Multi-layer Perceptron Architecture for Kinect-Based Gait Recognition

Bari, A. S. M. Hossain; Gavrilova, Marina L.

doi:10.1007/978-3-030-22514-8_31

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al [38] proposed a characteristics representation method by gathering the local normal vectors of hypersurface in the depth sequence to form a Polynormal combining the local shape and motion information of human body. Bari et al [39] designed a neural network framework for gait recognition and optimized the traditional machine learning model so that the accuracy rate of gait recognition reached 93.73%. Ali et al [10] proposed an action recognition framework based on Kinect to detect human skeleton joints.…”

Section: Posture Recognitionmentioning

confidence: 99%

“…Although Kinect interaction and posture recognition were studied in the above literatures, some focused on the posture recognition of partial human body [23], [33]- [35], [38], [39], and some did not consider the human body structures [1], [21], [30], [34]- [36], [40]. Moreover, some models were complicated or required an amount of computation [9], [31], [33], [34].…”

Section: Posture Recognitionmentioning

confidence: 99%

“…Moreover, some models were complicated or required an amount of computation [9], [31], [33], [34]. And what's more, most did not explore the posture characteristics from static and dynamic perspectives [1], [9], [10], [21]- [23], [25], [30], [31], [33]- [36], [39]- [41]. In order to reduce the complexity of posture recognition, the skeleton model was simplified, and characteristic consistent distance values were generated for the static and dynamic posture recognitions.…”

Section: Posture Recognitionmentioning

confidence: 99%

“…The DMM-l2regularized method [36] might implement unreliably due to large intra-class changes. The MLP-RMSProp-tanh [39] and the Deterministic Learning [1] methods were only applied in dynamic gait recognition, and static postures and systemic postures were not examined. When SVM algorithm [40] was used in posture recognition, the meaningless transition between two sign language postures often reduced recognition accuracy.…”

Section: Comparisons To Other Literatures and Significancementioning

confidence: 99%

See 3 more Smart Citations

Posture Recognition Technology Based on Kinect

Chu

Xin

2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Aiming at the complexity of posture recognition with Kinect, a method of posture recognition using distance characteristics is proposed. Firstly, depth image data was collected by Kinect, and threedimensional coordinate information of 20 skeleton joints was obtained. Secondly, according to the contribution of joints to posture expression, 60 dimensional Kinect skeleton joint data was transformed into a vector of 24-dimensional distance characteristics which were normalized according to the human body structure. Thirdly, a static posture recognition method of the shortest distance and a dynamic posture recognition method of the minimum accumulative distance with dynamic time warping (DTW) were proposed. The experimental results showed that the recognition rates of static postures, non-cross-subject dynamic postures and cross-subject dynamic postures were 95.9%, 93.6% and 89.8% respectively. Finally, posture selection, Kinect placement, and comparisons with literatures were discussed, which provides a reference for Kinect based posture recognition technology and interaction design.

show abstract

Section: Posture Recognitionmentioning

confidence: 99%

Section: Posture Recognitionmentioning

confidence: 99%

Section: Posture Recognitionmentioning

confidence: 99%

Section: Comparisons To Other Literatures and Significancementioning

confidence: 99%

See 2 more Smart Citations

Posture Recognition Technology Based on Kinect

Chu

Xin

2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

Gait Recognition for 2-Second Walks Using Viewpoint Normalization and SlidingWindow Process

2023

View full text Add to dashboard Cite

Many events, such as robberies, missing people, and other suspicious activities, are often captured by cameras. However, these videos are, more often than not, short and not from an optimal angle. Biometric recognition techniques such as facial or iris recognition are inadequate for situations like this. Gait recognition techniques are more suitable than other types of biometrics in such situations. In this work, we propose a new gait recognition technique using viewpoint normalization and a sliding window process. The proposed technique is designed to handle short walking videos captured from any angle. The proposed technique consists of 3 steps. First, a 2-second walk is preprocessed using the sliding window process. This step allows us to generate more gait data in a form of a set of sliding windows from only a 2second walk. Then sliding windows are transformed into the optimal viewpoint using ViewNet, a proposed neural network designed for finding and transforming sliding windows into the optimal viewpoint angle. Finally, local joint movement information is extracted from sliding windows and used to identify a person using IdenNet, a proposed neural network designed for identifying a person from local joint movements. Four evaluation methods, the top k accuracy test, the precision-recall curves, the cumulative matching characteristic curves, and the gallery-size test, are used to assess the proposed technique. The experimental results show that the proposed technique outperforms existing techniques on all four tests. In particular, the proposed technique can provide a small group, not more than 5, of suspects with a chance above 90% that the real person of interest is in the group. Moreover, the proposed technique still maintains high accuracy even when used with a larger pool of people.

show abstract