Cricket Event Recognition and Classification from Umpire Action Gestures using Convolutional Neural Network

The advancement of hardware and deep learning technologies has made it possible to apply these a variety fields. A architecture, the Convolutional Neural Network (CNN), revolutionized field computer vision. One most popular applications vision is in sports. There are different types events cricket, which makes complex game. This task introduces new dataset called SNWOLF for detecting Umpire postures categorizing cricket match. proposed will be preliminary help, was assessed system development automatic generation highlights from sport. When comes umpire authority make crucial decisions about on-field incidents. referee signals important incidents with hand gestures that one-of-a-kind. Based on referee's stance video action frame, identifies frequently used classification: SIX, NO BALL, WIDE, OUT, LEG BYE, FOUR. method utilizes Networks (CNNs) architecture extract features classify identified frames into six event classes. Here created completely 1040 images Action Images containing events. Our train CNNs classifier 80% tested 20% remaining images. approach achieves an average overall accuracy 98.20% converges very low cross-entropy losses. influential answer sport highlights.