A Novel Skeleton-Based Human Activity Discovery Using Particle Swarm Optimization with Gaussian Mutation

Abstract

Human activity discovery aims to distinguish the activities performed by humans, without any prior information of what defines each activity. Most methods presented in human activity recognition are supervised, where there are labeled inputs to train the system. In reality, it is difficult to label data because of its huge volume and the variety of activities performed by humans. In this paper, a novel unsupervised approach is proposed to perform human activity discovery in 3D skeleton sequences. First, important frames are selected based on kinetic energy. Next, the displacement of joints, set of statistical, angles, and orientation features are extracted to represent the activities information. Since not all extracted features have useful information, the dimension of features is reduced using PCA. Most human activity discovery proposed are not fully unsupervised. They use pre-segmented videos before categorizing activities. To deal with this, we used the fragmented sliding time window method to segment the time series of activities with some overlapping. Then, activities are discovered by a novel hybrid particle swarm optimization with a Gaussian mutation algorithm to avoid getting stuck in the local optimum. Finally, k-means is applied to the outcome centroids to overcome the slow rate of PSO. Experiments on three datasets have been presented and the results show the proposed method has superior perfor- * Corresponding author.

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

“…3 Use the roulette wheel selection method to choose a cluster as c * Recalculate the number of cluster by k = k − 1 effectiveness, we compared the proposed method with nonautomatic methods (having prior knowledge of the number of clusters) including KM (k-means), SC (spectral clustering), ENSC (elastic net subspace clustering), SSC (Sparse Subspace Clustering) [35] and GMM (Gaussian mixture model) and automatic methods including DBSCAN, MS (Mean-shift clustering), PSO [51], HPGMK [8], and MOPGMGT [36].…”

“…Even though this approach has achieved promising results, their approach cannot handle complex scenarios because their inputs were of well-segmented videos, and they required prior knowledge about the number of performed activities. Hadikhani et al [8] presented a clustering method based on PSO that received unsegmented frames as inputs and clustered them. They presented feature extraction from informative skeleton joints by combining different techniques.…”

“…For this reason, the kinetic energy of each frame is calculated based on the joints using Eq. ( 1) based on [8]. The movement of joint j in frame i and i-1 is calculated.…”

“…2: The proposed system is depicted in this diagram. Pre-processing based on [8] are performed, which includes choosing keyframes, extracting features from informative joints, dimension reduction, and segmentation of frames into fixed-length time overlapping windows before clustering the activities. In the clustering phase, the number of clusters starts from k max and continues until it reaches k min .…”

“…Feature extraction methods can be divided into 3 categories namely displacement, statistical, and orientation. In this paper, a combination of all approaches presented in [8] is used to describe the human body's shape and movement. Human activity discovery (HAD) is one of the crucial tasks in a HAR system.…”