Gait Recognition

Abstract

Gait recognition has received increasing attention as a remote biometric identification technology, i.e. it can achieve identification at the long distance that few other identification technologies can work. It shows enormous potential to apply in the field of criminal investigation, medical treatment, identity recognition, human-computer interaction and so on. In this chapter, we introduce the state-of-the-art gait recognition techniques, which include 3D-based and 2D-based methods, in the first part. And considering the advantages of 3D-based methods, their related datasets are introduced as well as our gait database with both 2D silhouette images and 3D joints information in the second part. Given our gait dataset, a human walking model and the corresponding static and dynamic feature extraction are presented, which are verified to be view-invariant, in the third part. And some gait-based applications are introduced.

Application of data recognition system based on artificial intelligence algorithm

“…In this paper, the system uses the DirectShow function of OpenCV to provide high quality data acquisition function, which can facilitate users to store the image information obtained by the device in the file, and provide effective preparation for subsequent processing. The DirectShow system structure is shown in Figure 2 below: [8] Figure 2 DirectShow system structure diagram Secondly, image processing. In this paper, two kinds of image processing algorithms and decoding methods are proposed, one is genetic algorithm, the other is the improved BP neural network algorithm, both of which can effectively process the collected QR code image.…”

Modern methods of human identification using gait characteristics

“…In the model-based approach, the extracted characteristics predominantly include the distance and angles of individual points on the human body. (Sun, Wang, & Li, 2017).…”

“…Figure 5: Input data processing using a model-free approach a) gait energy image; b) motion silhouette image; c) shape variation-based image; d) gait entropy image; e) compressed silhouettes image; (Sun et al, 2017) During the extraction and presentation of the characteristics of human gait, different algorithms were used for the processing of individual characteristics (Table 2). (Wan et al, 2018).…”

“…Figure 4: Input data processing using the model-based approach a) joint model; b) static human parameters; c) stick model; d) volumetric model; e) static and dynamic characteristics(Sun, Wang, & Li, 2017).…”

3D Gait Recognition based on Functional PCA on Kendall's Shape Space

“…Over the past few years, several 2D methods have been proposed making use of the body either by establishing a prior body model [1] or by using the overall shape of silhouette attributes [2], [3]. However, the use of video data make the problems of self-occlusion, pose variations, illumination and appearance changes difficult to handle in addition to the important task of background subtraction [4]. In order to overcome these limitations, a new modality is emerging -3D skeletal data.…”