The invention relates to a UAV (unmanned aerial vehicle) power inspection image key power component automatic diagnosing and marking system which comprises a power component target detection module, apower component fault detection module, a human-computer interaction module providing a human-computer interaction function, a marking module and a UAV power inspection image library. According to the system, the intelligent automatic diagnosing and marking of a UAV power inspection image is achieved, the workload of the inspection personnel is reduced, the inspection efficiency and the accuracyrate are improved, and a data support is provided for the application of artificial intelligence in the field of power inspection key power component identification and fault detection. At the same time, the standardization of power inspection image storage and marking is promoted.

UAV power inspection image key power component automatic diagnosing and marking system

The present disclosure relates to a video classification method and apparatus. The method comprises: acquiring a key frame, comprising a human face, in a video; acquiring a human face feature in the key frame; acquiring a human face feature corresponding to a picture type; according to the human face feature in the key frame and the human face feature corresponding to the picture type, determining a picture type to which the video belongs; and distributing the video to the picture type to which the video belongs. The technical solution can intelligently and automatically classify a video into a picture type corresponding to a person participating in the video, so that user manual classification is not needed and the classification accuracy is high.

Video classification method and apparatus

The invention relates to a drone aerial photo library building, classifying and retrieving method suitable for power inspection. A drone aerial photo library includes three sub-databases, namely a video database, a photo database and an imperfect photo database; the video database is used for storing videos and flight data which are collected by a drone during power inspection aerial photography,the photo database is used for storing aerial photos with qualified quality evaluation results and label files of photo annotation information, and the imperfect photo database is used for storing aerial photos with unqualified quality evaluation results. By the adoption of the drone aerial photo library building, classifying and retrieving method, the photo library is built, and the collected drone power inspection aerial photos are classified, screened, annotated and managed. According to the built drone aerial photo library suitable for the power inspection, through a regularized naming andmultiple classification method, data contents are scientifically managed; the contents of the photos qualified in quality are classified according to power parts, fault states are annotated, and therefore reliable data support is provided for application researches of artificial intelligence in the field of the power inspection.

Drone aerial photo library building, classifying and retrieving method suitable for power inspection

A video may be categorized into a picture category or a video category A key frame of the video includes a face and a face feature in the key frame is obtained Face features respectively associated with a plurality of picture categories are acquired and the video is assigned to one of the picture categories based on a comparison of the key frame face feature and the face features of the picture categories Videos may first be associated with a video category by comparing key frame face features from the videos, and then the video category may be assigned to a picture category based on comparison of a video category face feature with a plurality of picture category face features Alternatively, a video may be assigned to a picture category based on matching capture times and capture locations between the video and a reference picture in the picture category

Video categorization method and apparatus, and storage medium

The invention discloses a data synchronization method of a PC (Personnel Computer) end and a mobile terminal based on hydraulic polling business. The data synchronization method mainly comprises two parts of uploading polling data at the mobile terminal and downloading the polling data at the PC end, wherein uploading the polling data at the mobile terminal comprises the following steps of importing polling attribute basic information and multimedia data information in mobile equipment into the PC end, converting the basic data information into data objects through sorting operation of the polling data, storing the data objects in a database and storing multimedia data in a multimedia database to effectively manage the polling data; downloading the polling data at the PC end comprises the following steps of downloading newest hydraulic polling data to the mobile terminal from the PC end to facilitate obtaining result information of last polling when a user carries out polling at each time, and comparing with the current polling site condition to judge the hydraulic safety situation. According to the data synchronization method, the polling data can be automatically, timely and accurately put in storage conveniently, the processing time for the polling data is reduced, and the working efficiency and the accuracy for polling personnel can be improved.

Lyu Xing

Papers

Data synchronization method of PC (Personnel Computer) end and mobile terminal based on hydraulic polling business