Sensor fusion of camera, GPS and IMU using fuzzy adaptive multiple motion models

Abstract

A tracking system that will be used for Augmented Reality (AR) applications has two main requirements: accuracy and frame rate. The first requirement is related to the performance of the pose estimation algorithm and how accurately the tracking system can find the position and orientation of the user in the environment. Accuracy problems of current tracking devices, considering that they are low-cost devices, cause static errors during this motion estimation process. The second requirement is related to dynamic errors (the end-to-end system delay; occurring because of the delay in estimating the motion of the user and displaying images based on this estimate. This paper investigates combining the vision-based estimates with measurements from other sensors, GPS and IMU, in order to improve the tracking accuracy in outdoor environments. The idea of using Fuzzy Adaptive Multiple Models (FAMM) was investigated using a novel fuzzy rule-based approach to decide on the model that results in improved accuracy and faster convergence for the fusion filter. Results show that the developed tracking system is more accurate than a conventional GPS-IMU fusion approach due to additional estimates from a cam-

The impact of position errors on crowd simulation

“…However, they have not yet been tested on high-density scenarios, which result in stampedes; so far the performance of CNNs was benchmarked against the UCSD dataset [54], which focuses on sparse crowds with non-pedestrian anomalous objects (e.g., skaters, biker, carts, and wheelchairs) and anomalous pedestrian patterns (e.g., a pedestrian walking in opposite direction to other pedestrians). Conceptually, one may create a hybrid stampede detection system that would leverage GPS trackers and video data feeds synergistically, improving the accuracy of the stampede analysis [5].…”

Improving target tracking robustness with Bayesian data fusion

“…Object tracking is a key element of computer vision and a heavily researched topic. This problem has multiple applications in autonomous following drones [6], autonomous vehicles, augmented reality [3] and robotics [7,22]. Wu et al [22] and Kristan et al [11] discuss at least 50 unique trackers that have been developed.…”

“…Initially, the idea of adaptive fusion began in the 1960s with the introduction of the Kalman filter (KF). Additionally, other approaches based on particle filters (PF) [5] and fuzzy logic [3] have also recently risen to prominence. Each of these methods assumes some sort of prior knowledge about the trajectory of what you are tracking.…”

Proactive Model for Handling Conflicts in Sensor Data Fusion Applied to Robotic Systems

“…A lot of these techniques are carried out on a set of homogeneous sensors while others exist that are used on heterogeneous sensors, like for example to calculate a more accurate position of the robot (Bostanci et al, 2018;Nemra and Aouf, 2010).…”