Automatic interpretation of sports games is a major challenge, especially when these sports feature complex players organizations and game phases. This paper describes a bottom-up approach based on ...the extraction of semantic features from the video stream of the main camera in the particular case of soccer using scene-specific techniques. In our approach, all the features, ranging from the pixel level to the game event level, have a semantic meaning. First, we design our own scene-specific deep learning semantic segmentation network and hue histogram analysis to extract pixel-level semantics for the field, players, and lines. These pixel-level semantics are then processed to compute interpretative semantic features which represent characteristics of the game in the video stream that are exploited to interpret soccer. For example, they correspond to how players are distributed in the image or the part of the field that is filmed. Finally, we show how these interpretative semantic features can be used to set up and train a semantic-based decision tree classifier for major game events with a restricted amount of training data. The main advantages of our semantic approach are that it only requires the video feed of the main camera to extract the semantic features, with no need for camera calibration, field homography, player tracking, or ball position estimation. While the automatic interpretation of sports games remains challenging, our approach allows us to achieve promising results for the semantic feature extraction and for the classification between major soccer game events such as attack, goal or goal opportunity, defense, and middle game.
When used by autonomous vehicles for trajectory planning or obstacle avoidance, depth estimation methods need to be reliable. Therefore, estimating the quality of the depth outputs is critical. In ...this paper, we show how M4Depth, a state-of-the-art depth estimation method designed for unmanned aerial vehicle (UAV) applications, can be enhanced to perform joint depth and uncertainty estimation. For that, we present a solution to convert the uncertainty estimates related to parallax generated by M4Depth into uncertainty estimates related to depth, and show that it outperforms the standard probabilistic approach. Our experiments on various public datasets demonstrate that our method performs consistently, even in zero-shot transfer. Besides, our method offers a compelling value when compared to existing multi-view depth estimation methods as it performs similarly on a multi-view depth estimation benchmark despite being 2.5 times faster and causal, as opposed to other methods. The code of our method is publicly available at https://github.com/michael-fonder/M4DepthU .
The amount and extractability of DNA in different parts of MON810 GM hybrid was studied during different developmental stages. To quantify GM contents, an evaluation was performed of the effect of ...plant development stage on DNA density. To this end, the evolution of weights, absolute DNA yields, DNA densities and ratios of endosperm and embryo relative to total maize kernel were studied. Sampling at four stages during the growth shows an influence on relative GM quantification based on haploid genome equivalents, due to the specific maize seed composition and differences in DNA extractability from different seed tissues. During plant growth, plant parts with potential GM genes (embryo in kernel and cob on total plant) increase in importance on weight and DNA concentration level, while the endosperm drops in relative importance. Expected % GM maize values are calculated for a whole field harvest of grain maize.
In order to meet the future requirement of using non-antibiotic resistance genes for the production of transgenic plants, we have adapted the selectable marker system PMI/mannose to be used in ...Agrobacterium-mediated transformation of flax (Linum usitatissimum L.) cv. Barbara. The Escherichia coli pmi gene encodes a phosphomannose isomerase (E.C. 5.1.3.8) that converts mannose-6-phosphate, an inhibitor of glycolysis, into fructose-6-phosphate (glycolysis intermediate). Its expression in transformed cells allows them to grow on mannose-selective medium. The Agrobacterium tumefaciens strain GV3101 (pGV2260) harbouring the binary vector pNOV2819 that carries the pmi gene under the control of the Cestrum yellow leaf curling virus constitutive promoter was used for transformation experiments. Transgenic flax plants able to root on mannose-containing medium were obtained from hypocotyl-derived calli that had been selected on a combination of 20 g L-¹ sucrose and 10 g L-¹ mannose. Their transgenic state was confirmed by PCR and Southern blotting. Transgene expression was detected by RT-PCR in leaves, stems and roots of in vitro grown primary transformants. The mean transformation efficiency of 3.6%, that reached 6.4% in one experiment was comparable to that obtained when using the nptII selectable marker on the same cultivar. The ability of T1 seeds to germinate on mannose-containing medium confirmed the Mendelian inheritance of the pmi gene in the progeny of primary transformants. These results indicate that the PMI/mannose selection system can be successfully used for the recovery of flax transgenic plants under safe conditions for human health and the environment.
Reliable measurements of feet trajectories are needed in some applications, such as biomedical applications. This paper describes the data processing pipeline used in GAIMS, which is a non-intrusive ...system that measures feet trajectories based on multiple range laser scanners. Our processing pipeline relies on a new tracking paradigm, and it is based on two innovative algorithms: the first algorithm localizes the feet directly from the observed point cloud without any clustering, and the other algorithm identifies the feet. After reviewing the various types of noise affecting the point cloud, this paper explains the limitations of the classical processing approach and gives an overview of our new pipeline. The effectiveness of the proposed approach is established by discussing the results that have been obtained in several studies based on GAIMS.
Slow-motion replays provide a thrilling perspective on pivotal moments within sports games, offering a fresh and captivating visual experience. However, capturing slow-motion footage typically ...demands high-tech, expensive cameras and infrastructures. Deep learning Video Frame Interpolation (VFI) techniques have emerged as a promising avenue, capable of generating high-speed footage from regular camera feeds. Moreover, the utilization of event-based cameras has recently gathered attention as they provide valuable motion information between frames, further enhancing the VFI performances. In this work, we present a first investigation of event-based VFI models for generating sports slow-motion videos. Particularly, we design and implement a bi-camera recording setup, including an RGB and an event-based camera to capture sports videos, to temporally align and spatially register both cameras. Our experimental validation demonstrates that TimeLens, an off-the-shelf event-based VFI model, can effectively generate slow-motion footage for sports videos. This first investigation underscores the practical utility of event-based cameras in producing sports slow-motion content and lays the groundwork for future research endeavors in this domain.
Action spotting is crucial in sports analytics as it enables the precise identification and categorization of pivotal moments in sports matches, providing insights that are essential for performance ...analysis and tactical decision-making. The fragmentation of existing methodologies, however, impedes the progression of sports analytics, necessitating a unified codebase to support the development and deployment of action spotting for video analysis. In this work, we introduce OSL-ActionSpotting, a Python library that unifies different action spotting algorithms to streamline research and applications in sports video analytics. OSL-ActionSpotting encapsulates various state-of-the-art techniques into a singular, user-friendly framework, offering standardized processes for action spotting and analysis across multiple datasets. We successfully integrated three cornerstone action spotting methods into OSL-ActionSpotting, achieving performance metrics that match those of the original, disparate codebases. This unification within a single library preserves the effectiveness of each method and enhances usability and accessibility for researchers and practitioners in sports analytics. By bridging the gaps between various action spotting techniques, OSL-ActionSpotting significantly contributes to the field of sports video analysis, fostering enhanced analytical capabilities and collaborative research opportunities. The scalable and modularized design of the library ensures its long-term relevance and adaptability to future technological advancements in the domain.
The Viterbi algorithm, presented in 1967, allows a maximum likelihood decoding of partial response codes. This study focuses on the duobinary code which is the first member of this family and has ...been specified for the digital part of television systems recommended by International Organizations. Up to now the error-rate, which is the main criterion of the performance, has been evaluated by simulation. Although there exist theoretical bounds, these bounds are not satisfactory for a channel such as broadcasting (by terrestrial transmitters, cable networks or satellite) which is strongly impaired by noise, and linear and non-linear distortions. Analytical methods, verified by simulation, are presented here in order to evaluate the theoretical and exact values of the error-rate, in the form of series of numerical integrations, for a transmission in baseband or in radio-frequency with quadriphase modulation (or AM/VSB for cable networks) and coherent demodulation, in presence of noise and several distortions. This methodology can be later extended to other partial response codes, to convolutional codes and their concatenations.
Camera calibration is a crucial component in the realm of sports analytics, as it serves as the foundation to extract 3D information out of the broadcast images. Despite the significance of camera ...calibration research in sports analytics, progress is impeded by outdated benchmarking criteria. Indeed, the annotation data and evaluation metrics provided by most currently available benchmarks strongly favor and incite the development of sports field registration methods, i.e. methods estimating homographies that map the sports field plane to the image plane. However, such homography-based methods are doomed to overlook the broader capabilities of camera calibration in bridging the 3D world to the image. In particular, real-world non-planar sports field elements (such as goals, corner flags, baskets, ...) and image distortion caused by broadcast camera lenses are out of the scope of sports field registration methods. To overcome these limitations, we designed a new benchmarking protocol, named ProCC, based on two principles: (1) the protocol should be agnostic to the camera model chosen for a camera calibration method, and (2) the protocol should fairly evaluate camera calibration methods using the reprojection of arbitrary yet accurately known 3D objects. Indirectly, we also provide insights into the metric used in SoccerNet-calibration, which solely relies on image annotation data of viewed 3D objects as ground truth, thus implementing our protocol. With experiments on the World Cup 2014, CARWC, and SoccerNet datasets, we show that our benchmarking protocol provides fairer evaluations of camera calibration methods. By defining our requirements for proper benchmarking, we hope to pave the way for a new stage in camera calibration for sports applications with high accuracy standards.
The rapid advancement of artificial intelligence has led to significant improvements in automated decision-making. However, the increased performance of models often comes at the cost of ...explainability and transparency of their decision-making processes. In this paper, we investigate the capabilities of large language models to explain decisions, using football refereeing as a testing ground, given its decision complexity and subjectivity. We introduce the Explainable Video Assistant Referee System, X-VARS, a multi-modal large language model designed for understanding football videos from the point of view of a referee. X-VARS can perform a multitude of tasks, including video description, question answering, action recognition, and conducting meaningful conversations based on video content and in accordance with the Laws of the Game for football referees. We validate X-VARS on our novel dataset, SoccerNet-XFoul, which consists of more than 22k video-question-answer triplets annotated by over 70 experienced football referees. Our experiments and human study illustrate the impressive capabilities of X-VARS in interpreting complex football clips. Furthermore, we highlight the potential of X-VARS to reach human performance and support football referees in the future.
PDF
