The paper describes a deep neural network-based detect for ball, detection in high resolution, long shot, video recordings of cricket matches. The detect ball , has an efficient fully convolutional architecture and can operate on input video stream with high resolution.
It produces ball confidence map encoding the position of the detected ball, player confidence map ball and player bounding boxes tensor encoding players’ positions and bounding boxes. This improves discriminability of small objects (the ball) as larger visual context around the object of interest is taken into account for the classification using yolov5.
Due to its specialized design, the network has two orders of magnitude less parameters than a generic deep neural network-based object detector, such as SSD or YOLOv5. This allows real-time processing of high resolution input video stream. Our code and pre-trained model can be found on the project website. if you are looking for source code of Cricket ball tracking using yolov5 project click the link below.
Introduction to ball detection and tracking using yolov5 project
In this paper using YOLOV5 deep neural network architecture to predict ball. Accurate and efficient ball detection is a key element of any solution intended to automate analysis of video recordings of source. The method proposed in this paper allows effective and efficient ball in long shot, video recordings.
It’s intended component of the computer system developed for ball academies and clubs to automate analysis of video recordings. Detecting the ball from long-and short distance in video.
First, the ball is very small compared to other objects visible in the observer scene by frame by frame. its difficult find the ball, so we read the frame, Ball size varies significantly depending on the position.
In long shot recordings in cricket game, the ball can appear as small as 6 pixels, when it’s on the far side of the pitch, opposite from the camera; and as big as 20 pixels, when it’s on the near side of the field. At such small size, the ball can appear indistinguishable from parts of the player body or the background clutter.
System Architecture of Ball Tracking using yolov5
H/w and S/W requirements
Computer : System.
Ram : 1GB
Rom : 32GB
Technology : Machine Learning.
Front End : GUI-tkinter.
IDLE : python 3.10.4
Virtual Envs : Anaconda