Classification of Multi-class Daily Human Motion using Discriminative Body Parts and Sentence Descriptions

Abstract

In this paper, we propose a motion model that focuses on the discriminative parts of the human body related to target motions to classify human motions into specific categories, and apply this model to multi-class daily motion classifications. We extend this model to a motion recognition system which generates multiple sentences associated with human motions. The motion model is evaluated with the following four datasets acquired by a Kinect sensor or multiple infrared cameras in a motion capture studio: UCFkinect; UT-kinect; HDM05-mocap; and YNL-mocap. We also evaluate the sentences generated from the dataset of motion and language pairs. The experimental results indicate that the motion model improves classification accuracy and our approach is better than other state-of-the-art methods for specific datasets, including human-object interactions with variations in the duration of motions, such as daily human motions. We achieve a classification rate of 81.1% for multi-class daily motion classifications in a non cross-subject setting. Additionally, the sentences generated by the motion recognition system are semantically and syntactically appropriate for the description of the target motion, which may lead to human-robot interaction using natural language.

Searching 3d Motion Patterns of Vietnamese Traditional Dances

“…Feature extraction of the 3D motion data affects an algorithm's performance significantly. In 2017, Yusuke Goutsu, Wataru Takano and Yoshihiko Nakamura found two matters with 3D motion features [16]. Firstly, local features, which got from some parts of the body, would give better results than global features, which collected the whole body.…”

Disassembling Object Representations without Labels

“…For the Fuzzy Classification, there is no directly related work so far to our knowledge. The most similar methods are some multi-label classification works [16,26,32,33], which transform the multi-label classification into multiple single label classification tasks. However, those methods are all supervised by annotated labels, where the unsupervised fuzzy classification problem does not exist.…”

Automatic body part identification in real‐world clinical dermatological images using machine learning

“…While some algorithms have been developed to segment human body parts in still images and video, to the best of our knowledge no data on algorithms classifying real‐world dermatological images based on specific body parts have been published to date. For example, algorithms have been developed to detect body parts when entire people are depicted, either in still photos or videos 15–17 . These algorithms, however, do not consider the high zoom levels and skin pathologies in dermatological clinical images and therefore are unsuited for classifying dermatological clinical pictures.…”

“…For example, algorithms have been developed to detect body parts when entire people are depicted, either in still photos or videos. [15][16][17] These algorithms, however, do not consider the high zoom levels and skin pathologies in dermatological clinical images and therefore are unsuited for classifying dermatological clinical pictures.…”