The Gait Analysis Of Paralytic Based On Video Sequences

In recent years, it is one of the most important research subjects that using the video and image processing to analysis the field of computer image processing, it has a very broad application prospect. It can be widely used in clinical diagnoses, rehabilitation engineering, ergonomics, gymnastic, science, bionic system control and manufacturing and so on. In the clinical field, it is very useful in the diagnosing and healing of the disabled people by analyzing their kinetic information. A human gait analysis system for paralytics based on video sequences is designed in this paper. The process of kinetic analysis includes the followings.Fistly, sagittal human walking video image sequences should be obtained; secondly the proper algorithm is adopted for the orientation of human lower limb joint points; thirdly, joint angles can be calculated using of the two dimensional coordinates of human lower limb joint points which are in the image sequences.The orientation of human lower limb joint points plays an important role in gait analysis; it is a very important research work of how to extract characteristics associated with human body structure and the completion of gait analysis. There is not any marker in the algorithm which is proposed in this paper. The algorithm is based on the geometry properties of walking human. The image sequence is acquired by a single camera firstly, and the human region is extracted from the image by the background subtraction. After the human region and height are obtained, we can further complete the lower limb joints detection of walking human. For this algorithm any markers are not needed to paste on the lower limbs joint angles, and also the shelter problem of marks are not existed. The joint points of video sequences are labeled automatically while the transform curve of human lower limb joint angles are shown at the same timeThe experimental results indicate that the proposed algorithm has a good precision orientation, an easy performance and a real-time detection and it can also extract the human lower limb angles accurately. The parameters extracted can help doctors to do the gait analysis quantificationally , which can correct its abnormal gait and the ability of walking can be raised.