A Fast Statistical Approach for Human Activity Recognition

Abstract

An essential part of any activity recognition system claiming be truly real-time is the ability to perform feature extraction in real-time. We present, in this paper, a quite simple and computationally tractable approach for real-time human activity recognition that is based on simple statistical features. These features are simple and relatively small, accordingly they are easy and fast to be calculated, and further form a relatively low-dimensional feature space in which classification can be carried out robustly. On the Weizmann publicly benchmark dataset, promising results (i.e. 97.8%) have been achieved, showing the effectiveness of the proposed approach compared to the-state-of-the-art. Furthermore, the approach is quite fast and thus can provide timing guarantees to real-time applications

Human action recognition in compressed domain using PBL-McRBFN approach

“…Pixel domain approaches [8], [9], [10], [11], [12], [13], [14] offer better classification at the cost of higher computational complexity and hence very few have achieved real-time recognition. Sadek et al [15] uses a finite set of features directly derived from difference frames of the action snippet for activity recognition which works at 18fps. Yu et al [16] presented action recognition using semantic texton forests which work on video pixels generating visual codewords.…”

2D Information Space Based Action Recognition

“…Samy et al [1] generates a sequence of difference images from successive frames of a video sequence. Features such as centroid, mean absolute deviation from the center of motion and intensity of motion are extracted from difference image resulting a set of features.…”

A two-layer framework for activity recognition with multi-factor activity pheromone matrix

“…Majority papers in ADLs based on sensor data show that traditional processing methods usually calculate the statistic distribution value. Feature vectors are constructed by some statistical numeric values, such as sensor-triggered count by space or time zone [3,4]. This model could have an effectively recognition, but simple construction of feature vector makes some identifiable information lost from the activity ontology.…”