Gait Recognition Using Pose Estimation and Signal Processing

Lima, Vitor C. de; Schwartz, William Robson

doi:10.1007/978-3-030-33904-3_68

Cited by 8 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One can also observe that our method, with the chi-square distance function, was superior to the method by Wang et al [8] and was competitive with the state-of-the-art methods proposed by Liu at al. [11] and De lima and Schwartz [12].…”

Section: Resultsmentioning

confidence: 99%

“…It is possible to notice that, again, the chi-square distance function showed better results than Euclidean distance function. Yu et al [9] 83.50% Chen et al [10] 91.10% De Lima and Schwartz [12] 98.00%…”

Section: Resultsmentioning

confidence: 99%

“…Chisquare function obtained a better result. Table I shows the rank-1 accuracy values obtained by three methods presented in Section II ( [4], [11], [12]), including two recent methods that can be considered state-of-the-art ( [11] and [12]), and also by our method (using both distance functions) for each position of the camera in the CASIA Gait Dataset-A. One can observe that all methods showed better results when the person is in the front position to the camera.…”

Section: Resultsmentioning

confidence: 99%

“…In De Lima and Schwartz [12], a model-based approach is used to extract the position of the subject's joints from each video frame utilizing a pose estimation algorithm. Then, this information is transformed into signals and movement histograms to be used as feature descriptors and the subject is classified using a 1-NN classifier, with Euclidean distance.…”

Section: Related Workmentioning

confidence: 99%

“…The main hypothesis of our work is based on the results obtained by the works presented in Section II, mainly in [12], which shows that with the information of how the body members behave during the gait cycle, it is possible to determine a gait signature based on the angular variation of each limb part and this signature would keep sufficient spatiotemporal information about the gait for performing biometric identification.…”

Section: Gait Recognitionmentioning

confidence: 99%

See 4 more Smart Citations

A New Method for Gait Recognition Using 2D Poses

Jangua¹,

Marana²

2020

Anais Do XVI Workshop De Visão Computacional (WVC 2020)

View full text Add to dashboard Cite

Over the last decades, biometrics has become an important way for human identification in many areas, since it can avoid frauds and increase the security of individuals in society. Nowadays, most popular biometric systems are based on fingerprint and face features. Despite the great development observed in Biometrics, an important challenge lasts, which is the automatic people identification in low-resolution videos captured in unconstrained scenarios, at a distance, in a covert and noninvasive way, with little or none subject cooperation. In these cases, gait biometrics can be the only choice. The goal of this work is to propose a new method for gait recognition using information extracted from 2D poses estimated over video sequences. For 2D pose estimation, our method uses OpenPose, an open-source robust pose estimator, capable of real-time multi-person detection and pose estimation with high accuracy and a good computational performance. In order to assess the new proposed method, we used two public gait datasets, CASIA Gait Dataset-A and CASIA Gait Dataset-B. Both datasets have videos of a number of people walking in different directions and conditions. In our new method, the classification is carried out by a 1-NN classifier. The best results were obtained by using the chi-square distance function, which obtained 95.00% of rank-1 recognition rate on CASIA Gait Dataset-A and 94.22% of rank-1 recognition rate on CASIA Gait Dataset-B, which are comparable to state-of-the-art results.

show abstract

Section: Resultsmentioning

confidence: 99%