Citation Number
6
Views
13
Downloands
6
Futbol maçlarında hakemlerin verebileceği kararlara yardımcı olması amacıyla, otonom sistemlere olan ihtiyaç gün geçtikçe artmaktadır. Bu talep artışının ana sebebi maçlarda hakemlerin önemli maçlarda sonuca etki edebilecek kritik hatalar yapabilmesinden kaynaklanmaktadır. Bundan dolayı, birçok ülkede futbol maçlarında hakemlerin yanı sıra bilgisayarlı görü sistemine dayalı çalışan yardımcı hakem sistemleri de devreye girmiştir. Bu tarz sistemler ile hatalar aza indirilerek adil bir rekabet ortamının sağlanması amaçlanmaktadır. Bu çalışmada futbol maçlarında gol olayının tespiti için bir bilgisayarlı görü sistemi(GolKaSis) tasarlanmıştır. GolKaSis’te öncelikle, tasarlanan futbol sahası prototipinde kaleye yakın bir bölgeye yerleştirilen kameradan elde edilen videolardan alınan görüntüler negatif ve pozitif olarak ayrılmıştır. Bu görüntülerden pozitif olanlar gol olayını gösterenlerden, negatif olanlar ise gol olayının meydana gelmediği video görüntülerinden oluşmaktadır. Geliştirilen bilgisayarlı görü sisteminde gerçek zamanlı alınan video görüntüleri ile pozitif görüntülerin eşleştirilmesi ise Haar Cascade Sınıflandırıcı sağlanarak gol olayı tespit edilmektedir. Tasarlanan prototip üzerinde yapılan test işlemlerinde önerilen bilgisayarlı görü sisteminin gol olayını %91 başarım oranı ile doğru olarak tespit ettiği görülmüştür. Ayrıca çalışmada, videolardan elde edilen görüntülerdeki ışık şiddetinin gol olayının doğru olarak tespit edilmesine etkisi olduğu görülmüştür. Bu nedenle kullanılan kameranın özellikleri de göz önüne alınarak ışık şiddetinin uygun şekilde ayarlanması gerekmektedir.
In order to help judges make decisions in football matches, the need for autonomous systems is increasing on a daily basis. The main reason for this increase in demand is that in matches the judges can make critical errors that can affect the outcome in important matches. As a result, in many countries, as well as judges in football matches, as well as assisted judgment systems that work based on the computer vision system have been activated. This type of system is aimed at reducing errors and providing a fair competition environment. In this study, a computer vision system (GolKaSis) was designed to detect the goal event in football matches. In GolKaSis, first and foremost, the images taken from the videos taken from the camera placed in a area near the castle in the prototype of the designed football field are divided negatively and positively. The positive of these images consist of the videos that show the goal event, the negative of the video that does not happen the goal event. In the developed computer vision system, the matching of real-time video images with positive images is provided by the Haar Cascade Classification system to detect the goal event. In the test processes on the prototype designed, it was shown that the recommended computer vision system correctly identified the goal event with a 91% success rate. The study also found that the light strength in the images obtained from the videos has an impact on the correct detection of the goal event. Therefore, taking into account the characteristics of the camera used, the light intensity should be adjusted properly.
The need for autonomous systems increases day by day in order to be able to appeal to the referee's decisions in soccer. The main reason for this increase in demand is the fact that referees can make critical mistakes that could have an effect on important matches. Therefore, in many countries football referees, who are based on the computer vision system as well as referees, have been engaged in soccer games. It is aimed to provide fair competition environment by reducing mistakes with such systems. In this study, a computer vision system, GolKaSis, was designed for the determination of the goal event in football matches. In the GolKaSis, firstly, the images taken from the videos obtained from the cameras placed in a region close to the tower in the designed football field prototype are separated as negative and positive. The ones that are positive from these images are those showing the goal event, the ones that are negative are the video images where the goal event is not coming to fruition. In the developed computer vision system, the matching of the positive video with the video images taken in real time is determined by providing Haar Cascade Classifier. It has been seen that the computerized vision system proposed in the test procedures on the designed prototype correctly determined the goal event with 91% success rate. Furthermore, in the study, it was seen that the intensity of the light in the videos obtained from the videos is the effect of correcting the goal phenomenon. Thus, taking into account the characteristics of the camera, it is necessary to determine the intensity of the light.
Field : Mühendislik
Journal Type : Ulusal
Article Detail 
Citation Owners
Similar Articles
Download PDF
Journal Information
Listen Paper
Print This Page
Share
Mendeley
