13results about How to "Solve the robustness problem" patented technology

The invention discloses a road obstacle recognition method based on machine vision, and the method comprises the steps: carrying out the precise positioning of the spatial position of an obstacle through a multi-sensor information fusion algorithm according to the azimuth and distance information of the obstacle estimated through a sound source positioning algorithm and the position information outputted by an obstacle detection model, and improving the positioning precision; the method comprises the following steps: acquiring guide mark information, such as road signs and lane lines, extracting guide mark features through a semantic segmentation algorithm, carrying out dynamic fusion on the guide mark features and an obstacle recognition result, and improving the accuracy and robustness of obstacle recognition by using prior information; in order to solve the problem of insufficient parallax analysis precision in long-distance, high-speed motion and other scenes, a monocular depth estimation algorithm based on deep learning is introduced, pixel-level depth information is predicted from a single image through a convolutional neural network, and the precision of obstacle distance estimation is improved.

The invention discloses a multipath channel parameter reconstruction and beam coverage prediction method, and relates to the technical field of wireless communication. Aiming at the problems of low data utilization efficiency, limited environment modeling precision, strong coupling of measured data and antenna beam configuration and the like in the prior art, the method comprises the steps of configuring antenna beams and orientation parameters, collecting reference signal receiving strength, performing deterministic channel modeling simulation, establishing a mapping model, performing sparse recovery, constructing a channel propagation model, evaluating a channel map and the like. In combination with a coherence perception weighting network (CARE-Net) algorithm and ray tracing (RT) physical prior guidance, accurate reconstruction from a low-dimensional reference signal receiving strength (RSRP) measurement value to a high-dimensional multipath parameter is realized. The method has the advantages that the reconstructed multi-path parameters are decoupled from the antenna configuration, the method has the cross-beam / cross-configuration generalization prediction capability, the channel coverage performance under different antenna configurations can be accurately predicted, a reliable basis is provided for wireless network optimization, and the method is low in cost, high in precision and strong in generalization.

The present invention relates to a permanent magnet synchronous motor control method and system based on second-order auto-disturbance rejection control, which belongs to the field of permanent magnet synchronous motor control technology and solves the problems of poor robustness and weak anti-disturbance capability of traditional auto-disturbance rejection controllers. Based on the established d-q axis mathematical model of the permanent magnet synchronous motor, a state equation is obtained; a second-order auto-disturbance rejection controller is established; based on a model reference adaptive observer, an estimated speed ω of the permanent magnet synchronous motor is obtained. r ; Set the speed of the permanent magnet synchronous motor ω r and speed given value ω r * At the same time, input the second-order ADRC to obtain the q-axis voltage prediction value u q ; and, the result obtained by subtracting the d-axis current value of the permanent magnet synchronous motor from the reference value of the d-axis current is input into the PI controller to obtain the d-axis voltage prediction value u d ; The PWM control signal is obtained and input into the inverter connected to the permanent magnet synchronous motor to realize the drive control of the permanent magnet synchronous motor. The robustness and anti-interference ability of the controller are improved.

The invention provides a router fault automatic repair method, system and device and a medium, and the scheme comprises the steps: responding to the occurrence of a fault, and obtaining log data corresponding to the current fault in real time; obtaining a problem classification result and a problem mark of the current fault by using a pre-trained fault classification model based on deep learning based on the obtained log data; based on the problem classification result and the problem mark, accessing a pre-constructed problem solving large model according to a preset public network service path to obtain a solution of the current fault; and executing the currently obtained solution to realize automatic repair of the router fault. According to the scheme, by designing the problem solving large model, the router can automatically repair most of self faults, and by periodically updating the problem solving large model, the robustness of the problem solving large model can be effectively improved.

The application discloses an image processing method, device and system. The method comprises the following steps: receiving a first image; processing the first image by using a processing model to obtain a second image, wherein the resolution of the second image and the resolution of the first image satisfy a first preset condition, the processing model is used for inputting the first image into a first generation network to obtain a third image, inputting the third image into a second generation network to obtain the second image, and the resolution of the third image and the resolution of the first image satisfy a second preset condition; and displaying the second image. The application solves the technical problem that the robustness and stability of the image processing method in the related art in a real scene are poor.

The application discloses a flight control oriented OTA upgrading method, system, device, computer readable storage medium and program product, belongs to the field of computer science and technology, and aims to solve the problems of insufficient safety of an existing upgrading process, unreliable data transmission and weak batch management capability for a heterogeneous architecture. The method establishes a first connection, sends a start request frame containing a specific identification code and an inverse code, sets an upgrading flag and resets the flight control, and disconnects the connection. After resetting, a second connection is established, firmware is transmitted and written, an end request frame with the same frame structure is sent, the flight control is finally reset and starts new firmware, and the connection is disconnected. The frame structure containing the identification code and the inverse code, the instruction code and the check code enhances the communication reliability and the anti-interference capability. The stage resetting and the flag mechanism ensure that the upgrading process is controllable and recoverable, avoids firmware damage or startup failure, and improves the safety and stability of the flight control system remote upgrading.

The invention provides a circulating system equipped with a submersible type cylindrical linear induction electromagnetic pump, which is characterized in that the electromagnetic pump is arranged in a container filled with liquid metal along the longitudinal direction, an inert gas tank is arranged for sealing, and a radiating fin structure is arranged on the outer side of an external stator of the electromagnetic pump. According to the submersible electromagnetic pump circulation system, the occupied area and weight of the liquid metal circulation loop are remarkably reduced, the service life of the liquid metal circulation loop under different working condition requirements is greatly prolonged, and the requirements of deep sea, deep space and other extreme environments for robustness and light weight of equipment can be effectively met.

The invention discloses a noise correlation cross-modal matching loss adjustment method and device based on meta-learning. The method comprises the following steps: constructing a pairing sample set containing a multi-modal data pair; quantifying semantic correlation of each multi-modal data pair in the pairing sample set by using a cross-modal model, and selecting an initial loss function; constructing a loss adjustment network, and balancing the noise sensitive loss function and the noise insensitive loss function to obtain an adaptive loss function; optimizing the loss adjustment network by using a meta-learning algorithm; updating model parameters of the cross-modal model on the target noise data set by using the optimized loss adjustment network; and inputting the query target and each object in the matching database into the updated cross-modal model to obtain the similarity of the query object relative to each object in the matching database. The problem that the robustness and the matching accuracy of the cross-modal model are difficult to consider at the same time in the prior art is solved, and powerful support is provided for landing of the cross-modal model in an actual scene.

The application relates to the technical field of file processing, and discloses a file processing method suitable for structured and unstructured data, which comprises the following steps: S1, identifying the type of an input file and classifying the input file, including structured data, semi-structured data and unstructured data; S2, pre-processing and feature extraction are performed on different types of data; S3, the correlation between different data modalities is quantified based on multi-modal mutual information optimization; S4, the interaction consistency between data modalities is verified, and the fusion weight is dynamically adjusted. Through classification and feature extraction of structured data, semi-structured data and unstructured data, efficient fusion of multi-modal data is realized by using mutual information optimization and a dynamic weighting strategy. Compared with a traditional method, the application can significantly improve the precision and robustness of data processing, and provides an efficient solution for multi-modal data fusion in a complex scene.

The invention discloses a line feature matching method based on Fourier representation and posterior probability estimation, and the method comprises the steps: detecting and extracting line features on an image sequence pair, and calculating a binary descriptor; obtaining an initial line feature matching pair; a compact Fourier series is introduced to represent a mapping relation satisfied between adjacent images; prior maximum likelihood estimation is established; iteratively solving a maximum post-test estimation parameter satisfied by the line feature matching pair; establishing a uniform distribution probability model; screening image line feature matching pairs meeting a probability threshold value; and searching residual feature matching pairs, completing iteration and realizing accurate and steady matching of image line features. According to the method, the problem of accurate and robust matching of the image line features is solved only through the basic line feature descriptors, the mapping relation between the images is represented through Fourier, the likelihood estimation model is established in combination with the geometrical relation met by line feature matching, and accurate and efficient matching of the line features is achieved based on EM algorithm iterative convergence.

This invention relates to a remote sensing image scene classification method based on uncertain visual-language alignment, comprising the following steps: acquiring remote sensing images as training and testing sets; using a CLIP dual encoder to map the original image and text to a shared point representation space; the uncertain encoder predicting each embedding vector along two paths; internally, the uncertain encoder performing two-level interactions on the input embedding vectors; globally modeling the image and text as two Gaussian distributions based on the mean and variance vectors, maximizing the image-text similarity that should be correctly matched in the entire batch; acquiring new remote sensing images and inputting them into the trained model, which then classifies the scenes in the remote sensing images. This application captures fuzzy mappings between modalities in the probability space, providing a more generalized representation for downstream remote sensing image scene classification tasks.

The embodiment of the invention provides a voice endpoint detection method, a storage medium and a program product. The method comprises the steps that a voice signal to be detected is acquired, framing and windowing processing is carried out on the voice signal, a framing and windowing signal is obtained, and the voice signal comprises noise; first nonlinear filtering processing and second nonlinear filtering processing are carried out on the framing windowing signal, a first enhanced signal and a second enhanced signal are obtained, and a delay parameter corresponding to the first nonlinear filtering processing is smaller than a delay parameter corresponding to the second nonlinear filtering processing; performing cepstrum domain feature extraction processing and fusion processing on the first enhanced signal and the second enhanced signal to obtain fusion features; and according to the fusion feature, the voice signal is detected to obtain a detection result, and the accuracy and stability of voice endpoint detection are improved.

This invention discloses a method and apparatus for 3D scene reconstruction based on neural networks and multi-view consistency. The method includes: extracting image frames from video data and downsampling them; using a pre-trained monocular absolute depth estimation model to predict the downsampled images; using a scale offset recovery module to recover the inconsistent scale and offset between downsampled absolute depth maps; projecting the obtained scale offset consistent depth maps between downsampled image frames using optimizable camera parameters; selecting local and global keyframes; supervising optical flow information, geometric consistency, and regularization terms; optimizing depth and camera parameters; inputting the relevant parameters into an image-depth fusion module for processing; and outputting the 3D scene reconstruction result. This invention reduces the reliance on sensors in existing methods, improves the density and robustness of 3D scene reconstruction methods, and solves the problem of difficulty in achieving both robustness and density in existing 3D scene reconstruction methods.