Sitting posture detecting method based on target detection and body posture estimation

Abstract

The invention, which belongs to the technical field of image processing and computer vision, relates to a sitting posture detecting method based on target detection and body posture estimation. A fusion feature formed by fusion of a feature I and a feature II is extracted, the fusion feature is inputted into a CNN, and if the fusion feature is from a training set, the feature is used for traininga network parameter; if the fusion feature is from a verification set, the feature is used for verifying a network parameter, an error signal is transmitted by a back propagation algorithm, the gradient is updated, an optimal value is found, and classification regression is carried out by using flexible maximum activation function Softmax to obtain a final classification result and classificationaccuracy. Therefore, a problem of target loss under the complicated condition with multiple targets in existing sitting posture detection is solved; the traditional method relying on a wearable deviceor sensor is abandoned; and with the method based on target detection and body posture estimation, the sitting posture of each task target can be determined accurately under the conditions of complicated background and high group density.

Description

technical field [0001] The invention belongs to the technical field of image processing and computer vision, and relates to a sitting posture detection method based on target detection and human body posture estimation. Background technique [0002] With the further development of artificial intelligence technology, deep learning technology has also received more and more attention. Unmanned vehicles, smart home systems, and other industries that are booming with artificial intelligence technology are also changing people's lifestyles and production methods all the time. Machines replace humans and liberate productivity. Applications. The teaching and management methods on campus should also take advantage of the "free ride" of deep learning to improve the work of educators. In the past, when people evaluated a teacher's teaching effect, a special teaching supervisor went to each classroom to inspect, which was not only time-consuming and labor-intensive, but also might ca...

AI Technical Summary

Problems solved by technology

However, if the students listening to the class appear to be lying on the desk, distracted and sleepy, it can indicate that the teacher's teaching quality is not good, and he needs to improve his teaching methods

General methods can be mainly divided into methods based on the deployment of sensors based on the environment, based on wearable devices and based on single-person cameras. These methods not only cannot detect multiple targets in real time, but also have high costs and do not have much advantage

Images