Scaling up SoccerNet with multi-view spatial localization and re-identification.

Soccer videos are a rich playground for computer vision, involving many elements, such as players, lines, and specific objects. Hence, to capture the richness of this sport and allow for fine automated analyses, we release SoccerNet-v3, a major extension of the SoccerNet dataset, providing a wide variety of spatial annotations and cross-view correspondences. SoccerNet's broadcast videos contain replays of important actions, allowing us to retrieve a same action from different viewpoints. We annotate those live and replay action frames showing same moments with exhaustive local information. Specifically, we label lines, goal parts, players, referees, teams, salient objects, jersey numbers, and we establish player correspondences between the views. This yields 1,324,732 annotations on 33,986 soccer images, making SoccerNet-v3 the largest dataset for multi-view soccer analysis. Derived tasks may benefit from these annotations, like camera calibration, player localization, team discrimination and multi-view re-identification, which can further sustain practical applications in augmented reality and soccer analytics. Finally, we provide Python codes to easily download our data and access our annotations.

SeedQuant: a deep learning-based tool for assessing stimulant and inhibitor activity on root parasitic seeds.

Witchweeds (Striga spp.) and broomrapes (Orobanchaceae and Phelipanche spp.) are root parasitic plants that infest many crops in warm and temperate zones, causing enormous yield losses and endangering global food security. Seeds of these obligate parasites require rhizospheric, host-released stimulants to germinate, which opens up possibilities for controlling them by applying specific germination inhibitors or synthetic stimulants that induce lethal germination in the host's absence. To determine their effect on germination, root exudates or synthetic stimulants/inhibitors are usually applied to parasitic seeds in in vitro bioassays, followed by assessment of germination ratios. Although these protocols are very sensitive, the germination recording process is laborious, representing a challenge for researchers and impeding high-throughput screens. Here, we developed an automatic seed census tool to count and discriminate germinated seeds (GS) from non-GS. We combined deep learning, a powerful data-driven framework that can accelerate the procedure and increase its accuracy, for object detection with computer vision latest development based on the Faster Region-based Convolutional Neural Network algorithm. Our method showed an accuracy of 94% in counting seeds of Striga hermonthica and reduced the required time from approximately 5 min to 5 s per image. Our proposed software, SeedQuant, will be of great help for seed germination bioassays and enable high-throughput screening for germination stimulants/inhibitors. SeedQuant is an open-source software that can be further trained to count different types of seeds for research purposes.

Recognition of children on age-different images: Facial morphology and age-stable features.

The situation of missing children is one of the most emotional social issues worldwide. The search for and identification of missing children is often hampered, among others, by the fact that the facial morphology of long-term missing children changes as they grow. Nowadays, the wide coverage by surveillance systems potentially provides image material for comparisons with images of missing children that may facilitate identification. The aim of study was to identify whether facial features are stable in time and can be utilized for facial recognition by comparing facial images of children at different ages as well as to test the possible use of moles in recognition. The study was divided into two phases (1) morphological classification of facial features using an Anthropological Atlas; (2) algorithm developed in MATLAB® R2014b for assessing the use of moles as age-stable features. The assessment of facial features by Anthropological Atlases showed high mismatch percentages among observers. On average, the mismatch percentages were lower for features describing shape than for those describing size. The nose tip cleft and the chin dimple showed the best agreement between observers regarding both categorization and stability over time. Using the position of moles as a reference point for recognition of the same person on age-different images seems to be a useful method in terms of objectivity and it can be concluded that moles represent age-stable facial features that may be considered for preliminary recognition.