Video tracking and identifying unmarked moving insects Open Access

Tan, Zhixin (Spring 2018)

Permanent URL:


 The quantitative measurement of animal behavior is a critical problem in many biological studies. Computer-assisted video tracking is among the most prominent methods for the measurement, especially for small animals such as insects. However, many existing video tracking methods cannot identify unmarked insects efficiently, which compromises the tracking quality. In this study, we developed a framework that involves Kalman filter, color correlogram comparison (idTracker), and artificial neural networks to track and identify multiple insects in the video, even when their trajectories are interrupted due to occlusion. We implemented and tested these algorithms on the videos of bumblebees, several of which showed desirable performances. We also evaluated the performance of different individual insect identifiers and proposed some directions for improvement. This study demonstrated the feasibility of this framework and supported the possibility of being widely used in insect behavior research.

Table of Contents

1 Introduction

2 Material and Methods

3 Results and Discussions

4 Conclusions and future directions


About this Honors Thesis

Rights statement
  • Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.
  • English
Research Field
Committee Chair / Thesis Advisor
Committee Members
Last modified

Primary PDF

Supplemental Files