Model-Based Feature Extraction for Gait Analysis and Recognition

Abstract

Abstract. Human motion analysis has received a great attention from researchers in the last decade due to its potential use in different applications. We propose a new approach to extract human joints (vertex positions) using a model-based method. Motion templates describing the motion of the joints as derived by gait analysis, are parametrized using the elliptic Fourier descriptors. The heel strike data is exploited to reduce the dimensionality of the parametric models. People walk normal to the viewing plane, as major gait information is available in a sagittal view. The ankle, knee and hip joints are successfully extracted with high accuracy for indoor and outdoor data. In this way, we have established a baseline analysis which can be deployed in recognition, marker-less analysis and other areas. The experimental results confirmed the robustness of the proposed method to recognize walking subjects with a correct classification rate of %92.

Heel strike detection based on human walking movement for surveillance analysis

“…During the strike phase, the foot of the striking leg stays at the same position for nearly half a gait cycle (when the foot is in contact with the floor), whilst the rest of the human body moves forward (Bouchrika and Nixon, 2007). Also, when the left and right feet cross, the head is at its highest position.…”

“…They solved for self-occlusion of the feet by using optical flow and motion correspondence. Bouchrika and Nixon (2007) built an accumulator map of all corner points using the Harris corner detector during an image sequence. Then, the heel strike position was estimated using the density of proximity of the corner points.…”

Covariate Analysis for View-Point Independent Gait Recognition

“…To extract the gait features of walking subjects from the covariate dataset, we applied the model-based method described in [6] to automate the extraction process of the joint trajectories. To extract candidate joint positions, the Distance Transform is performed on the silhouettes of walking subjects.…”

Gait recognition method for arbitrary straight walking paths using appearance conversion machine

“…Several methods have been proposed for gait recognition from various different perspectives [1,5,15,[18][19][20]23].…”