Baby Abnormal Behavior Detection Method Based on Conditional Generative Adversarial Network and SVM

Abstract

The baby abnormal behavior detection method based on conditional generation confrontation network and SVM belongs to the field of video image processing and deep learning technology. The present invention judges whether the baby’s behavior is abnormal by analyzing the baby’s movement trajectory in the video. Firstly, the baby video is obtained, and a reasonable length is intercepted. And convert it into a frame image, mark the limbs and the whole body to establish a sample library; then use the conditional generative confrontation network to track the baby's limbs and whole body; then perform wavelet approximate waveform and wavelet power spectrum calculation on the obtained target trajectory, and The obtained features are classified with support vector machine SVM and comprehensively judged; the present invention detects the movement trajectory of the baby's limbs and whole body information, which is more comprehensive than single limb detection information, and the combined training of the wavelet domain and the power spectrum domain improves the detection accuracy. Detecting whether the baby's behavior is abnormal and intervening early is of great significance for preventing diseases such as cerebral palsy in babies.

Description

technical field [0001] The invention belongs to the technical field of video image processing and deep learning, and in particular relates to a method for detecting abnormal behavior of infants based on conditional generative confrontation network and SVM. Background technique [0002] Abnormal behaviors of infants mainly refer to that within five months of birth, there is no small and medium-speed movement in all directions with variable acceleration throughout the whole body, and other forms of movement suitable for age (such as midline movement of limbs, hand-knee touch) , visual search, fingers grabbing clothes, etc.) and the overall movement fluency is not good. Abnormal behaviors of infants correspond to brain damage, which may lead to cerebral palsy in severe cases. Since cerebral palsy is usually diagnosed after a child is one to two years old, it is very important to study the detection of abnormal behaviors in early infants and to intervene in time. practical sign...

AI Technical Summary

Problems solved by technology

The first method is to use a specific video recording method for infants, and use the whole body motion quality evaluation criteria to judge whether the behavior is abnormal. This method mainly relies on observation and has a certain degree of 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