Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDigital Taxonomist: Identifying Plant Species in Citizen Scientists Photographs
71
0
0.0
(
0
)
Added by
Riccardo de Lutio
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Automatic identification of plant specimens from amateur photographs could improve species range maps, thus supporting ecosystems research as well as conservation efforts. However, classifying plant specimens based on image data alone is challenging: some species exhibit large variations in visual appearance, while at the same time different species are often visually similar; additionally, species observations follow a highly imbalanced, long-tailed distribution due to differences in abundance as well as observer biases. On the other hand, most species observations are accompanied by side information about the spatial, temporal and ecological context. Moreover, biological species are not an unordered list of classes but embedded in a hierarchical taxonomic structure. We propose a machine learning model that takes into account these additional cues in a unified framework. Our Digital Taxonomist is able to identify plant species in photographs more correctly.
rate research
Read More
67 -
Voncarlos M. Araujo
, Alceu S. Britto Jr.
, Luiz E. S. Oliveira andn Alessandro L. Koerich
2020
Automatic plant classification is a challenging problem due to the wide biodiversity of the existing plant species in a fine-grained scenario. Powerful deep learning architectures have been used to improve the classification performance in such a fine-grained problem, but usually building models that are highly dependent on a large training dataset and which are not scalable. In this paper, we propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. It uses the botanical taxonomy as a basis for a coarse-to-fine strategy applied to identify the plant genus and species. The two-view representation provides complementary global and local features of leaf images. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species. The experimental results on two challenging fine-grained datasets of leaf images (i.e. LifeCLEF 2015 and LeafSnap) have shown the effectiveness of the proposed method, which achieved recognition accuracy of 0.87 and 0.96 respectively.
We provide 28 new planet candidates that have been vetted by citizen scientists and expert astronomers. This catalog contains 9 likely rocky candidates ($R_{pl} < 2.0R_oplus$) and 19 gaseous candidates ($R_{pl} > 2.0R_oplus$). Within this list we find one multi-planet system (EPIC 246042088). These two sub-Neptune ($2.99 pm 0.02R_oplus$ and $3.44 pm 0.02R_oplus$) planets exist in a near 3:2 orbital resonance. The discovery of this multi-planet system is important in its addition to the list of known multi-planet systems within the K2 catalog, and more broadly in understanding the multiplicity distribution of the exoplanet population (Zink et al. 2019). The candidates on this list are anticipated to generate RV amplitudes of 0.2-18 m/s, many within the range accessible to current facilities.
Printed and digitally displayed photos have the ability to hide imperceptible digital data that can be accessed through internet-connected imaging systems. Another way to think about this is physical photographs that have unique QR codes invisibly embedded within them. This paper presents an architecture, algorithms, and a prototype implementation addressing this vision. Our key technical contribution is StegaStamp, a learned steganographic algorithm to enable robust encoding and decoding of arbitrary hyperlink bitstrings into photos in a manner that approaches perceptual invisibility. StegaStamp comprises a deep neural network that learns an encoding/decoding algorithm robust to image perturbations approximating the space of distortions resulting from real printing and photography. We demonstrates real-time decoding of hyperlinks in photos from in-the-wild videos that contain variation in lighting, shadows, perspective, occlusion and viewing distance. Our prototype system robustly retrieves 56 bit hyperlinks after error correction - sufficient to embed a unique code within every photo on the internet.
Due to the efforts by numerous ground-based surveys and NASAs Kepler and TESS, there will be hundreds, if not thousands, of transiting exoplanets ideal for atmospheric characterization via spectroscopy with large platforms such as JWST and ARIEL. However their next predicted mid-transit time could become so increasingly uncertain over time that significant overhead would be required to ensure the detection of the entire transit. As a result, follow-up observations to characterize these exoplanetary atmospheres would require less-efficient use of an observatorys time---which is an issue for large platforms where minimizing observing overheads is a necessity. Here we demonstrate the power of citizen scientists operating smaller observatories ($le$1-m) to keep ephemerides fresh, defined here as when the 1$sigma$ uncertainty in the mid-transit time is less than half the transit duration. We advocate for the creation of a community-wide effort to perform ephemeris maintenance on transiting exoplanets by citizen scientists. Such observations can be conducted with even a 6-inch telescope, which has the potential to save up to $sim$10,000~days for a 1000-planet survey. Based on a preliminary analysis of 14 transits from a single 6-inch MicroObservatory telescope, we empirically estimate the ability of small telescopes to benefit the community. Observations with a small-telescope network operated by citizen scientists are capable of resolving stellar blends to within 5/pixel, can follow-up long period transits in short-baseline TESS fields, monitor epoch-to-epoch stellar variability at a precision 0.67%$pm$0.12% for a 11.3 V-mag star, and search for new planets or constrain the masses of known planets with transit timing variations greater than two minutes.
Plant species identification in the wild is a difficult problem in part due to the high variability of the input data, but also because of complications induced by the long-tail effects of the datasets distribution. Inspired by the most recent fine-grained visual classification approaches which are based on attention to mitigate the effects of data variability, we explore the idea of using object detection as a form of attention. We introduce a bottom-up approach based on detecting plant organs and fusing the predictions of a variable number of organ-based species classifiers. We also curate a new dataset with a long-tail distribution for evaluating plant organ detection and organ-based species identification, which is publicly available.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
