Abstract
This paper introduces a novel approach to improve bee tracking. For this research, 50 Hz 2D videos have been recorded. The first part of the model tracks bees using a method combining colour thresholding and foreground detection, and then produces the bees’ shapes as blobs on a binary image. These blobs are analysed to estimate the positions and directions of motion of the bees. However, when bees cross over one another in the image, they are hard to track. This paper tackles this problem by using the standard Hough transform applied to bee research. Then a Kalman filter is used to track the bees using their estimated position information. Because of the 50 Hz frame rate, the trajectories of the bee movements are too variable to track reliably. The Kalman filter is modified to fit this situation. Multiple bees are being tracked, so the Hungarian assignment algorithm is used to assign predictions and measurements to individual bees. The experiment shows the bees are reliably tracked in the close view 50 Hz 2D video.
Similar content being viewed by others
References
Campbell, J., Mummert, L., & Sukthankar, R. (2008). Video monitoring of honey bee colonies at the hive entrance. Visual Observation & Analysis of Animal & Insect Behavior, 8, 1–4.
Kimura, T., Ohashi, M., Crailsheim, K., Schmickl, T., Odaka, R., & Ikeno, H. (2012). Tracking of multiple honey bees on a flat surface. Emerging Trends in Engineering and Technology. Fifth International Conference (pp. 36–39). IEEE. https://doi.org/10.1109/ICETET.2012.25.
Dearden, A., Demiris, Y., & Grau, O. (2006). Tracking football player movement from a single moving camera using particle filters. Proceedings of the 3rd European Conference on Visual Media Production (pp. 29–37). https://doi.org/10.1049/cp:20061968.
Weng, S.-K., Kuo, C.-M., & Tu, S.-K. (2006). Video object tracking using adaptive Kalman filter. Journal of Visual Communication and Image Representation, 17(6), 1190–1208. https://doi.org/10.1016/j.jvcir.2006.03.004.
Shantaiya, S., Verma, K., & Mehta, K. (2015). Multiple object tracking using Kalman filter and optical flow. European Journal of Advances in Engineering and Technology, 2(2), 34–39.
Stauffer, C., & Grimson, W. E. L. (1999). Adaptive background mixture models for real-time tracking. Computer Vision and Pattern Recognition. IEEE Computer Society Conference, 2, 264–252. https://doi.org/10.1109/cvpr.1999.784637.
Wang, K., Liang, Y., Xing, X., & Zhang, R. (2015). Target detection algorithm based on Gaussian mixture background subtraction model. In Z. Deng & H. Li (Eds.), Proceedings of the Chinese intelligent automation conference (Vol. 336, pp. 439–447). Berlin: Springer. https://doi.org/10.1007/978–3–662-46469-4_47 Lecture Notes in Electrical Engineering.
Cheng, H. D., Jiang, X. H., Sun, Y., & Wang, J. (2001). Color image segmentation: advances and prospects. Pattern Recognition, 34(12), 2259–2281. https://doi.org/10.1016/S0031-3203(00)00149-7.
Lu, S., Tsechpenakis, G., Metaxas, D. N., Jensen, M. L., & Kruse, J. (2005). Blob analysis of the head and hands: a method for deception detection. System Sciences. Proceeding of the 38th Annual Hawaii International Conference (pp. 20–23). https://doi.org/10.1109/HICSS.2005.122.
Thou-Ho, C., Yu-Feng, L., & Tsong-Yi, C. (2007). Intelligent vehicle counting method based on blob analysis in traffic surveillance. Innovative Computing. Information and Control. Second International Conference (pp. 238-238). https://doi.org/10.1109/icicic.2007.362.
Kuhn, H. (2005). The Hungarian method for the assignment problem. Naval Research Logistics, 52(1), 7–21. https://doi.org/10.1002/nav.20053.
Nandashri, D., & Smitha, P. (2015). An efficient tracking of multi object visual motion using hungarian method. International Journal of Engineering Research and Technology, 4(4). 10.17577/IJERTV4IS041410.
Ballard, D. H. (1981). Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition, 13(2), 111–122. https://doi.org/10.1016/0031-3203(81)90009-1.
Prasad, D. K., & Leung, M. K. (2012). Methods for ellipse detection from edge maps of real images. Machine Vision-Applications and Systems. InTech. https://doi.org/10.5772/35150.
Maji, S., & Malik, J. Object detection using a max-margin Hough transform. Computer Vision and Pattern Recognition. IEEE Conference (pp. 1038–1045). https://doi.org/10.1109/cvpr.2009.5206693.
Cardani, D. (2001). Adventures in hsv space. Laboratorio de Robótica, Instituto Tecnológico Autónomo de México.
Cheng, Y., & Collins, J. (2015). A model for honey bee tracking on 2D video. International Conference on Image and Vision Computing New Zealand (pp. 1–6). https://doi.org/10.1109/IVCNZ.2015.7761542.
Acknowledgements
The paper is supported by Darren Bainbridge, who provided access to beehives.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, C., Collins, J. Improvement of Honey Bee Tracking on 2D Video with Hough Transform and Kalman Filter. J Sign Process Syst 90, 1639–1650 (2018). https://doi.org/10.1007/s11265-017-1307-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-017-1307-x