Online fusion positioning method based on monitoring video and PDR

Abstract

The invention discloses an online fusion positioning method based on a monitoring video and a PDR. The method comprises the following steps: collecting data of a mobile phone motion sensor of a user, and obtaining a PDR track of the user according to a PDR algorithm; collecting video stream data of a real-time monitoring camera, and obtaining a video pedestrian track by adopting a deep learning pedestrian detection framework and a feature weighting algorithm; carrying out PDR track and video pedestrian track matching by using a dual track matching algorithm; and determining the current position and tracking trajectory of the user according to the matching result. In order to solve the problems that the system deployment cost and the positioning precision are difficult to balance, the system cost is high and the practical application feasibility is low in the existing positioning technology, the video pedestrian tracking technology and the PDR technology are comprehensively utilized, and monitoring camera equipment which is widely deployed in the indoor environment and a smart phone carried by a user are fully utilized; the method does not need to additionally deploy positioning equipment, reduces the cost of a positioning system, makes up for the respective defects of the two technologies, and improves the positioning precision.

Description

technical field [0001] The invention relates to a positioning method, in particular to an online fusion positioning method based on monitoring video and PDR. Background technique [0002] Existing indoor positioning technologies are mainly divided into two categories. The first category uses wireless signals such as Wi-Fi, PDR, geomagnetism, Bluetooth, UWB, and radio frequency for positioning. The main problems of this type of positioning technology are system deployment costs and positioning accuracy. It is difficult to balance between them. If you use Wi-Fi, PDR, geomagnetic and other positioning technologies, you can use existing hardware equipment to reduce positioning costs, but the signal is unstable, easily disturbed by the environment, and the positioning accuracy is low; if you use Bluetooth, UWB, Positioning technologies such as radio frequency can obtain good positioning accuracy, but additional hardware devices need to be deployed, and the system construction cos...

AI Technical Summary

Problems solved by technology

[0002] Existing indoor positioning technologies are mainly divided into two categories. The first category uses wireless signals such as Wi-Fi, PDR, geomagnetism, Bluetooth, UWB, and radio frequency for positioning. The main problems of this type of positioning technology are system deployment costs and positioning accuracy. It is difficult to balance between them. If you use Wi-Fi, PDR, geomagnetic and other positioning technologies, you can use existing hardware equipment to reduce positioning costs, but the signal is unstable, easily disturbed by the environment, and the positioning accuracy is low; if you use Bluetooth, UWB, Radio frequency and other positioning technologies can achieve good positioning accuracy, but additional hardware equipment is required, and the system construction cost is high, which is not conducive to actual promotion and application

The second category is to use multiple positioning technologies for fusion positioning. The positioning accuracy is higher than that of a single positioning technology, but there are still problems such as high system cost or low practical application feasibility.

Images