42results about How to "Fully aware" patented technology

The invention relates to an unmanned underwater vehicle IVFH (intelligent vector field histogram) collision avoidance method, in particular, an unmanned underwater vehicle two-dimensional IVFH (intelligent vector field histogram) collision avoidance method. With the method adopted, an unmanned underwater vehicle can obtain the location information of an obstacle through processing sensor data in a navigation process, so that the unmanned underwater vehicle can focus on security and rapidity, and the unmanned underwater vehicle can have a certain intelligence like human beings; and reasonable collision avoidance actions can be decided based on factors such as the distance of the obstacle, the distance of a target point, free grid percentage and known field of vision percentage, for example, course and navigational speed instructions can be determined, so that the unmanned underwater vehicle can avoid the obstacle so as to prevent danger. The method of the invention is suitable for collision avoidance conditions of unmanned underwater vehicles.

The invention discloses a heterogeneous network communication-based urban inland inundation monitoring and information service system, which comprises a data acquisition layer, a transmission control layer, a dispatching management layer and an information distribution layer. The invention also discloses a monitoring method of the heterogeneous network communication-based urban inland inundation monitoring and information service system. The method is based on heterogeneous network communication, and comprises the following steps of firstly measuring an inland inundation parameter and an equipment working condition parameter by a sensor and the like, and acquiring the inland inundation parameter and the equipment working condition parameter by a measurement and control module, and sending the acquired parameters to a wireless communication gateway; then, sending to a management center server for processing, issuing a control command by the management center server according to processing results, sending the control command to the measurement and control module so as to control corresponding control equipment; meanwhile, sending service information to an information service terminal by the management center server through the internet and a short message GSM (global system for mobile). The heterogeneous network communication-based urban inland inundation monitoring and information service system and the monitoring method thereof disclosed by the invention have the advantage that urban inland inundation loss is greatly reduced by omnibearing urban digitized draining and waterlogging control guidance dispatching management, and the like.

The invention provides a video processing method, a video processing device, a video processing system, a computer readable storage medium and electronic equipment, and relates to the technical fieldof video processing. The video processing method comprises the steps of obtaining a to-be-processed video, and determining an original video frame sequence to be subjected to frame insertion in the to-be-processed video; determining the change degree of foreground objects of two preset original video frames in the original video frame sequence; according to the change degree of the foreground objects of the two original video frames, determining a selectable time phase of to-be-interpolated frames between the two original video frames; and performing frame interpolation between the two original video frames based on the selectable time phase of the to-be-interpolated frame between the two original video frames to generate a processed video. According to the invention, the inherent contentof the video can be modified.

The invention discloses a traffic contraband recognition method based on self-attenuation weight and multiple local constraints. The method comprises the following steps: preparing original data; datapreprocessing. Data set creation. A structure of a classical convolutional neural network LeNet-5 network is used as a structure of a contraband classification network; for different layers of convolution features output by the LeNet-5 network, transverse connection is carried out according to the direction from a deep layer to a shallow layer in combination with the self-attenuation weight to construct fusion features; a self-attenuation weight coefficient is adjusted in a self-adaptive manner during model training; and a final category is calculated by designing a local multi-constraint strategy for the traffic contraband. According to the invention, automatic recognition and classification of traffic prohibited articles are realized based on deep learning and the convolutional neural network; and automatically learning high separability characteristics of the traffic forbidden objects by extracting a design characteristic learning network, training a traffic forbidden object automatic classification model, and completing the traffic forbidden object automatic recognition method for the common RGB image.

The invention discloses an elevator display device and relates to the technical field of elevator display. The invention comprises a panel, one or more display units and a display control unit; the display units are arranged in landing and / or a lift car and are used for displaying elevator operation information; the display control unit is used for controlling the elevator operation information tobe displayed on the display units, and display unit display image areas include running direction arrows, current floor display, pre-registration information display, current speed display, current floor height display and lift car position indication; and building floor indication is printed on one surface of the panel. The elevator display device can display the speed and the current height information according to the building floor indication model matched with the actual floor and the lift car position indication, can conduct more intuitive dynamic simulation information display for passengers, and solves the problem that an existing elevator display device is not intuitive enough for the passenger.

The invention discloses a human body detection method in a low-illumination environment based on image enhancement, electronic equipment and a storage medium, and the detection method comprises the steps: inputting a low-illumination image into a low-illumination image enhancement module, and obtaining an enhanced image; inputting the enhanced image into an improved human body detection module, and outputting a human body detection prediction result; performing multi-stage joint optimization on the low-illumination image enhancement module and the human body detection module through a multi-task loss function, and training to obtain an end-to-end low-illumination human body detection framework; and inputting the low-illumination image into the trained end-to-end low-illumination human body detection framework, carrying out image enhancement and human body detection, and outputting a human body detection prediction result. The end-to-end low-illumination image human body detection framework constructed by the invention realizes higher detection precision through mutual adaptation of the low-illumination image enhancement module and the human body detection module, and has stronger robustness for human body detection in different illumination environments.

The invention provides a feature matching method based on an attention mechanism and neighborhood consistency. The method comprises the following steps: extracting a picture key point and a descriptor thereof by using a convolutional neural network; key point positions are coded, and position information is fused into descriptors; using a self-attention network and a cross-attention network to enhance the characterization capability of the descriptors and searching a corresponding relation between the descriptors of the two pictures; constructing a graph by using a k-nearest neighbor algorithm according to the attention weight, evaluating neighborhood consistency of nodes by using a graph neural network, and fusing consistency information into attention aggregation; and according to the enhanced descriptor, calculating a matching result by using a Sinkhorn algorithm and mutual neighbor screening. The invention provides a method for integrating neighborhood consistency into an attention mechanism, the neighborhood consistency in the attention aggregation process is dynamically evaluated while global context information is aggregated by the attention mechanism, and local information and global information are combined to jointly enhance the characterization capability of a descriptor, so that higher-quality matching is obtained.

The present invention relates to the technical field of electric power equipment, in particular to an amorphous alloy transformer, which includes a casing. The top of the casing is provided with an annular mouth, and a rubber ring is arranged in the annular mouth. hole, a fixed block is installed in the fixed hole, the fixed block is provided with a mounting hole and a first wire hole, a bearing is installed in the mounting hole, a screw is installed in the inner ring of the bearing, and one end of the screw located inside the housing is threaded with a A positioning rod is provided on one side of the sleeve, a positioning rod is arranged on one side of the screw rod, a placement shell is installed on an end surface of the sleeve facing toward the center of the shell, and a camera is arranged inside the placement shell. The invention has a simple structure, and the internal conditions of the transformer can be photographed by the camera. The camera can move up and down through the rotation of the screw rod, and can rotate along the annular mouth, so that external personnel can fully know the internal conditions of the transformer and facilitate maintenance.

The present disclosure provides a video processing method, a video processing apparatus, a video processing system, a computer-readable storage medium and an electronic device, and relates to the technical field of video processing. The video processing method includes: acquiring a video to be processed, and determining an original video frame sequence to be interpolated in the to-be-processed video; determining the degree of change of foreground objects of two preset original video frames in the original video frame sequence; The degree of change of the foreground object of the video frame determines the optional time phase to be interpolated between the two original video frames; based on the optional time phase to be interpolated between the two original video frames, the Interpolate between frames to generate a processed video. The present disclosure can make modifications to the inherent content of the video.

The invention discloses a method for designing a sensing circuit system based on a delay line type surface acoustic wave. The method includes the following steps: first, making a delay line type surface acoustic wave device without a sensitive film; second, making a delay line including a sensitive film Linear SAW gas sensor; 3. Select the appropriate parameters to form the reference oscillation generating circuit; 4. Select the appropriate parameters to form the oscillation generating circuit; 5. Select the appropriate parameters to form the oscillating signal mixing and processing circuit; Appropriate parameters of the circuit; 7. The connection of the reference oscillation generating circuit, the oscillation generating circuit, the oscillation signal mixing processing circuit and the low frequency signal conditioning circuit. The invention has a reasonable design, and the designed delay line-based surface acoustic wave sensing circuit system has low power consumption and generates a high-stability sensing signal.

The invention relates to a full fabric skin sensing autonomous flexible deformation search and rescue robot and an operating method thereof. The search and rescue robot consists of three parts, namely a head part, a body part and a tail part, wherein the three parts are connected together through a connecting mechanism; the head part is provided with a life detection device, a driving device, a control device, a power device, a communication device, a camera and an infrared device; the body part and the tail part are provided with a driving device, a control device and a power device; each part consists of a plurality of joints; a deformation mechanism is a structure which is used for supporting in the joints; the joints are connected together through the driving device; and the outer surface of the entire robot is covered by a flexible fabric skin layer. The robot is suitable for executing detection tasks of living bodies under ruin environments of earthquake, coal mine disasters andthe like; the robot can also enter a narrow space in ruins through deformation of the robot to detect life information; and thus, the search and rescue range of the robot is expanded, the rescue efficiency is increased, and valuable time is brought for rescuing more lives.

The present invention relates to a method for predicting vehicle queuing dissipation time based on image self-learning, comprising: S1, preset the analysis area of ​​each lane of the entrance; S2, collect the image of the entrance; S3, segment the lane image from the image of the entrance; S4 1. The self-learning neural network analyzes the lane image to obtain the predicted time of vehicle queuing and dissipation; S5. Obtain the actual time of vehicle queuing and dispersal; S6. Calculate the predicted difference between the predicted time of queuing and disperse and the actual time; S7. Judge the predicted difference Whether they are all less than the first preset threshold, if it is judged to be yes, start to predict the vehicle queuing dissipation time in the next cycle, otherwise execute step S8; S8, add the lane image and the actual time of queuing dissipation to the sample relationship database, retrain and Update the self-learning neural network of step S4. Compared with the prior art, the present invention realizes prediction model evolution through image self-learning, and can accurately predict vehicle queuing dissipation time.

The invention provides a method based on visual cognition in radio communication, comprising the steps of obtaining visual information, detecting image features, identifying targets, analyzing radio scenes, selecting radio communication modes and managing resources, etc. The invention can observe the radio communication environment by way of seeing, actively interact with the radio environment, fully recognize the whole scene of the radio environment, learn and reason the radio communication environment and make more effective and accurate decisions. In addition, the invention can be widely applied to the existing radio communication systems, flexibly provide more diversified application services, provide solutions with pertinence for meeting the all-round requirements of the users and realize humanization and intellectualization of radio communications.

The invention discloses a garment treatment control system which represents garment treatment condition through thread crumb generation condition so as to adopt corresponding response measures. The garment treatment control system comprises a thread crumb representing value generation module, a storage module and a thread crumb generation and analysis module, the thread crumb representing value ismainly used for acquiring amount of thread crumbs in a detection area and generating a thread crumb content representing value according to the amount of the thread crumbs, the storage module is mainly used for storing data acquired and generated by each module and threshold values and set values, and the thread crumb generation and analysis module is mainly used for analyzing thread crumb generation condition during running of a garment treatment program according to data in the thread crumb representing value generation module and the storage module. The invention further discloses garmenttreatment equipment with the garment treatment control system.

The invention relates to a method for one measurement and multiple evaluations of the effective parts of total flavonoids of Xintahua. The relative correction factor between anthocyanins was calculated by the correction factor to calculate the contents of Brassin, luteolin, and montiflorin in Xintahua, and determined by liquid chromatography. The detection method of the invention has the advantages of high practicability, simple operation and cost saving, makes up for the deficiency of only measuring the content of a single component of rutin, and can effectively detect four components of rutin, apigenin, luteolin and montanulin in Xintahua. At the same time, the quality control of the effective parts of the total flavonoids of Xintahua was further improved.

The invention discloses a method for designing a mine safety monitoring system based on a surface acoustic wave sensor. The method comprises the following steps: 1. fabricating a delay line type surface acoustic wave device including a sensitive film; 2. selecting suitable parameters for forming an oscillation generating circuit 3. Select the appropriate parameters to form the low-frequency signal conditioning circuit; 4. The connection between the oscillation generating circuit and the low-frequency signal conditioning circuit; 5. The connection between the sensor group and the FPGA main controller; The method of the invention has simple steps, reasonable design, low power consumption of the designed mine safety monitoring system, improves the accurate monitoring of environmental parameters such as temperature, humidity, gas concentration in the mine, facilitates the accurate transmission of the mine environmental parameters to the monitoring center, and improves the performance of the mine. The accuracy of environmental detection and corresponding measures such as early warning are made to avoid the occurrence of safety accidents.

This application belongs to the technical field of cold chain logistics distribution, and specifically relates to a cold chain logistics system for fresh agricultural products with a traceability function. The lower end of the refrigerator box is provided with a guide rail, and the upper center of the refrigerator box is provided with a cold air joint. There is a block device on the top, and a carton storage car is installed in the refrigerating room. The rollers at the lower end of the carton storage car roll along the guide rail. For the cartons of fresh agricultural products, temperature and humidity sensors are installed near the cartons. The data acquisition system collects the temperature and humidity data of the temperature and humidity sensors in real time. Through the cooperation of carton storage vehicles and refrigerated vehicles, the air conditioner can effectively refrigerate the fresh agricultural products in the cartons, and use traceability The system determines the collection of traceability information of fresh agricultural products in the process of collection, transportation, sales, etc., to ensure the safety of the quality of agricultural products and consumers' full awareness of agricultural products when purchasing.