Abstract: A heterogeneous image registration method includes: performing edge detection on collected images, in combination with a curvature scale space strategy to extract contour curved segments in an edge image. Implementing a feature point detection strategy based on global and local curvature detecting feature points in the contour curved segments, and obtaining the nearest minimum local curvature of the feature points pointing to starting and end points of the contour, respectively. Calculating the number of neighborhood sampling points and neighborhood auxiliary feature points of neighborhoods on both edges of each of the feature points according to the nearest minimum local curvature. Using neighborhood auxiliary feature points and feature points to form a feature triangle, calculating an angle bisector vector and a main direction corresponding to the feature point in the feature triangle.

Abstract: The present invention provides a high-precision identification method and system for substations, including building a Mask RCNN objection recognition network model based on convolutional neural networks; inputting acquired image information of a object into the Mask RCNN object recognition network model for preliminary recognition and outputting a recognition result of the object; using an information entropy to create a semantic decision tree and correcting the recognition result of the object according to a principle of relative correlation between different objects and outputting a final recognition decision result; reading the recognition decision result to obtain a true type of the object to be recognized. The present invention greatly improves the accuracy of image recognition of substations, and has a positive role in the research and development of automatic inspection equipment for inspection robots.

Abstract: The present disclosure provide a method for identifying power equipment targets based on human-level concept learning, including: creating a dataset of power equipment images, and annotating power equipment in power equipment images; training neural network and Bayesian network with the annotated dataset and respectively acquire identification results and conditional probabilities; calculating probabilities of unions with the conditional probabilities; and filtering the identification result corresponding to the highest probability of the union as identification result of the dataset of the power equipment images and complete the identification of the power equipment. The present disclosure combines Mask R-CNN and probabilistic graphical model. The bottom layer uses Mask R-CNN, and the top layer uses Bayesian network to train in identifying power equipment images, so that a small amount of data samples can achieve good recognition, which improved the performance of Mask R-CNN model.

Abstract: The present invention provides a high-precision identification method and system for substations, including building a Mask RCNN objection recognition network model based on convolutional neural networks; inputting acquired image information of a object into the Mask RCNN object recognition network model for preliminary recognition and outputting a recognition result of the object; using an information entropy to create a semantic decision tree and correcting the recognition result of the object according to a principle of relative correlation between different objects and outputting a final recognition decision result; reading the recognition decision result to obtain a true type of the object to be recognized.

Abstract: A heterogeneous image registration method includes: performing edge detection on collected images, in combination with a curvature scale space strategy to extract contour curved segments in an edge image. Implementing a feature point detection strategy based on global and local curvature detecting feature points in the contour curved segments, and obtaining the nearest minimum local curvature of the feature points pointing to starting and end points of the contour, respectively. Calculating the number of neighborhood sampling points and neighborhood auxiliary feature points of neighborhoods on both edges of each of the feature points according to the nearest minimum local curvature. Using neighborhood auxiliary feature points and feature points to form a feature triangle, calculating an angle bisector vector and a main direction corresponding to the feature point in the feature triangle.

Abstract: The present disclosure provide a method for identifying power equipment targets based on human-level concept learning, including: creating a dataset of power equipment images, and annotating power equipment in power equipment images; training neural network and Bayesian network with the annotated dataset and respectively acquire identification results and conditional probabilities; calculating probabilities of unions with the conditional probabilities; and filtering the identification result corresponding to the highest probability of the union as identification result of the dataset of the power equipment images and complete the identification of the power equipment. The present disclosure combines Mask R-CNN and probabilistic graphical model. The bottom layer uses Mask R-CNN, and the top layer uses Bayesian network to train in identifying power equipment images, so that a small amount of data samples can achieve good recognition, which improved the performance of Mask R-CNN model.

Abstract: A battery cathode, a composition for a catalyst layer of a battery cathode, and a battery, each achieves excellent performance while using a non-platinum catalyst. The battery cathode includes a catalyst layer, wherein the catalyst layer contains a non-platinum catalyst, has a thickness of 15 ?m or more, and has a conductance per 1 cm2 of an electrode area of more than 100 S and less than 350 S.

Abstract: A battery cathode, a composition for a catalyst layer of a battery cathode, and a battery, each achieves excellent performance while using a non-platinum catalyst. The battery cathode includes a catalyst layer, wherein the catalyst layer contains a non-platinum catalyst, has a thickness of 15 ?m or more, and has a conductance per 1 cm2 of an electrode area of more than 100 S and less than 350 S.

Abstract: Embodiments of the present invention disclose a service transmission processing method, a node device and a network system are provided. One method includes: receiving service data after relay processing by a 3R relay node, where the relay processing includes terminating and regenerating an Optical Channel (OCh) of the service data, and when the OCh is terminated, transparent transmission is performed on an Optical channel Transport Unit (OTU); and performing defect detection on a path of the OTU to obtain a detection result of the path of the OTU. Another method includes: obtaining an overhead in an Optical Transport Network (OTN) frame; and judging whether the overhead includes a Client Signal Fail (CSF) inserted after a signal fails, and if the overhead includes the CSF, determining a path where a defect occurs according to the CSF.

Abstract: A charger device includes a switch, a voltage converter, a constant current circuit, and an automatic disconnecting circuit. The switch is connected to an alternating current (AC) power supply which triggers the charger device to work. The automatic disconnecting circuit is connected to the battery, the voltage converter and the constant current circuit automatically disconnect the voltage converter from the AC power supply when the battery is fully charged. The automatic disconnecting circuit comprises a first resistor, a voltage follower, a second resistor, a first zener diode, a variable resistor, a comparator, a third resistor, a first switch element, a diode and a relay. The relay comprises a coil and a normally-open switch connected between the AC power supply and voltage converter. The normally-open switch turns on or turns off to control a connection between the charger device and the AC power supply.

Abstract: A charger device includes a switch, a voltage converter, a constant current circuit, and an automatic disconnecting circuit. The switch is connected to an alternating current (AC) power supply which triggers the charger device to work. The automatic disconnecting circuit is connected to the battery, the voltage converter and the constant current circuit automatically disconnect the voltage converter from the AC power supply when the battery is fully charged. The automatic disconnecting circuit comprises a first resistor, a voltage follower, a second resistor, a first zener diode, a variable resistor, a comparator, a third resistor, a first switch element, a diode and a relay. The relay comprises a coil and a normally-open switch connected between the AC power supply and voltage converter. The normally-open switch turns on or turns off to control a connection between the charger device and the AC power supply.

Abstract: Embodiments of the present invention disclose a service transmission processing method, a node device and a network system are provided. One method includes: receiving service data after relay processing by a 3R relay node, where the relay processing includes terminating and regenerating an Optical Channel (OCh) of the service data, and when the OCh is terminated, transparent transmission is performed on an Optical channel Transport Unit (OTU); and performing defect detection on a path of the OTU to obtain a detection result of the path of the OTU. Another method includes: obtaining an overhead in an Optical Transport Network (OTN) frame; and judging whether the overhead includes a Client Signal Fail (CSF) inserted after a signal fails, and if the overhead includes the CSF, determining a path where a defect occurs according to the CSF.

Abstract: The invention provides a method for determining the prognosis of pulmonary sarcoidosis in an individual subject, comprising conducting gene expression analysis on a sample from the subject. The sample is obtained by bronchoscopy under procedural methods not requiring general anaesthesia.