近年來，深度攝影機的價格越來越便宜，使更多的研究者可以使用深度攝影機。相對於原本的二維影像，增加深度資訊對於電腦視覺的應用有很大的幫助。棒球投手在牛棚練習時，通常沒有裁判來判定好壞球，投手無法對自己的球質做評估。因此本論文提出一個使用深度攝影機建立一個3D好球帶系統，判斷出球質與速度。最後，使用AutoCAD畫出3D好球帶以及棒球的立體軌跡供投手做參考。 In recent years,the price of depth camera became low,so that researchers can use depth camera to do more application. For computer vision,depth images can provide more useful information. When the pitcher practice in the bullpen, usually no referee to determine the quality of the ball, pitcher unable to do an assessment of their ball''s quality. Therefore,this paper proposes a 3D Strike-Zone system on Kinect2,to determine ball’s Quality and speed. Finally, we use AutoCAD to reconstruction 3D Strike-Zone and shooting trajectory to pitcher for reference.
