tv Shift Deutsche Welle December 29, 2024 7:15pm-7:30pm CET
7:15 pm
of course, as always is more news on our website, dw, dot com. and of course on social media where our handle is predictably at the w needs a mike look and thanks for watching and bye for now, the easiest on the rounded oak trees. and they use by day, by night and over the full season they 2 great adaptive living see to
7:16 pm
europe of 3 gold january, good dw, the if you want to be the best and professional football, you're going to have to need the best players, the best training and the best strategy, and now to stay at the top of the game, it's becoming increasingly important to also have the best i got. so how is artificial intelligence changing? football? could you imagine supporting a football team made off of robots? these robots are already able to play against each other on the football field. the goal of the rather comfortable the noise is that by 2050 that robots will be able to defeat hope all is well champions. to be honest though, it's hard to imagine traditional football fans being that excited about a verbal football team. but technology is becoming more and more important in sport
7:17 pm
with a fans like it or not. digital clocks documenting yellow and red cards. lines people, kate, the rest in the loop, fly radio and with the help of video system. the referees of a, of the game is assessed from full angles. pitch side monitors, provide video evidence. it's undeniable. professional football is more technical than ever. you all can raise is responsible for a free innovation at the german football association, known as the day of pay doesn't take me commodities. so technology makes sorta fair . it makes decisions, verifiable, more transparent. decisions can be assessed as right or wrong. the vast majority of decisions can be categorized in this way, but fans on always as enthusiastic, it can take a long time to john to, to be evaluated. this is all passengers. you have to be careful that the technology
7:18 pm
doesn't take over now and you have to differentiate between times when using it make sense. and when it might endanger the nature of the game on to the end of the, i'd have to, you know, to, at the end of the day. but still, the referee must decide whether the outputs provided by match their perception on the picture appear in the to we even have also mind a volume of implants. and that's where i applications come in. the world football association fee for has already gradually used a new semi automatic offside detector in tournaments, cameras mounted under the stadium roof and census in the bowls and thought out to an a assistance. this then calculates the relative position of players in the bowl 500 times the 2nd, that then generates the 3 d models and notifies the referee when a player is off side. someone that goes it, the whole boat upside. it's not the steel that if it is out of the seas that i, if it is the or as possible for the decision on the field of play v i is
7:19 pm
a controversial topic in football, but it's not going anywhere. so football fans might as well in price that and that's where artificial intelligence can actually help as the tech gets better referees will be able to make better decisions. of course, that means training the systems properly and football authorities do need to ensure it's safe. got it against manipulation by humans, the events and peace of even the up, the out the from out here been revel reuse. we have deliberately manipulated matches. so of course, when introducing new technologies, we must ensure that they run as securely as possible. for example, that they can not be hand or manipulated somebody outside. they have them criminal, spent hours money, forget to have them come in order for i models to work. they need a lot of data. luckily full already has bucket loads. in modern game analysis there to data types this event on like, who passed as how often. and then there's positional data profess a minute from the german sport university. cologne explains really what we see
7:20 pm
positional data in both football and handball video in the corresponding visualized . positional data, individual players behavior can be extrapolated from positional data. tactical structures of the team can also be recognized. and hate map show who was with during the game. the daughter is gathered but track is in chest straps worn by. the players for save is around the pitch and shoulder. the data is transmitted securely, the set to then analyze in real time on line. another way of collecting positional data is to evaluate images using so called computer vision. the one difficulty is that not all players are always visible in the image at all. i could be the solution here to the document how this to us. i hope people find a more data you have, the higher the problem ability that you will find patterns. those patterns can be
7:21 pm
used to establish your correlation, which can help predict future outcomes. at the end of the day, football is complex. many parameters play a role, but the more parameters i include in my analysis, the closer am to reality in this includes us to this, in the opinion on that, and the importance of data is increasing as is the demand. so match analyst, they often consider just as important as traditional assistant coaches, but to be able to use the data extensively, analysts need training. the need to have them skills most match. analysts don't have the programming skills needed for working with data in a targeted into quick fashion vita so all by the sofa comprehensive data collection exist. mostly in top, you are paying lakes, but in the future, a team's success will depend not only on having the best players and coaches, but also the best program is when it's called cost and the ad in uh, the best thing. now it's all about who builds the best day i,
7:22 pm
who has the best parameters and who can use outputs from games or training. they must draw the right conclusions, communicate essentials to the players and ultimately improve training programs. i took him when he thinks me towards in 19 and analyzing data as quickly as possible with it has become a crucial in professional football. and it's even able to predict the probability of injuries, england international high retain, has invested in a day or system, which is real time data to maximize training programs. this can prevent injuries and optimize performance or artificial intelligence can also detect exhaustion which could help coaches during matches. they'd be able to take place off the field before they even have a chance of getting injured. this is just one area where coaches could make use of a lot and the tech is already helping them to find weaknesses in the off position. typically match analysis takes place on the screen like here, the german sport universe, the cologne data is collected and analyzed,
7:23 pm
such as police opponents behavior corner kicks, for example, precise, but time consuming. and i need to be analyzing a game with video data would take us about 8 hours, depending on how many parameters we include. put if we have position data and analyze it with our software, the same task that takes needs the seconds. so we can evaluate a lot more games in a shorter time. the last a clear advantage for those teams already working with a lot of those who can evaluate more games were more readily recognized. hutton's in opponents tactics and based on that training plans can be tailored for each new opponent that over less than 10 you a minute says the effectiveness of a new tactical approach can be tested to see. and as a team have access to data from the general display, got kind of what is, what is the noise?
7:24 pm
clicking you can test new group tactics or new skills beforehand. we can test those things here at the sports university and say the next day whether it made a difference or not, i thought the sliced missing. until today, such insights would become apparent only over the course of the season, or even after a few to face. but now priced asian analysis allows for more targeted training tactics that the idea is unsuccessful. are avoided the daniel limit football success con on lead, be planned on a computer for us. but the, some spots on the other side of the from feed on the football differs from many other sports. in that there was a large element of chance. we're talking 42 percent of all goals scored in unplanned actions. that can be trained and defense. why the game will always remain a bit mystical? maybe that's why it's so exciting on the outside. also,
7:25 pm
functions on football will always have that. i'm pretty simple element which makes it so loved by millions across the world. but algorithms could still help with many important questions, like how can players improve the game even further? or is it worth buying a certain player? that's what german analysis platform play a is attempting to achieve with their system. that much talent as they spa the on demand document, hudson, the data gives talent visibility, and the more data we have, the more visible global talent will be for us. personally, i believe that a i will completely change football and democratize football. mia? i mean, it's was on to you all klein or mission, so the more accessible data becomes the easier it will be for smaller clubs who don't have 2050 head scouting teams to find claims for their ranks. this could be the, the didn't i can find city. i think a bunch of the i all i platform play uh,
7:26 pm
analyzes data to find the next generation of full size, making recommendations to clubs on who to look out for play, use as data from football associations. the also collects its own, missing all of human lines, no sheets to then we also note whether someone scores a one new oral for new whether someone passes forward or backward 6 got whether it happens under pressure, whether it triggers something since whether it influences the rest of the game, this involves 400 data points, which we have converted into 12 mega matrices, 12 data points that are most important for a particular position. and i just guess we might be of interest for them. today play a compiles and compares data from close to a 1000000 football games. what's most, 300000 players of documented in the system such as buying unix, jamal and we'll see on amazon put in seattle on copeland kind of. yeah, it's fine. extreme to know plans via i can see what his potentially is on our end
7:27 pm
as a club. i can plan for that. yeah, i see. 2024 is he's here after that to lose a little momentum here, but not significantly in 2025, 2026. you'll continue to play at the top of this game and position the role of the met him. i mentioned it to make his claim the i o, i can calculate players. future performance with an a press is 90 percent accuracy to further improve the full costs of frequently monitored and results scrutinized. could this main good buy for its human kind of puts me in these, that fire stick in my some bisson of the august dusty machine and running just as i can. and the question implies a kind of fear, a few of that machines will take over football and everything else too. i don't believe that will happen. it will never happen in my bye, even to my thoughts that off i'm of the mention on with progress. it always depends
7:28 pm
on whether we can approach innovation fearlessly bravely it's n wisely to make better decisions. not on, i thought best of it and tried on suppressing the embracing tech. it can only be beneficial for football. unfortunately, based systems still aren't available for everyone. some of them such as play uh, currently only focusing on the men's game. and it's clear that to use a line football at the moment. you need cash. so we'll artificial intelligence actually make the game better, or will it just make the beach club strong go let us know what you think and see you next week. the, it's time for visionaries. for
7:29 pm
sustainability. but also for horsepower. the, it's time to the mobo revolution. on dw, i love it. i love the smell of a texture. there's only one thing i love about it. and how can we do without factory farming and avoid a climate disaster? will them meet? so the future be grown in a lab. the taste of future food fake sticks in 45 minutes on d. w. the untold story. only for detail. at this point of the find it
7:30 pm
4 Views
Uploaded by TV Archive on
