Overview of LifeCLEF 2022: An Evaluation of Machine-Learning Based Species Identification and Species Distribution Prediction

Abstract

Building accurate knowledge of the identity, the geographic distribution and the evolution of species is essential for the sustainable development of humanity, as well as for biodiversity conservation. However, the difficulty of identifying plants and animals is hindering the aggregation of new data and knowledge. Identifying and naming living plants or animals is almost impossible for the general public and is often difficult even for professionals and naturalists. Bridging this gap is a key step towards enabling effective biodiversity monitoring systems. The LifeCLEF campaign, presented in this paper, has been promoting and evaluating advances in this domain since 2011. The 2021 edition proposes four data-oriented challenges related to the identification and prediction of biodiversity: (i) PlantCLEF: cross-domain plant identification based on herbarium sheets, (ii) BirdCLEF: bird species recognition in audio soundscapes, (iii) GeoLifeCLEF: remote sensing based prediction of species, and (iv) SnakeCLEF: Automatic Snake Species Identification with Country-Level Focus. LifeCLEF Lab OverviewAccurately identifying organisms observed in the wild is an essential step in ecological studies. Unfortunately, observing and identifying living organisms requires high levels of expertise. For instance, plants alone account for more than

Computer vision‐assisted photogrammetry and one‐image 3D modeling in marine mammals

“…The small image inventory limited the machine learning and training on porpoise vs. nonporpoise objects. Second, the current program cannot perform species identification or individual recognition, which is considered a formidable task in the field of artificial intelligence (Almeida et al, 2022; Høye et al, 2021; Joly et al, 2022; Yu & Pei, 2021). Third, the influence of the pectoral fin needed to be further reduced, which could be achieved with a better algorithm or a more extensive training data set.…”

Optimizing Biodiversity Conservation in Sundaland through Advanced Geospatial Techniques and Remote Sensing Technologies

“…However, the integration of artificial intelligence (AI) with geographical information systems (GIS) and remote sensing technology has introduced innovative approaches to address these challenges [84]. AI models, trained on [86], enable automated species identification and population monitoring using diverse sources such as camera trap photos, drone footage, and satellite imagery. This advancement facilitates the tracking of migration patterns and habitat utilization with remarkable accuracy [87].…”

“…extensive datasets, are significantly contributing to biodiversity conservation efforts[85]. First, image recognition algorithms, as demonstrated byJoly et al (2022) …”

Overview of LifeCLEF 2023: Evaluation of AI Models for the Identification and Prediction of Birds, Plants, Snakes and Fungi

“…To measure progress in a sustainable and repeatable way, the LifeCLEF 2 virtual lab was created in 2014 as a continuation and extension of the plant identification task that had been run within the ImageCLEF lab 3 since 2011 [15,16,17]. Since 2014, LifeCLEF has expanded the challenge by considering animals and fungi in addition to plants and including audio and video content in addition to images [21,22,23,24,25,26,27,29,28]. Nearly a thousand researchers and data scientists register yearly to LifeCLEF to download the data, subscribe to the mailing list, benefit from the shared evaluation tools, etc.…”