MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122147 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'dual-environment waste detection system using convolutional neural networks and yolo architecture.'
Inventor(s) include Dr. P. Baskaran; Mr. Anant Mohan; and Waghmare Aayushi Avinash.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a dual-environment waste detection system comprising a convolutional neural network module (FIG. 1) configured to classify underwater waste objects from underwater image data, a YOLO architecture module configured to detect and classify terrestrial waste objects from terrestrial image data, and a unified inference engine configured to route input images based on environmental context. The convolutional neural network module includes a sequential architecture having an input layer for 224 224 3 pixel images, convolutional blocks with Conv2D layers having progressively increasing filter sizes from 32 to 64 to 128 filters using 3 3 kernels, batch normalization, MaxPooling2D, dropout layers, and dense layers with softmax activation for multi-class classification. The YOLO architecture module includes a YOLOv8 model with 24 convolutional layers, 4 max-pooling layers, and 2 fully connected layers processing 640 640 pixel images and outputting bounding box coordinates and class probabilities."
Disclaimer: Curated by HT Syndication.
