Video scene segmentation judgment method, intelligent terminal and storage medium

• Main Authors: CHEN MINGLIANG, WU JIAFEI, LAI CHANGMING, YANG FUJUN, XU YONGZE
• Format: Patent
• Language: Chinese; English
• Published: 05.07.2019
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a video scene segmentation judgment method, an intelligent terminal and a storage medium. The video scene segmentation judgment comprises the following steps: carrying out feature extraction on two images from multiple dimensions by adopting a deep learning network; performing cascading and splicing on the extracted features to form a depth cascading feature vector with a fixed length; and judging the similarity of the depth cascading feature vectors, and judging whether video scene segmentation judgment occurs or not according to a similarity result. According to the invention, an effective video switching detection algorithm and a cascading feature extraction model are used; a deep learning network is adopted to carry out feature extraction on images from different dimensions, finally, the features are cascaded to form a deep cascading feature vector with a fixed length, the similarity of the feature vector is measured to judge whether video segmentation is carried out or not, and wh