Abnormal gait detection method based on human side gait video

Abstract

The invention discloses an abnormal gait detection method based on the side gait video of a person. The side gait video is collected by a common ordinary camera or a mobile phone, and the characteristics of a person's stride change and body forward are extracted from the video, and the normal The characteristic information of gait trains a single classification support vector machine model, which can quickly and effectively detect whether the corresponding gait is normal or abnormal. The invention does not need special detection equipment, does not need to perform gait detection in a specific place, and has high flexibility. The present invention considers the characteristics of body leaning forward when extracting gait features from gait videos, and can effectively prevent the detection ability of the abnormal gait detection model from being affected by abnormal training data, thereby improving the detection accuracy. The present invention only needs to use the characteristics of normal gait information to train a single-category support vector machine model, has few training samples, and can quickly and accurately detect normal / abnormal gait, thereby assisting doctors in the diagnosis of abnormal gait and improving the work efficiency of doctors.

Description

technical field [0001] The invention relates to the field of gait recognition, in particular to a method for extracting features from a human side gait video and combining an abnormal gait detection model to realize abnormal gait detection. Background technique [0002] Gait is the walking posture of a person, and abnormal gait is the abnormal walking posture that occurs when a person's body is abnormal. Common causes of abnormal gait include pain, central nervous system abnormalities, and musculoskeletal injuries. There are many types of abnormal gaits. Typical abnormal gaits include spastic hemiplegic gait, spastic paraplegic gait, sensory ataxia gait, panic gait, myopathic gait, cross-threshold gait, and hysterical gait. Wait. The appearance of some typical gaits reflects the existence of characteristic diseases. By observing and analyzing abnormal gaits, symptoms can be diagnosed in patients, such as panic gait and freezing gait common in patients with Parkinson's dise...

AI Technical Summary

Problems solved by technology

These methods are based on hardware equipment to analyze the patient's gait, which requires high equipment and needs to be carried out in a specific place, with low flexibility, which is not conducive to the detection of abnormal gait in daily life

Individual studies (such as the invention patent "abnormal gait detection method and abnormal gait detection system" with the application number of 2017107435559) classify normal abnormalities by extracting features from human body contours, but only consider the characteristics of changes in the stride of the lower body, and do not consider some Abnormal gaits, such as the characteristics of the upper body leaning forward in the panic gait, and the training model used are easily affected by the abnormal gait data in the training data, and cannot effectively detect a variety of abnormal gaits

Images