Sensor data-based deep learning step detection method

Abstract

The invention discloses a sensor data-based deep learning step detection method. The method comprises the main contents of data input, modal transfer, transfer learning and image classification, and comprises the following steps of: firstly pre-processing a gait data set by adoption of a pre-trained convolutional neural network model, and re-adjusting the size to be 229*229 after noise separation; fitting a bounding box to slice pre-processed images; carrying out image extraction by utilizing a maximum frame method, an average method and a sequence analysis method; and carrying out transfer learning on the extracted images by a pre-trained Inception-v3 model, and obtaining a result after classification. According to the method, the pre-trained network model is adopted, so that plenty of calculation resources and time are saved; by utilizing the concept of transfer learning, the limitation that the other tasks cannot be learned when various flag-free data sets are executed is avoided; and the obtained classification precision is about 90% and is 12% higher than that of the conventional machine learning method.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a sensor data-based deep learning footstep detection method. Background technique [0002] With the rapid development of technology, convolutional neural networks have become the state-of-the-art in various computer vision tasks. Sensors present in everyday life environments generate large amounts of data that provide information for activity recognition and context-aware models. Using deep learning methods to extract useful information from raw sensor data can effectively perform tasks related to classification, recognition, and segmentation, but these techniques require a large amount of labeled data in order to train these very deep networks, and are still not available for various other tasks. Many labeled datasets. And there are data types that are not visually easy to interpret, such as sensor data. However, if the deep learning footstep detection method based on sensor da...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of difficult network model training and difficult visual interpretation of data, the purpose of the present invention is to provide a deep learning footstep detection method based on sensor data

Images