The plant species identification is a key issue for the phenological observation of tree crowns using phenocams. In this paper, entitle “Phenological visual rhythms: Compact representations for fine-grained plant species identification” and published at Pattern Recognition Letters, Volume 81, 2016, the authors present an effective and efficient approach for capturing phenological patterns from time series generated by digital images.
The approach offers rich information regarding spatio-temporal data, which is useful in many fields of applicability. It focuses on applications to identify and distinguish the behavior of plant species. In this scenario, visual rhythms are characterized by traditional and recently proposed image description algorithms. Such methods are able to codify key image features into fixed-size representations.
Experimental results have shown that the approach presents high accuracy on identifying individual plant species from its specific visual rhythm. Additionally, the representation is compact, making it suitable for long-term data series.
Jurandy Almeida, Jefersson A. dos Santos, Bruna Alberton, Leonor Patricia C. Morellato, Ricardo da S. Torres, Phenological visual rhythms: Compact representations for fine-grained plant species identification, Pattern Recognition Letters, Volume 81, 1 October 2016, Pages 90-100, ISSN 0167-8655, http://dx.doi.org/10.1016/j.patrec.2015.11.028.