STDF (standard test data format) feature based human behavior recognition algorithm

Abstract

The invention discloses an STDF (standard test data format) feature based human behavior recognition algorithm. The algorithm includes: according to a concept that strenuous exercise areas provide more discrimination information in behavior recognition, determining human exercise salient areas by means of depth information of video images, calculating optical flow features in areas to obtain an energy function for measuring area activeness, subjecting the exercise salient areas to Gaussian sampling according to the energy function to enable sample points to distribute in the exercise salient areas, taking the acquired sample points as action low-level features to describe human behaviors, and adopting an SVM (support vector machine) classifier for recognition of the behaviors by the aid of a BoW bag-of-word model. According to experimental data, average behavior recognition accuracy rate of the STDF feature based human behavior recognition algorithm reaches 92% in SwustDepth datasets.

Description

technical field [0001] The invention relates to the technical field of video processing, in particular to a human behavior recognition algorithm based on STDF features. Background technique [0002] Behavior recognition based on video images has a wide range of applications in intelligent video surveillance, video retrieval, human-computer interaction and smart home. The main task of behavior recognition is to use a computer to analyze image sequences containing pedestrians to identify human actions. Behavior recognition based on computer vision mainly includes two steps of behavior feature extraction and behavior classification. At present, the features used in behavior recognition algorithms mainly include global features and local features. [0003] In video images, there are not only connections in the space of a single image, but also interrelationships between frames. Therefore, in various specialties, the characteristics of spatiotemporal volume have attracted exte...

AI Technical Summary

Problems solved by technology

Therefore, it is necessary to calculate the pixel points one by one when extracting spatio-temporal features. The calculation of feature extraction is relatively large, and the extracted interest points are relatively sparse. Using spatio-temporal interest points as features is not very descriptive.

On the contrary, dense sampling can extract a large number of sample points, but the number of sample points obtained by dense sampling is huge, the performance of behavior is not strong, and it introduces unnecessary background information for behavior recognition

In complex scenes, the recognition efficiency of dense sampling is low and the effect is not good

Images