{"id":4,"date":"2011-10-17T10:06:39","date_gmt":"2011-10-17T10:06:39","guid":{"rendered":"https:\/\/bbh.create.aau.dk\/?page_id=4"},"modified":"2011-10-17T10:06:39","modified_gmt":"2011-10-17T10:06:39","slug":"forskning","status":"publish","type":"page","link":"https:\/\/bbh.create.aau.dk\/","title":{"rendered":"Forskning|Research"},"content":{"rendered":"

En af de umiddelbare udfordringer med automatisk analyse af haller er de etiske og juridiske aspekter forbundet med at videooptage brugere i offentlige rum. For at im\u00f8dekomme denne udfordring er hele projektet bygget op omkring termiske kameraer. Pointen med s\u00e5danne kameraer er, at identitet IKKE kan genkendes, se afsnittet “Hvad er et termisk kamera?” nederst p\u00e5 siden.<\/p>\n

One immediate challenge with automatic analysis of sports arenas are the ethical and legal aspects when introducing video recorders in the public domain. In order to overcome that challenge this project is based on the use of thermal cameras. With thermal cameras it is not possible to identify recorded persons. Read more about thermal cameras in the section “What is a thermal camera” at the bottom of the page.\n<\/p>\n

\nForskningen omhandler prim\u00e6rt robust detektion af mennesker og estimering af antal, genkendelse af typiske sportsgrene, samt tracking af sportsud\u00f8verne. Det er dokumenteret i videnskabelige artikler, se publikationslisten: Publikationer<\/a>.\n<\/p>\n

\nBillederne fra de termiske kameraer, se figur 1, vil analyseres automatisk vha. billedbehandling, som f\u00f8rst vil finde alle varme objekter, se figur 2 og hern\u00e6st vurdere hvilke der er mennesker, se figur 3. P\u00e5 den m\u00e5de t\u00e6lles antallet af personer samt deres position. For at give en bedre forst\u00e5else af de analyserede data udvikles en matematisk model der kan relatere de termiske kamerabilleder, figur 4, til et billede af hallens gulv set ovenfra, se figur 5. Efter antallet og positionerne er fundet, bygges yderligere analyser ovenp\u00e5 som har til form\u00e5l at levere endnu mere pr\u00e6cise informationer omkring hvad der foreg\u00e5r i hallen.\n<\/p>\n

\nThe research primarily focuses on detection and robust counting of people, classification of sports types and tracking of sports players. The work is published in scientific papers, see the list of publications: Publications.<\/a>\n<\/p>\n

\nImages captured by the thermal cameras, see figure 1, will be analysed automatically by using image processing that first identifies all hot objects, see figure 2, and then separates humans from noise, see figure 3. This way the number of persons can be counted and their positions recorded. To better visualise the recorded data a function is found that maps the found persons image coordinates, see figure 4, to their poisition on the court, see figure 5. Further analysis will extend this base functionality in order to give a more concise information about the utilisation of the arena.\n<\/p>\n

\n
\"Input
Figur 1: Input billede fra termisk kamera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Kun
Figur 2: Kun det varme er tilbage efter segmenteringen.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Til
Figur 3: Til sidst er kun personerne tilbage.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Billede
Figur 4: Input fra det termiske kamera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Billede
Figur 5: Spillernes position fundet ud fra det termiske billede.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Input
Figure 1: Input image from thermal camera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Only
Figure 2: Only warm areas are left after the segmentation.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Only
Figure 3: Only the persons are left.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Input
Figure 4: Input image fromm the thermal camera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"The
Figure 5: The position of the players are mapped to the court.<\/figcaption><\/figure>\n<\/div>\n
\n

Aktivitetstype<\/h3>\n

\n Ved at summere de registrerede positioner over tid, dannes der “aftryk” af observerede aktivitet. Disse aftryk kan bruges til automatisk at skelne mellem forskellige sportsgrene.\n <\/p>\n<\/div>\n

\n

Type of activity<\/h3>\n

\n By summarising the detected position over time, “prints” can be made of the observed activity. These prints can be used to distinguish different kinds of sport types.\n <\/p>\n<\/div>\n

\n
\"basketball\"
Basketball<\/figcaption><\/figure>\n<\/div>\n
\n
\"soccer\"
Soccer<\/figcaption><\/figure>\n<\/div>\n
\n
\"volleyball\"
Volleyball - 1 bane<\/figcaption><\/figure>\n<\/div>\n
\n
\"volleyball\"
Volleyball - 3 baner<\/figcaption><\/figure>\n<\/div>\n
\n
\"Badminton\"
Badminton<\/figcaption><\/figure>\n<\/div>\n
\n
\"handball\"
Handball<\/figcaption><\/figure>\n<\/div>\n
\n

\n De forskellige sportsgrene kan ogs\u00e5 genkendes ved at analysere bev\u00e6gelsen af hver person, f.eks. hastighed og st\u00f8rste afstand tilbagelagt.\n <\/p>\n<\/div>\n

\n

\n Sports types can also be classified by analysing the motion of each person, e.g., speed and maximum distance covered.\n <\/p>\n<\/div>\n

\n
\"basketball\"
Basketball<\/figcaption><\/figure>\n<\/div>\n
\n
\"soccer\"
Soccer<\/figcaption><\/figure>\n<\/div>\n
\n
\"volleyball\"
Volleyball<\/figcaption><\/figure>\n<\/div>\n
\n
\"Badminton\"
Badminton<\/figcaption><\/figure>\n<\/div>\n
\n
\"handball\"
Handball<\/figcaption><\/figure>\n<\/div>\n
\n

Aktivitetsniveau<\/h3>\n

I samarbejde med idr\u00e6tsforskere er der blevet udviklet et system, der automatisk udregner aktivitetsniveauet. Dvs. et system der automatisk kan omregne den bev\u00e6gelse der m\u00e5les via kamera til energioms\u00e6tning i kroppen.<\/p>\n<\/div>\n

\n

Activity level<\/h3>\n

In collaboration with researchers from sports science we have developed a system that automatically estimates the activity level of a person. The system can translate the motion captured by the camera into an energy consumption of the body.<\/p>\n<\/div>\n

\n\"ActivityLevel\"<\/a>\n<\/div>\n
\n

Hvad er et termisk kamera?<\/h3>\n

Et termisk kamera fungerer ved at det m\u00e5ler varmestr\u00e5ling som ligger i det infrar\u00f8de spektrum. Alle objekter med en temperatur over det absolutte nulpunkt afgiver varmestr\u00e5ling og jo h\u00f8jere temperatur jo h\u00f8jere intensitet. Derfor vil varme objekter, s\u00e5som mennesker, tr\u00e6de frem ved en koldere baggrund. Figur 6 og 7 viser samme scene taget med et almindeligt kamera og et termisk kamera. I figur 7 tr\u00e6der personerne tydeligt frem uanset baggrunden, mens personen til h\u00f8jre nemt kan overses i figur 6.<\/p>\n<\/div>\n

\n

What is a thermal camera?<\/h3>\n

A thermal camera measures thermal radiation which lies in the infrared spectrum. All objects with a temperature above absolute zero emit thermal radiation and the higher the temperature, the higer the intensity. Due to this, varm objects such as humans, will be easy detectable in front of a colder background. Figure 6 and 7 shows the same scene captured by a regular and a thermal camera. In figure 7 all persons are easy detected as white blobs on a grey background whereas in figure 6 the persons are more disguised in the changing background.<\/p>\n<\/div>\n

\n
\"Billede
Figur 6: Billede taget med et almindeligt kamera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Billede
Figur 7: Billede taget med et termisk kamera. Personerne er nemme at finde, men kan ikke genkendes.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Image
Figure 6: Image captured with a regular camera.<\/figcaption><\/figure>\n<\/div>\n
\n
\"Image
Figure 7: Image captured with a thermal camera. Persons are easy to detect, but can't be recognised.<\/figcaption><\/figure>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

En af de umiddelbare udfordringer med automatisk analyse af haller er de etiske og juridiske aspekter forbundet med at videooptage brugere i offentlige rum. For at im\u00f8dekomme denne udfordring er hele projektet bygget op omkring termiske kameraer. Pointen med s\u00e5danne kameraer er, at identitet IKKE kan genkendes, se afsnittet “Hvad er et termisk kamera?” nederst … Continue reading “Forskning|Research”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-4","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=\/wp\/v2\/pages\/4","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4"}],"version-history":[{"count":0,"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=\/wp\/v2\/pages\/4\/revisions"}],"wp:attachment":[{"href":"https:\/\/bbh.create.aau.dk\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}