Video event detection method of continuous learning

Abstract

The invention provides a video event detection method of continuous learning. The detection method comprises an initial learning stage and an incremental learning stage, wherein in the initial learning stage, video data with a tag is prepared, sparse self coding is used for learning the video data with the tag, and a priori model is trained; in the incremental learning stage, the priori model which is trained is used for classifying new video data, a probability score and a gradient distance are calculated, and automatic tag adding or manual tag adding is selected for the new video data by active learning according to a calculation result. The video event detection method is combined with deep learning and the active learning to automatically select the most proper characteristics and utilize video streaming data to gradually improve a traditional model; when the new video data is obtained, unsupervised learning is used for extracting characteristics, then, the active learning is used for reducing the work of manual classification as much as possible, the model is perfected gradually, and finally, a purpose of continuous learning is achieved.

Description

technical field [0001] The invention relates to various fields of computer vision, pattern recognition and machine learning, in particular to a continuous learning video event detection method. Background technique [0002] Most of the existing video event detection systems manually extract the features in the video, such as motion features such as gradient histogram (HOG) and optical flow histogram (HOF). These artificially selected features cannot be applied to all fields or Scenarios require different trade-offs based on different applications. And deep learning is an effective way to solve this problem. [0003] Some studies also try to use deep learning methods, such as C3D, but they all use a large amount of labeled data to train a fixed model. This model cannot be changed during use, which makes it unable to adapt to complex environments. changes, and cannot accurately identify all untrained event categories in the video, which is very inapplicable for constantly ch...

AI Technical Summary

Problems solved by technology

[0004] The amount of video data is very large, and processing requires a large amount of computing resources. Direct processing of video data will cause high delay or even congestion. Therefore, a reasonable encoding method is required to express video motion

Images