Tracking by Identification Using Computer Vision and Radio

Abstract

We present a novel system for detection, localization and tracking of multiple people, which fuses a multi-view computer vision approach with a radio-based localization system. The proposed fusion combines the best of both worlds, excellent computer-vision-based localization, and strong identity information provided by the radio system, and is therefore able to perform tracking by identification, which makes it impervious to propagated identity switches. We present comprehensive methodology for evaluation of systems that perform person localization in world coordinate system and use it to evaluate the proposed system as well as its components. Experimental results on a challenging indoor dataset, which involves multiple people walking around a realistically cluttered room, confirm that proposed fusion of both systems significantly outperforms its individual components. Compared to the radio-based system, it achieves better localization results, while at the same time it successfully prevents propagation of identity switches that occur in pure computer-vision-based tracking.

The validity and reliability of a novel indoor player tracking system for use within wheelchair court sports

“…A static tag placed in another known location was then used to calibrate the system. This procedure takes multiple measurements from the static tag using its known x, y and z coordinates to determine the orientation and offset off each sensor (Mandeljc, Perš, Kristan, & Kovačič, 2012). During all dynamic tests (tests ii, iii & iv) nine tags were monitored, with three tags sampling at a low (4 Hz), medium (8 Hz), and high The accuracy of a motionless tag was assessed by individually placing three tags of different sampling frequency (low, medium and high) in each of the four corners of the court (where known coordinates exist).…”

A vision-based system to support tactical and physical analyses in futsal

“…The signals must be strong enough to be detected by antennas positioned around the game region, and tags must be light and small enough to allow players to perform comfortably and efficiently [39]. However, intrusive systems identify an object of interest, among a set of similar objects, in a precise and fast way, thus minimizing identity switches [28].…”

“…Microwave [9] and Radio Frequency Identification (RFID) [28] approaches use triangulation and arrival times of signals to estimate player position. In the Local Position Measurement (LPM) approach [3], the RFID sensors also emit microwaves to transmit performance data (e.g.…”

RFID-based and Kinect-based indoor positioning system

“…However, this system requires a functionally complicated mobile robot and RFID reader equipped with multidirectional antenna, which has high cost. Mandeljc et al [9] proposed a system using UWB (ultrawideband) and video for indoor person positioning. Although this system has good positioning effect, multiple UWB equipment and cameras are required to be installed at the scene, thus, the system construction cost is very high.…”