SpinPerfom – A low-cost cricket spin bowling performance analysis model
**SpinPerfom – A low-cost cricket spin bowling performance analysis model**
\ No newline at end of file
**//Individual component **
Detecting whether the player steps danger area or not
**//Main objectives **
In this research, the main objective of the individual component is to detect whether the player steps on the danger area or not.
**//Specific objectives**
For implementing the player stepping the danger areas as mentioned in the background, there are three main approaches. Below show what the objectives need when using all the approaches.
• Collect data.
For the model training purpose, it is required to collect the data. In this individual component two of the following scenarios will be considered
• Scenario where players step the danger area during the follow through.
• Scenario where players step the danger area during the follow through.
• Preprocessing of the data set
Collect the footages of the players during their practice session and extract the frame.
Refine the images and organize them into two different folders one as danger area and other as non-danger area.
• Model training and testing
The preprocessed data is fed into the CNN in batches, and the CNN learns to extract relevant features from the images using multiple convolutional layers. The extracted features are then passed through fully connected layers to classify the images as "danger area" or "non-danger area".
The author is going to utilize the pre trained models Inception V3 and VGG16 for this purpose.
Get the training and accuracy and the accuracy after evaluation
