Human Gait recognition is emerging as a supportive biometric technique in recent years that identifies the people through the way they walk. The gait recognition in model free approaches faces the challenges like spee...Human Gait recognition is emerging as a supportive biometric technique in recent years that identifies the people through the way they walk. The gait recognition in model free approaches faces the challenges like speed variation, cloth variation, illumination changes and view angle variations which result in the reduced recognition rate. The proposed algorithm selected the exhaustive angles from head to toe of a person, and also height and width of the same subject. The experiments were conducted using silhouettes with view angle variation, and cloth variation. The recognition rate is improved to the extent of 91% using Support vector machine classifier. The proposed method is evaluated using CASIA Gait Dataset B (The institute of Automation, ChineseAcademy of Sciences), China. Experimental results demonstrate that the proposed technique shows promising results using state of the art classifiers.展开更多
Video shot boundary detection is the primary task for content based video management and retrieval system. This paper proposes a shot boundary detection strategy by exploiting the pros of Normalized Periodogram for ef...Video shot boundary detection is the primary task for content based video management and retrieval system. This paper proposes a shot boundary detection strategy by exploiting the pros of Normalized Periodogram for efficiently representing the content of the video. A Normalized Periodogram based distance metric to detect the key frames using shot boundary, namely Distance- Left-Right (D<sub>LR</sub>), is addressed, which is computed on a sliding sub-window basis. The D<sub>LR</sub> sequence is used to detect the suspected shot boundary frames and a transition type detection procedure is adapted to these suspected frames for discriminating the abrupt and gradual transitions. The proposed shot boundary detection methodology yields Precision—95.02%, Recall—93.15% and F1 score—94.07% for cut, Precision—86.57%, Recall—86.67% and F1 score—86.61% for gradual, Precision—90.6%, Recall—90.02% and F1 score—90.3% for overall transitions. Experimental results show that the proposed approach is superior to the recently available shot boundary detection techniques because of its robustness and simplicity, and presents an effective distance metric to detect the shot boundary.展开更多
文摘Human Gait recognition is emerging as a supportive biometric technique in recent years that identifies the people through the way they walk. The gait recognition in model free approaches faces the challenges like speed variation, cloth variation, illumination changes and view angle variations which result in the reduced recognition rate. The proposed algorithm selected the exhaustive angles from head to toe of a person, and also height and width of the same subject. The experiments were conducted using silhouettes with view angle variation, and cloth variation. The recognition rate is improved to the extent of 91% using Support vector machine classifier. The proposed method is evaluated using CASIA Gait Dataset B (The institute of Automation, ChineseAcademy of Sciences), China. Experimental results demonstrate that the proposed technique shows promising results using state of the art classifiers.
文摘Video shot boundary detection is the primary task for content based video management and retrieval system. This paper proposes a shot boundary detection strategy by exploiting the pros of Normalized Periodogram for efficiently representing the content of the video. A Normalized Periodogram based distance metric to detect the key frames using shot boundary, namely Distance- Left-Right (D<sub>LR</sub>), is addressed, which is computed on a sliding sub-window basis. The D<sub>LR</sub> sequence is used to detect the suspected shot boundary frames and a transition type detection procedure is adapted to these suspected frames for discriminating the abrupt and gradual transitions. The proposed shot boundary detection methodology yields Precision—95.02%, Recall—93.15% and F1 score—94.07% for cut, Precision—86.57%, Recall—86.67% and F1 score—86.61% for gradual, Precision—90.6%, Recall—90.02% and F1 score—90.3% for overall transitions. Experimental results show that the proposed approach is superior to the recently available shot boundary detection techniques because of its robustness and simplicity, and presents an effective distance metric to detect the shot boundary.
