RFID-based multi-target passive-type indoor activity identification method

Abstract

The invention discloses an RFID-based multi-target passive-type indoor activity identification method, which takes perturbation of RFID tag phases caused by human activities as fingerprint information and obtains activity situations of multiple targets by using perturbation of different tag phases caused by activities of many persons. However, current indoor activity identification methods are mainly for a single target, and cannot be applied or lead to big activity identification errors in multi-target indoor scenes. The method of the invention realizes multi-target activity identification without the requirement that targets carry devices, solves the defects of indoor activity identification in terms of target quantity, achieves good dynamic adaptability to the environment, and is low in economic cost.

Description

Technical field [0001] The invention belongs to the field of wireless activity recognition, and relates to a multi-target activity recognition method, in particular to an RFID-based multi-target passive indoor activity recognition method. Background technique [0002] In many application scenarios, especially indoor scenarios, activity recognition technology has become particularly important. Activity recognition technology can provide the most basic facilities for medical care, optimized management, smart home, and health tracking. The traditional method of activity recognition is generally through a camera, a radar, or a hardware device such as a sensor for the subject. These methods all have large or small defects: the camera-based method is most affected by the light, and the camera poses a serious threat to human privacy protection; as far as radar is concerned, the operating range of the low-cost 60GHz radar solution is only A limited number of tens of centimeters; one of...

AI Technical Summary

Problems solved by technology

These methods all have major or minor defects: the camera-based method is most obviously affected by light, and the camera poses a serious threat to people's privacy protection; as far as radar is concerned, the 60GHz radar low-cost solution has only a limited operating range. Limited tens of centimeters; one of the biggest flaws of the method based on wearable sensors is "must wear", which will inevitably bring a lot of unnecessary troubles to the served

There are two main reasons: the activity recognition of multiple targets cannot be realized in the detection area; the accuracy is too poor to accurately estimate and complete the activity recognition of multiple targets

[0005] In summary, the existing passive activity recognition methods generally have the following defects: 1) multi-target activity recognition cannot be realized in the monitoring area; 2) the equipment is not cheap; 3) the accuracy cannot meet people's needs

Images