on a Gaussian window, and a Gaussian window scale factor is used to optimize the Gaussian window function; S03, performing a synchronous squeezing rearrangement operation on the improved variable resolution S transform result, so that energy components scattered in adjacent frequency intervals are aggregated to real frequency axis positions, and a time-frequency matrix after synchronous squeezing rearrangement is obtained; and S04, detecting signal components of the time-frequency matrix after synchronous squeezing rearrangement. The application can reduce energy diffusion and realize high-precision detection of non-stationary multi-scale complex dynamic power quality disturbance signals.

The present invention discloses a method for constructing variable-resolution vector tiles, comprising the following steps: step 1, determining a vector tile pyramid division level m to n, where m≤n; step 2, constructing a multi-scale vector dataset based on the vector tile pyramid level L; step 3, based on the multi-scale vector dataset constructed in step 2, constructing variable-resolution vector tiles with adaptive data density according to the spatial distribution characteristics of the data; step 4, encoding the variable-resolution vector tiles based on a Geohash algorithm, wherein each encoding includes the level of the tile on the pyramid and the spatial position information of the tile. The present invention can dynamically adjust the tile size according to the spatial distribution density characteristics of the data, thereby ensuring load balancing between different tiles and improving the transmission and rendering efficiency of the vector tiles.