The main contents of the project include the identification of objective answer cards and the output of results, the identification of marking marks of subjective questions and the output of results, and the statistics and management of examination data. The automatic evaluation of objective questions is realized by computer vision method, and the score recognition of subjective questions is realized based on faster RCNN.
The main contents of the project include: worker identity information management, attendance records, etc; Vehicle management, license plate recognition, vehicle type classification, etc; Personnel monitoring, operation environment monitoring, etc. Key technologies such as edge detection, image classification / segmentation and scene semantic recognition are adopted.
The main contents and difficulties of the project are sand dredger recognition and sand digging behavior recognition of river personnel along the way. Based on the understanding of key technologies such as target object segmentation technology in image / video, moving target tracking technology in video, human posture detection and scene semantics, the behavior monitoring of sand dredger and river monitoring are realized.
The main contents of the project include real-time banknote image acquisition, image detection and processing, and classification of old and new banknotes. The key technologies such as image detection and processing, feature points and gray gradient co-occurrence matrix are adopted, and the classification of old and new banknotes is realized based on DAG-SVM multi classifier.
Copyright © 2019 BUAA Mobile and Social Computing Research Group