EcoIP: An open source image analysis toolkit to identify different stages of plant phenology for multiple species with pan-tilt-zoom cameras

a r t i c l e i n f o Because of the increased number of cameras employed in environmental sensing and the tremendous image output they produce, we have created a flexible, open-source software solution called EcoIP to help automatically determine different phenophases for different species from digital image sequences. Onset and ending dates are calculated through an iterative process: (1) training images are chosen and areas of interest identified, (2) separation of foreground and background is accomplished based on a naive Bayesian method, (3) a signal is created based on the separation model and (4) it is then fit to a sigmoid that contains the dates of interest. Results using different phenological events of different species indicate that estimated dates fall within a few days of the observed dates for most cases. Our experiments indicate that color separability and scene illumination are contributing factors to this error. EcoIP is implemented as an open platform that encourages anyone to execute, copy, distribute, study, change, and/or improve the application. Plant phenology is one of the most responsive and easily observable traits in nature that are impacted by changing climate (Badeck et al., 2004). Indeed, plant phenology relates strongly to primary productivity and is sensitive to microclimatic variations, thus its study is vital to understanding species responses, ecosystem function, and the effects of climate (Wright et al., 1999). The interest in plant phenology and global climate change has increased significantly in recent years, especially with estimates of the advancing initiation of spring activity by both ground-based (Root et al. is devoted to observing continental-scale trends in plant systems and growth dynamics. Ideally, the best way to observe large-scale changes in phenological patterns with climate change is with remote sensing applications that are linked to ground-based measurements. Indeed, the manual collection of phenological data provides important information at the organism level while satellite imagery is captured over wide areas but at low spatial resolution, often too coarse to detect species and community level responses (Badeck et al., 2004). The use of new technology is being investigated to scale up (Allen et al., 2007) and standardize ground-based measurements by using a subset of species (USA-NPN, www.usanpn. org; Betancourt et al., 2007; Schwartz et al., 2012), and by modeling local climatic conditions (Jolly et al., 2005). Though methods are still lacking , the use of visible light digital cameras holds promise (Richardson et …