121 results about "Embedded hardware" patented technology

The invention relates to a high-efficiency image recognition system based on embedded edge equipment, which belongs to the technical field of computer application and comprises a hardware acceleration module, an image recognition module and an image recognition module, reasoning tasks are distributed to different cores and a model quantification module through dual-core cooperation, quantification converts high-precision floating-point number representation into low-precision integers through weight and activation in a deep learning model, an automatic deployment module automatically converts the trained deep learning model into a format suitable for an embedded hardware platform, and the embedded hardware platform is used for realizing real-time reasoning. The data processing module is used for preprocessing and enhancing input data and ensuring that the data meet the input requirements of the deep learning model, and the reasoning engine module is responsible for loading and operating the optimized deep learning model on embedded equipment. And the efficient and reliable image recognition function is realized while the calculation, storage and energy consumption limitation of the embedded equipment is met.

The invention discloses an obstacle detection method for a visual impaired group guiding waistcoat system based on improved YOLOv11, and the method comprises the steps: 1, obtaining an obstacle data set, and completing the marking work of the data set; 2, a backbone network of the YOLOv11 is replaced by a ShuffleNetV2 (ShuffleNetV2); thirdly, a lightweight detection head is redesigned, and subsequent deployment is facilitated; 4, completing the training of the improved YOLOv11 model by using the data set; 5, deploying the improved YOLOv11 detection model into embedded hardware equipment for sensing; and 6, performing model reasoning to realize real-time obstacle detection of the camera on the waistcoat. According to the invention, the real-time performance and accuracy of obstacle detection on the waistcoat can be ensured, a reliable basis is provided for guiding a visual impaired group to make an obstacle avoidance decision, and the travel safety of the visual impaired group is ensured.

The invention discloses a toll station special situation emergency processing system integrated with a localized AI large model, and belongs to the technical field of toll station management and control. Comprising an edge computing device, a multi-element sensing module, a localization AI large model engine, a dynamic rule engine and an execution control interface. The edge computing device is responsible for being deployed in a toll station site and is embedded hardware with AI acceleration computing power, and the multi-source sensing module is responsible for being connected with a camera, a millimeter wave radar and an ETC-RSU device. According to the invention, by deploying the lightweight large model in the edge server, millisecond-level identification and automatic disposal of special situations such as vehicle card punching and dangerous goods leakage are realized. The system adopts a multi-modal data fusion technology, and is combined with a dynamic plan engine, so that the operation of core functions can still be ensured in an off-network environment, and the emergency response efficiency and safety of the toll station are remarkably improved.

The invention discloses a multi-bus decoupling distributed embedded hardware rendering architecture, system and method, and relates to the technical field of ultra-high-definition video hardware processing, and the key points of the technical scheme are that the architecture comprises a multi-bus decoupling module which comprises a plurality of hardware buses which are physically isolated from one another, each hardware bus is an exclusive hardware transmission link bearing a single-type manufacturing task; the modular processing unit is an independent hardware board card and is integrated with an external signal input port, an upstream bus signal input port and a downstream bus signal output port; the plurality of modular processing units are cascaded in sequence through a hardware bus in the multi-bus decoupling module to form a distributed assembly line rendering link; when the modular processing units are newly added, the signal processing capability and the rendering synthesis capability are linearly improved along with the increase of the number of the modular processing units. According to the invention, the problem of performance bottleneck of the traditional architecture in processing 4K / 8K ultra-high-definition and multichannel rendering is fundamentally solved.

The invention discloses a nuclear power plant instrument control system control algorithm simulation device and a simulation method thereof, and relates to the technical field of nuclear power plant instrument control software. The device comprises a user interface used for responding to user interaction operation, constructing a model structure of a control algorithm and receiving user input data as input data of the model structure; the code generation engine is used for analyzing the xml file corresponding to the model structure and obtaining source code implementation of a main operator of the model structure based on an analysis result; and the model entity is used for packaging and compiling the source code of the main operator to obtain an executable program of the model structure, executing the executable program based on the input data of the model structure to obtain a simulation result of the model structure, and sending the simulation result to the user interface for display. According to the device, the software verification process can get rid of dependence on embedded hardware equipment, and the software development and debugging efficiency is improved.

The invention discloses a camellia oleifera fruit identification optimization system based on an attention mechanism, and relates to the technical field of agricultural computer vision, and the system comprises a dynamic occlusion perception attention module which is connected to an input layer of a cross-modal spectral feature collaborative fusion network through a space-time double-flow occlusion reasoning unit. According to the oil tea fruit recognition optimization system based on the attention mechanism, the feature discrimination capability in an environment with dense branches and leaves is remarkably improved, the target recognition robustness in a low-contrast scene is effectively enhanced, the mismatching risk caused by illumination mutation is reduced, the tiny gradient change of young fruits is accurately captured, semantic and detail features are balanced, and the recognition efficiency is improved. Meanwhile, efficient parallel computing is achieved through embedded hardware deployment, real-time response under a complex scene is ensured, weak links of the model are iteratively strengthened, the stability and generalization ability of the system are overall improved, and a high-precision and low-delay camellia oleifera fruit recognition solution is provided for intelligent agriculture.

The invention provides an auxiliary correction method and system for color vision disorder, and the method comprises the following steps: S1, carrying out the color and texture decoupling of an input image through a perception consistent state space module, and extracting a global color distribution feature and a perception invariant texture feature; generating a personalized enhanced image in combination with dynamic color offset adjustment and CVD perception quality evaluation; s2, constructing a dynamic heterogeneous marshalling architecture, dynamically combining a high-precision model and a lightweight module, and realizing a self-adaptive network architecture with multi-level complexity and performance balance through frequency domain sensing decoupling, heterogeneous multi-dimensional static kernel and implicit neural frequency domain acceleration technologies; and S3, acquiring image data in real time by adopting an embedded hardware platform, optimizing a processing flow through a dynamic complexity threshold constraint model, outputting an enhanced image in combination with AR / VR equipment and a standardized interface, and guiding continuous optimization of a personalized color enhancement algorithm through effect analysis evaluation feedback.

The invention relates to an intelligent power supply switching method suitable for a power station, and aims at solving the problems that an existing spare power automatic switching device is low in response speed, single in starting condition, incomplete in switching-on logic and the like. According to the invention, parameters such as voltage, frequency, phase and current of the power supply are monitored in real time, and various switching logics such as rapid closing, synchronous capture closing, residual voltage closing and long delay closing are combined, so that rapid and safe switching between the main power supply and the standby power supply is realized. The system supports various triggering modes such as manual starting, protection starting, voltage loss starting, reverse power starting and non-current starting, and can adapt to complex scenes such as single-bus segmentation, single-bus and isolated network operation. Through an embedded hardware platform, a DSP + ARM + CPLD architecture is adopted, the system has efficient data acquisition and logic operation capability, and the switching time can be shortened to be within 10 milliseconds. Meanwhile, multiple safety mechanisms such as overcurrent protection, reverse power protection and decoupling protection are provided, and misoperation and parallel operation risks in the switching process are avoided.

The invention provides a real-time monitoring and root cause positioning method and system for software defects. The method comprises the following steps: collecting real-time monitoring data of a software processing thread, and generating a thread competition thermodynamic diagram for identifying a shared resource contention point through time sequence association processing; triggering a server memory bus embedded hardware detection device based on a contention point to dynamically capture a locking state transition signal, and converting the locking state transition signal into a locking event sequence; constructing a locking contention track diagram according to timestamp sorting, and completely displaying a process path of a locking mechanism from obtaining to releasing; constructing a dependency topological structure of the thread and the lock based on the trajectory graph, and identifying a resource contention chain; and mapping the contention chain into an unsynchronized shared variable access path in the source code, and triggering a real-time alarm signal. According to the method, the access path of the unsynchronized shared variable is accurately positioned, the lock competition diagnosis efficiency is improved, and the system deadlock risk is zeroed.

The invention relates to the technical field of automatic control, in particular to a control system optimization problem compiling method, device and system and a computer readable storage medium, and the method comprises the steps: obtaining a to-be-compiled optimization problem, and recognizing the structure information and feature information of the to-be-compiled optimization problem; obtaining parameter information of the embedded hardware, and matching and optimizing a corresponding numerical solution algorithm in combination with the structure and the feature information to obtain an optimized numerical solution algorithm; converting the optimized algorithm, structure information and parameter information into a first embedded execution code without dynamic memory allocation; performing memory and cache optimization on the memory layout of the first embedded execution code to generate a second embedded execution code; compiling the second embedded execution code into a binary file adaptive to embedded hardware, and deploying the binary file; the environment parameters are obtained and transmitted into embedded hardware, the target control solution is obtained by operating the binary file and solving based on the environment parameters, and the calculation efficiency and hardware compatibility in an embedded scene are improved.

The invention discloses an embedded hardware sensing dynamic feedback and data acquisition control method, and particularly relates to the field of general control or regulation systems, which comprises the following steps of: establishing a complete sensing acquisition framework by initializing a hardware control parameter set, synchronously acquiring original physical data and environmental parameters of a sensor, and preprocessing the original physical data and environmental parameters into available measurement values; comprehensively evaluating the deviation between actual output and a target value based on a quantitative difference model, and realizing dynamic correction and real-time feedback optimization of software level control parameters through a gradient optimization algorithm; when the parameter optimization effect does not reach the expectation, a hardware-level calibration process is automatically triggered, and temperature drift, power supply fluctuation and other physical characteristic drifts are compensated; a closed-loop control link is formed through multiple rounds of acquisition verification, it is ensured that the data precision is stable and reaches the standard, the sensing precision stability and control reliability of an embedded system in a complex environment are remarkably improved, and the method is suitable for high-precision embedded sensing application scenes.

The invention discloses a flight control end intelligent algorithm deployment method based on adaptive pruning, and the method comprises the following steps: S1, collecting flight control task state data and resource state data, and generating a flight control task resource state data set; s2, constructing a task characteristic vector based on the flight control task resource state data set; s3, inputting the task characteristic vector into a pruning strategy generation module to generate a dynamic grouping pruning strategy; s4, executing a dynamic grouping pruning operation on the improved Shuffle Net structure, and generating a task adaptive pruning network; s5, deploying the task adaptive pruning network to flight control end embedded hardware, and generating an intelligent reasoning control result; s6, monitoring the execution effect of the flight control task corresponding to the intelligent reasoning control result in real time; and S7, dynamically adjusting the task characteristic vector and the dynamic grouping pruning strategy to form an updated task adaptive pruning network. According to the method, the improved Shuffle Net and adaptive pruning are adopted, and real-time optimization and efficient deployment of a flight control end intelligent algorithm are realized.

The invention discloses a fast file system scheme applied to embedded hardware. Aiming at the characteristics of fixed storage size and few file directories of embedded hardware files, file management of a file system is simplified by adopting a file distribution area and a data area. The fast file system is divided into a file distribution area and a file data area. The file distribution area records a file name, the maximum file capacity and a file data area address. The file data area stores actual file content. In order to solve the problem that the file system is damaged due to sudden power failure during reading and writing of a common file system, the file distribution area is solidified according to the file number and the maximum capacity in the created file system in a pre-distribution mode, and the situation that the whole file system is damaged due to accidental interruption of file writing operation is avoided. According to the fast file system, file retrieval and file data area positioning can be accelerated through a method for hiding file names and file data area addresses. The method is simple in structure and suitable for embedded hardware.

The invention relates to the technical field of image processing, in particular to an asphalt pavement crack detection method and system suitable for a mobile platform, and the method comprises the steps: obtaining pavement crack images in a public data set and a self-built data set, carrying out the preprocessing optimization and marking of the pavement crack images, and generating a data set; the data set comprises a training set, a verification set and a test set; inputting a training set in the data set into a YOLOv5 network, wherein the YOLOv5 network comprises a trunk feature extraction network, a neck feature fusion network and three detection heads; constructing a road crack detection model based on improvement of a trunk feature extraction network in the YOLOv5 network; inputting a test set in the data set into the road crack detection model for performance evaluation; the complexity of network and operation is greatly reduced, memory access is reduced, the precision is improved compared with that of a source code, and algorithm deployment on embedded hardware equipment is facilitated.

The present invention belongs to the technical field of data acquisition and processing terminal equipment, and specifically relates to an embedded multi-interface data acquisition and processing device, which includes: an embedded hardware mainboard, a main embedded hardware platform and multiple sub-embedded hardware platforms arranged on the embedded hardware mainboard; the main embedded hardware platform is connected to the multiple sub-embedded hardware platforms via a CAN-FD bus, each sub-embedded hardware platform is connected to a corresponding external device, and the data collected by each sub-embedded hardware platform is sent to the main embedded hardware platform for processing or in response to instructions from the main embedded platform.

The invention discloses a digital zooming system and method based on deep learning, and belongs to the field of computer vision and image processing. The system is deployed on a microscope and an embedded hardware platform, and carries out dynamic center cutting on a low-resolution microscope image by receiving a zooming instruction so as to reserve a high-information-content area; then, a lightweight super-resolution model is used for processing the cut image, the model integrates a lightweight denoising network, multi-scale feature extraction, improved Pixel Shuffle upsampling and a global-local feature fusion mechanism, high-frequency details are effectively reconstructed, and artifacts are inhibited; and finally, outputting a high-resolution image to a display. According to the method, the multi-scale residual error and the channel attention are combined, key details such as image edges / textures are preferentially reserved, artifacts can be effectively avoided, and compared with a traditional zooming mode, the high-power image is clearer, and more edge details are reserved; according to the method, depth separable convolution and lightweight Transform are adopted, the number of model parameters is small, the reasoning speed is high, and mobile terminal deployment is adapted.

The utility model discloses a hardware embedding jig, and relates to the technical field of hardware machining and positioning. The fixture comprises a fixture body arranged outside the hardware, the jig body comprises a bottom supporting piece, an end limiting piece installed at the upper end of the bottom supporting piece in a matched mode, a first side positioning piece, a second side positioning piece, a first installation part integrally arranged on the inner side of the first side positioning piece, and a first assembly layer assembled on the outer side of the first side positioning piece, wherein the first side positioning piece and the second side positioning piece are located on the side face of the hardware. The second mounting part is integrally arranged on the inner side of the second side positioning piece, and the second assembling layer is assembled on the outer side of the second side positioning piece. By means of the precise positioning structure of the first side positioning piece, the second side positioning piece, the first installation part and the second installation part, it is ensured that hardware can be rapidly and precisely installed to the preset position, the time for manual measurement and adjustment is shortened, and the accuracy and efficiency of installation operation are improved.

1. The name of the design product: control module (POM Nano RP). 2. The use of the design product: for embedded project development, as the core operation processing unit of embedded systems, providing convenience for embedded hardware development. 3. The design points of the design product: the combination of shape and pattern. 4. The picture or photo that best indicates the design points: perspective view.

An integrated circuit (IC) chip includes a first memory storing first information and a second memory storing second information that needs to be protected against unauthorized access. A communication interface circuitry provides a processor external to the IC chip with read and / or write access to components of the IC chip. An embedded hardware security circuitry selectively provides the processor external to the IC chip with secure access to the second memory. Interconnect circuitry i) selectively grants the processor insecure access to the first memory via the communication interface circuitry, ii) selectively grants the processor secure access to the embedded hardware, and iii) restricts access to the second memory.

The application discloses a kind of hysteresis reference window sliding window adaptive threshold surge detection system and method, belong to aero-engine surge detection field.The method includes: real-time acquisition aero-engine pressure sensor output analog voltage signal, and carry out partial pressure, filtering and analog-digital conversion, obtain discrete sampling sequence;With sliding window intercept analysis window and carry out linear fitting, calculate its slope and residual standard deviation;Established by historical analysis window eigenvalue, with current window maintains hysteresis distance reference window;Based on the statistics of eigenvalue sequence in reference window, dynamically calculate adaptive threshold;By comparing current window eigenvalue with threshold value, and when the eigenvalue of continuous multiple windows exceeds threshold value, determine surge.The detection scheme provided by the application significantly reduces the amount of calculation through local window processing and dynamic threshold adjustment, solves the problem that existing algorithms are difficult to be deployed in real time in embedded hardware, and improves the detection accuracy and working condition adaptability.

The invention discloses a hardware temperature compensation pressure sensing module based on an LTCC embedded structure and a preparation method, and relates to the technical field of sensors. The module comprises an LTCC substrate body, an embedded main control unit, a surface sensing unit and an embedded hardware temperature compensation network, a closed embedded cavity is formed in the LTCC substrate, a vertical interconnection conductor is arranged in the LTCC substrate, the main control unit is embedded in the cavity, and the surface sensing unit outputs differential signals containing temperature excursion; the embedded thermistor and the partial pressure filter form a temperature reference signal, and the compensation resistor is used for zero calibration; the rear-stage signal conditioning circuit amplifies the differential signal, superimposes the pressure signal and the temperature reference signal in an analog domain according to a weighting proportion and performs low-pass filtering, and outputs the pressure signal and the temperature reference signal to a master control analog-to-digital conversion end after realizing temperature drift offset; embedded interconnection and hardware temperature compensation are achieved, temperature drift is restrained, heat dissipation shielding is enhanced, and the sampling utilization rate and mass production consistency are improved.

The invention discloses a multi-network integration control method and system based on network data feature recognition. According to the scheme, the method comprises the steps that an embedded Linux system is loaded through a multi-core embedded hardware platform, a switch chip driver is initialized, a VLAN is divided, and a configuration management core kernel module is established to serve as a control center; extracting a port, a protocol type and a connection state of the data packet to construct a feature vector, and distributing a service mark for the data packet through a multi-stage matching engine matching rule; querying a dynamic routing strategy table by taking the service mark as a main key, generating a forwarding parameter and synchronizing the forwarding parameter to a kernel routing cache and a physical switching chip; network state data are collected through Netlink, SNMP and active detection multiple channels, and event response is triggered after fusion analysis; and a routing strategy is dynamically optimized in combination with a strategy rollback mechanism, so that the stability of adaptive adjustment is ensured. According to the invention, the flow control precision and the adaptive capability of the multi-network fusion scene are improved.

The application discloses an image denoising processing method and device and a storage medium. In the method, an image frame to be processed is divided into a plurality of blocks with overlaps between the blocks, each block is input to a trained denoising model for denoising processing, each block after the denoising processing is subjected to boundary processing in at least one of a row direction and a column direction based on an overlapping area of the current block and adjacent blocks, and the plurality of blocks after the boundary processing are combined to obtain a processed image frame. The scheme not only improves the denoising effect of the deep learning denoising processed in blocks on embedded hardware, but also significantly reduces the blocking effect in the denoised image.

The present invention relates to a hand-held imaging system, device and method, composed of optical, electronic and mechanical modules, of specific ergonomic and functional design, configured to obtain images and videos in the visible and infrared spectrum of the anterior and posterior segment of the human eye, mainly non-mydriatic retinal exams controlled by an external mobile device, such as a smartphone, tablet or embedded hardware, for clinical purposes.

The invention relates to the technical field of bladder internal pressure monitoring and management, and provides a neurogenic bladder internal pressure monitoring and management system based on incremental learning, which comprises a data acquisition module, an embedded hardware platform and a user side prompt module. The data acquisition module is responsible for acquiring physiological parameter information such as bladder internal pressure, abdominal pressure and body position angle in real time. The bladder internal pressure prediction module integrated by the embedded hardware platform establishes a pressure-time relationship in a piecewise linear modeling mode, continuously adjusts model parameters by applying an incremental learning algorithm, and generates prediction data in a future time window; and the multi-modal state identification module receives the prediction data and the current multi-source physiological information, performs comprehensive analysis by applying a fuzzy logic reasoning mechanism, identifies and eliminates the influence of instantaneous interference factors, and outputs the grade evaluation of the bladder state. And the user side prompting module executes a grading early warning strategy according to the state grade and sends intervention prompting information of different emergency degrees to the patient.

The invention discloses an embedded software construction method and device, electronic equipment and a storage medium, and belongs to the technical field of software development, the method comprises the steps that construction parameters configured by a user are provided, and the construction parameters comprise a hardware identifier used for specifying a target embedded hardware platform type; calling a corresponding configuration file from a preset configuration library according to the hardware identifier, wherein the configuration file is used for providing a compiler tool chain path and default compiling options related to the platform; generating a compiling rule frame based on the configuration file, wherein the compiling rule frame comprises a to-be-compiled file list, a final compiling option and a target generation rule; and executing compiling operation according to the compiling rule framework to generate a target output file. According to the method, the preset configuration file is automatically matched through the hardware identifier, so that manual configuration redundancy is greatly reduced; dynamic switching of tool chain configuration during cross-platform construction is realized, and zero modification of platform migration is ensured.

The present application belongs to the technical field of embedded processor firmware, and particularly relates to an efficient firmware running system for a neural network processor, aiming to solve the problems of slow firmware deployment speed, large occupied space and low processing efficiency of files generated after compilation by a neural network compiler of the existing neural network processor. The system comprises: a file preprocessing unit configured to obtain files generated after compilation by a neural network compiler and preprocess the files to obtain preprocessed files; an embedded hardware platform configured to store the preprocessed files to a set memory address; and an efficient firmware configured to read and parse the preprocessed files, obtain operator stream files corresponding to a neural network model, and sequentially execute each operator through a pre-built operator execution efficient optimization method until a complete calculation of the neural network model is completed. The present application improves the processing efficiency of files generated after compilation by a neural network compiler, improves the firmware deployment speed, and reduces the occupied space.

Some embodiments provide a novel method for offloading firewall operations from a host computer executing a set of one or more virtual machines (VMs) to a physical network interface card (PNIC) connected to the host computer. The method configures, on the PNIC, a first firewall to determine actions to perform on flows associated with the set of VMs, and to offload processing of the flows to a flow-cache second firewall of the PNIC. The method configures, on the PNIC, the flow-cache second firewall to process a first set of flows based on a first set of actions determined by the first firewall, and to offload processing of a second set of flows to an embedded hardware switch of the PNIC. The method configures, on the PNIC, the embedded hardware switch to process the second set of flows based on a second set of actions determined by the first firewall.

The present application relates to the field of vehicle electronic control and active safety technology, and proposes a kind of vehicle driver incapacitation emergency control system and method.It includes: through driver monitoring camera and processing unit, based on eyelid closure degree and driving operation signal joint determination driver incapacitation, automatically trigger emergency response state;In response to the state, wake up forward perception unit to identify lane line and shoulder area;Local decision unit executes a finite state machine, sequentially executes lighting double flash warning light, speed gradually reduces and lane keeps based on lane line detection, and after vehicle speed reduces to threshold, guide vehicle to right side safe shoulder lane change and brake parking, while sending alarm message to terminal server in parallel to prepare subsequent remote manual takeover.The present application can fundamentally solve the timeliness and reliability problem of emergency control after driver sudden incapacitation without relying on driver active operation and remote communication large cycle, and can be deployed only with low-cost embedded hardware.

The invention belongs to the technical field of embedded graphic systems, and particularly discloses a mouse action response method of an embedded graphic system. According to the scheme, firstly, a response event of a mouse and the data sending frequency of the mouse are obtained; then, whether data is optimized or not is judged based on the data transmission frequency of the mouse and the mouse events, then the data is transmitted to the graphic system to be displayed, and if the data transmission frequency is larger than the response frequency of the graphic system, the continuous and identical mouse response events are optimized and then displayed by the graphic system. By means of the scheme, the problem that a graphic display system is stuck when a domestic embedded hardware platform is matched with multiple types of mouse devices can be successfully solved.