Convolutional Neural Networks Refitting by Bootstrapping for Tracking People in a Mobile Robot

Abstract

Convolutional Neural Networks are usually fitted with manually labelled data. The labelling process is very time-consuming since large datasets are required. The use of external hardware may help in some cases, but it also introduces noise to the labelled data. In this paper, we pose a new data labelling approach by using bootstrapping to increase the accuracy of the PeTra tool. PeTra allows a mobile robot to estimate people’s location in its environment by using a LIDAR sensor and a Convolutional Neural Network. PeTra has some limitations in specific situations, such as scenarios where there are not any people. We propose to use the actual PeTra release to label the LIDAR data used to fit the Convolutional Neural Network. We have evaluated the resulting system by comparing it with the previous one—where LIDAR data were labelled with a Real Time Location System. The new release increases the MCC-score by 65.97%.

Biometric recognition through gait analysis

“…An optimized design for the Convolutional Neural Network (CNN) that allows People Tracking (PeTra) for working in real-time 18 . Finally, a bootstrapping-based method that improves the accuracy at specific locations, such as empty rooms or corridors 19 .…”

“…Then, it was included a correlation method of location estimates using Kalman filters, as well as an optimization for the Convolutional Neural Network (CNN) 18 . Finally, a bootstrapping method was proposed to improve the accuracy of the tool in specific locations 19 . People Tracking (PeTra) is the tool selected to detect people in this work.…”