8results about How to "Improve discovery rate" patented technology

The application relates to the technical field of artificial intelligence, and provides a crop growth monitoring system based on artificial intelligence, which comprises the following steps: establishing a unique identifier for each plot, recording and maintaining plot boundary, crop type, sowing date and historical yield information, and organizing adjacent plots into a continuous plot set; based on a pre-trained growth identification basic model, performing growth grade identification on collected plot images, and performing lightweight parameter correction under the constraint of local samples to obtain the growth index of each plot; splicing the growth index of each plot into a growth trajectory in chronological order, calculating a risk index representing the severity of potential problems and an uncertainty index representing the degree of insufficient monitoring; according to the risk index and the uncertainty index, combining the operation time window, the traffic condition and the operation capacity, performing priority sorting and generating a patrol route queue; and outputting a scheduling suggestion for a target plot according to the route queue and the growth trajectory.

The invention discloses a power distribution tower cross arm bending inclination deformation defect image sample generation method, which utilizes a tower model and a panorama to construct a rendering scene, realizes diversified cross arm bending inclination deformation model generation through a bending model, and realizes image sample rendering through path tracking. And finally, converting the three-dimensional bounding box of the cross arm model which is bent, inclined and deformed to an image space to realize automatic generation of defect labeling box information. According to the method, a large number of high-simulation-degree power distribution tower cross arm bending inclination deformation image samples can be quickly and efficiently generated. A large number of training samples of the type of defects are provided for defect detection and recognition algorithm training, the discovery rate of the defect detection and recognition algorithm on the type of defects is improved, and the generalization performance of the defect detection and recognition algorithm is improved.

The application discloses a kind of main and backup routing methods of node trust degree evaluation and interruption adaptation in robot group coordination, the method includes: source node initiates routing request broadcast, and available path from source node to destination node is obtained by adaptive broadcast forwarding strategy;Afterwards, destination node carries out routing reply according to reverse path transmission;If the routing establishment from source node to destination node is successful, then enter the routing decision module based on Q learning algorithm;If the routing decision result selects main routing transmission strategy, then destination node enters trust degree evaluation module, interruption adaptive credible path or no credible path transmission module;If the routing decision result selects backup DTN (Delay Tolerant Networks, time delay tolerance network) routing transmission strategy or routing establishment is not successful, then destination node enters Prophet routing module;Through the main and backup routing methods of node trust degree evaluation and interruption adaptation in robot group coordination provided by the application example, the robustness and robustness of data transmission are improved.

The application provides a power distribution line defect intelligent identification method and system based on visual multi-modal fusion, and belongs to the technical field of power distribution line defect identification; solves the problem of low defect discovery rate of existing unmanned aerial vehicle inspection; comprises the following steps: collecting pictures of infrared cameras and zoom cameras at different far and near focal lengths through an unmanned aerial vehicle; solving an affine matrix for each group of collected infrared images and RGB images, and obtaining an affine matrix for affine transformation of the RGB images to the infrared images; training all collected RGB images using a yolov5l target detection model; cutting the infrared and visible light spliced video stream captured by the unmanned aerial vehicle, then transmitting the visible light video stream to the trained yolov5l target detection model for detection, judging the detected target, if it is a component defect, directly marking in the image, if it is a component target, mapping to the infrared image through the affine matrix, and judging whether the component has a thermal defect; the application is applied to line defect identification.

According to the heterogeneous computing network resource abnormity monitoring and early warning method, unified modeling, unified acquisition processing and unified monitoring are carried out on heterogeneous computing network resources, so that mutual separation of monitoring systems can be avoided, root cause positioning can be assisted, abnormity checking efficiency can be improved, abnormity influence range deduction is carried out based on root causes and topology, and the method has the advantages of being high in practicability and the like. The method is favorable for defining the influence range of exception on tenant services, and comprises the following steps: step 1, carrying out unified collection and processing on heterogeneous resource monitoring data based on a unified monitoring model and an index processing rule; 2, monitoring index anomaly detection is carried out based on an index monitoring threshold value; 3, searching a multi-index anomaly joint detection rule, performing joint detection analysis on a single anomaly monitoring index in combination with the resource topology, and if a matching rule does not exist, directly outputting an anomaly index; 4, auditing resource topology, inferring an abnormal influence range and outputting an inference result; and step 5, performing unified abnormity early warning according to the inference result.

This invention discloses a method, equipment, and medium for testing the corrosion resistance of gas pipelines, relating to the field of pipeline corrosion resistance testing technology. The method includes the following steps: obtaining the zinc bath temperature during hot-dip galvanizing of the gas pipeline to obtain galvanizing temperature data, and screening samples for inspection based on the galvanizing temperature data; acquiring images of the sampled gas pipelines to obtain initial image data, and conducting corrosion resistance tests; acquiring images of the sampled gas pipelines after testing to obtain test image data, and performing image corrosion analysis processing to obtain corrosion image data; obtaining the corrosion area of ​​the gas pipeline to obtain the pipeline corrosion resistance test result. This invention addresses the problem that existing pipeline corrosion resistance testing technologies, when detecting the white rust area in salt spray tests on gas pipelines, cannot dynamically set thresholds based on the surface characteristics of the gas pipeline to accurately separate the white rust from the background in the image, resulting in inaccurate white rust area measurements and a low detection rate of defective products.

The invention provides a sea patrol and reconnaissance device based on cooperation of a wave glider and an amphibious unmanned aerial vehicle, and the device comprises the wave glider integrated with an unmanned aerial vehicle take-off, landing and charging platform, the wave glider is used for carrying out long-endurance patrol on the sea surface, and under the condition that an abnormal target is detected or an instruction of a shore-based command center is received, the unmanned aerial vehicle takes off, lands and charges the unmanned aerial vehicle; sending a control instruction; when the amphibious unmanned aerial vehicle is parked on the unmanned aerial vehicle take-off, landing and charging platform, the amphibious unmanned aerial vehicle is electrically connected with the unmanned aerial vehicle take-off, landing and charging platform for charging; when the amphibious unmanned aerial vehicle receives the control instruction, the amphibious unmanned aerial vehicle takes off from the wave glider to get close to the abnormal target, reconnaissance is conducted on the abnormal target, and reconnaissance data are transmitted back to the shore-based command center through the wave glider; and after reconnaissance is finished, the amphibious unmanned aerial vehicle returns to the unmanned aerial vehicle taking-off, landing and charging platform. According to the invention, the maritime detection capability is improved.

The technical problem this invention aims to solve is to provide an emergency rescue aerial signal generator based on a micro-drone. This signal generator effectively increases the probability of being spotted by rescued personnel, can be carried through security checks, and can broadcast GPS coordinates, effectively reducing the difficulty of rescue and location after discovery. The signal generator includes a drone body, a power and control compartment, and a payload compartment. The upper end of the payload compartment is detachably mounted at the lower end of the power and control compartment. The payload compartment is equipped with a radio broadcast chip and a high-intensity illumination device. Based on a micro-drone design, the light signal remains in the air for a longer period, greatly increasing the probability of being spotted by rescued personnel. The device mainly consists of a micro-drone and electronic components, can be carried on public transportation such as trains and airplanes through security checks, and broadcasts GPS coordinates via the radio broadcast chip, facilitating rescue and location.