Evaluating the effect of viewing angle in different conditions for gait recognition
Gait recognition has gained interest of researchers as it performs identification of subjects at a distance from the camera. However, due to the changes in the viewing angles, it gets cumbersome for a system to perform recognition based on the walking pattern of an individual. In this work, the aim...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Asian Research Publishing Network
2017
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/58369/ http://irep.iium.edu.my/58369/ http://irep.iium.edu.my/58369/1/jeas_0817_6267_Makhdoomi2017_Evaluating%20the%20effect%20of%20viewing%20angle%20in%20different%20conditions%20for%20gait%20recognition.pdf http://irep.iium.edu.my/58369/7/Evaluating%20the%20effect%20of%20viewing%20angle%20in%20different%20conditions%20for%20gaitrecognition.pdf |
| Summary: | Gait recognition has gained interest of researchers as it performs identification of subjects at a distance from the camera. However, due to the changes in the viewing angles, it gets cumbersome for a system to perform recognition based on the walking pattern of an individual. In this work, the aim is to present a baseline method for the purpose of human recognition based on the shape of its body and walking pattern when the subject is observed from different viewing angles. The recognition is also tested on the subject in two different scenarios, apart from being observed at different viewing angles. Gait periodicity is estimated after extracting the silhouettes of an individual, followed by obtaining the total silhouette representation of an individual using Matlab. The total silhouette representations obtained from the probe gait data are compared to the gallery gait data representations for the purpose of similarity computation by calculating the RMS value between the said representations. Higher the value, lesser is the similarity & vice versa. The experiments are conducted on the CASIA gait dataset and obtained the gait recognition rate ranging from 23% to 69% in different scenarios. The results show that the proposed method outperforms the other existing methods & puts a decent fight to the base algorithm. |
|---|