MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017988 A) filed by Malla Reddy Engineering College For Women; and Malla Reddy University, Hyderabad, Telangana, on Feb. 18, for 'system and method for cricket ball trajectory prediction using hybrid cnn-lstm architecture.'
Inventor(s) include Y. Madhaveelatha; Deshoju Vemana Chary; Chinthamaneni Vijayalakshmi; Diddi Saritha; Malliga Thulasiraman; Lalband Neelu; Syed Husna Mehanoor; and N. Sridhar.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a computer vision and deep learning system for automated cricket ball trajectory prediction and tracking. The system employs a hybrid transfer learning framework that integrates convolutional neural networks (CNNs) for spatial feature extraction with long short-term memory (LSTM) networks for temporal sequence learning. Pre-trained CNN models such as ResNet50, ResNet18, and AlexNet are adapted for feature extraction, while a custom CNN is trained specifically for cricket ball recognition to achieve high accuracy under diverse match conditions including motion blur, occlusion, and varying lighting. Sequential analysis through the LSTM module enables prediction of future ball movements such as swing, spin, and bounce. The workflow begins with multi-camera video feeds, followed by preprocessing, detection, classification, and trajectory estimation. Outputs include trajectory overlays, pitch maps, release points, and speed variations, which are accessible through a user interface for analysts, coaches, and players. The invention improves automation, reduces manual errors, and provides industrial applicability in sports analytics, broadcasting, coaching systems, umpire decision support, and AI-powered training platforms."
Disclaimer: Curated by HT Syndication.
