Autors: Salim Al-Ali., Milanova Mariofanna., Manolova, A. H., Fox Victoria.
Title: Human action recognition using combined contour-based and silhouette-based features and employing KNN or SVM classifier
Keywords: —Contour-based, human action recognition, video recognition, silhouette-based

Abstract: This paper presents a new algorithm for human action recognition in videos. This algorithm is based on a combination of two different feature types extracted from Aligned Motion Images (AMIs). The AMI is a method for capturing the motion of all frames in a human action video in one image. The first feature is a contour based type and is employed to grasp boundary details of the AMI. It relies on the 1st and 2nd discrete time differential of the chord distance signature feature, so it is called Derivatives of Chord Distance Signature. The second feature is a silhouette-based type that is used to capture regional appearance details. It catches most of the visual components for the AMI using a Histogram of Oriented Gradients feature. Oriented Gradients (HOG) feature. Combining both features creates a complementary feature vector that makes it possible to obtain an optimal correct recognition rate of 100%. For the classification, the algorithm is utilized two different classifiers: K



    INTERNATIONAL JOURNAL OF COMPUTERS, vol. 9, pp. 37-47, 2015, United States, NAUN, ISSN 1998-4308

    Copyright NAUN

    Цитирания (Citation/s):
    1. Arora, Ishita, and M. Gangadharappa. "A Survey of Motion Detection in Image Sequences." In 2019 6th International Conference on Computing for Sustainable Global Development (INDIACom), pp. 215-223. IEEE - 2019 - в издания, индексирани в Scopus или Web of Science
    2. Yao, Xin, Xiaoran Shi, and Feng Zhou. "Complex-Value Convolutional Neural Network for Classification of Human Activities." In 2019 6th Asia-Pacific Conference on Synthetic Aperture Radar (APSAR), pp. 1-6. IEEE - 2019 - в издания, индексирани в Scopus или Web of Science
    3. Yao, X., Shi, X., & Zhou, F. (2020). Human activities classification based on complex-value convolutional neural network. IEEE Sensors Journal, 20(13), 7169-7180. - 2020 - в издания, индексирани в Scopus или Web of Science

    Вид: статия в списание, публикация в реферирано издание, индексирана в Google Scholar