The sudden outbreak and uncontrolled spread of COVID-19 disease is one of the most important global problems today. In a short period of time, it has led to the development of many deep neural network models for COVID-19 detection with modules for explainability. In this work, we carry out a systematic analysis of various aspects of proposed models. Our analysis revealed numerous mistakes made at different stages of data acquisition, model development, and explanation construction. In this work, we overview the approaches proposed in the surveyed Machine Learning articles and indicate typical errors emerging from the lack of deep understanding of the radiography domain. We present the perspective of both: experts in the field - radiologists and deep learning engineers dealing with model explanations. The final result is a proposed checklist with the minimum conditions to be met by a reliable COVID-19 diagnostic model.
We built an Instant Review System (IRS) for badminton, also named a Challenge System. It allows players to verify linesmen in/out decisions and makes the game fairer. Elements such as lighting, the influence of air-conditioning on the flight trajectory, or the moving mats can significantly impact the final in/out decision. Due to the construction of the shuttlecock, it behaves differently during the flight than, for example, a tennis ball. This publication discusses the problems we encountered during our work with the proposed solution. We present the evolution of the system’s architecture: the first version with the cameras mounted above the court and placed around the court close to the lines, tracking the shuttlecock in 3D; and the second, improved version with cameras placed only around the court, without 3D reconstruction. We used our system during the BWF World Senior Badminton Championships in Katowice. We present the system’s results from this tournament and compare them with linesmen’s decisions. We describe the system’s verification process by the Badminton World Federation and Polish Badminton Federation and discuss evaluation methods for such systems. Our solution is comparable to the commercial product used in the biggest badminton tournaments in regard to processing time and accuracy. Still, our architecture and algorithms make installing it much easier and faster, making the system more adaptive, reliable, flexible, and universal in relation to the practical requirements of sports halls.
30 January 2021 in Multimedia Tools and Applications
High-speed cameras are used in computer vision systems to track balls, shuttlecocks, or players in many different sports. Collected information is used for statistics, as coaches’ and players’ aids to improve technique and tactics or as referees’ aids to verify their decisions or to enrich television broadcasts. Sports arenas in which games are played are often equipped with lights generating flickering effects in captured movies. A fast and yet effective enough algorithm is necessary to remove flickering so movement detection and object tracking algorithms could be used. In this paper, we propose a fast flicker removal algorithm working as an online filter on frame streams at speeds exceeding 200 frames per second. Most of the solutions found in literature concentrate on effectiveness and accuracy and not on the speed of operation. In contrast, our original solution is designed with speed in mind with sufficient accuracy to be used before calculating differential frames to detect movement in streams. Our algorithm is adaptive and works when lighting conditions are changing (new light sources) and performs well with various light sources that are causing flickering. The results of the experiments carried out show the high effectiveness of the method implemented on CPU and GPU, allowing effective tracking of objects of interest in preliminary applications of a commercially offered instant review system for badminton.