An infant abnormal behavior detection method based on meanshift algorithm and svm

Abstract

The present invention adopts a method for detecting abnormal behavior of infants based on meanshift algorithm and SVM, firstly, the acquired infant video is preprocessed, and then the meanshift algorithm is used to track the target motion trajectory of the infant's limbs and whole body respectively in the video, and the obtained The motion trajectory information is saved, and then the motion trajectory information is extracted by the wavelet transform, a sample set is established for the extracted wavelet approximate waveform, and the set SVM support vector machine is used to train it, and the wavelet is used to obtain the power spectrum of the motion trajectory information. , the obtained features establish a sample set, which is also trained by the set SVM support vector machine, and the two trained models are tested. According to the difference in the accuracy of the two models, the data weighted fusion algorithm is used to set different weights The parameters are weighted and judged to obtain the best training results.

Description

technical field [0001] The invention belongs to the technical field of video image processing, and in particular relates to a method for detecting abnormal behavior of infants based on meanshift algorithm and SVM. Background technique [0002] Abnormal behavior of infants mainly means that the sequence of movements of the whole body is small, monotonous, and lacks movement complexity and fluency within one month after birth; within two to five months after birth, there is no variable acceleration throughout the body. Small-scale moderate-speed movement in all directions, other forms of movement suitable for age, such as limb midline movement, hand-knee contact, visual search, fingers grabbing clothes and other forms of movement are lacking, and the overall movement fluency is poor. Clinically, the persistent abnormal behavior of infants often indicates poor neurodevelopmental outcomes, and the prognosis is very likely to develop into cerebral palsy, mental retardation, etc. ...

AI Technical Summary

Problems solved by technology

The first method is to use a specific video recording method for the baby, use the whole body movement quality evaluation criteria for the video results, and judge whether the baby's behavior is normal by the person who has obtained the Prechtl's Method evaluation qualification certificate issued by the European GM Trust. This method mainly relies on clinical observation , there is a certain subjectivity

The second method is to wear a sensor device for the baby to observe the parameters, but this wearable method itself will cause some interference to the baby's movement, resulting in inaccurate prediction results

The third method is to use the computer to extract the baby's movement characteristics for pattern recognition analysis. This method will not interfere with the baby's movement and is objective, but in the process of extracting movement characteristics and recognition, often only a limited number of body parts are used. There is no analysis of the overall movement of the whole body, so it has a certain specificity

[0004] Due to the defects of the above algorithm, it is difficult to achieve ideal results in practical applications, so it is necessary to improve

Images