This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.
Three-dimensional (3D) object classification is crucial in various applications, including autonomous driving, robotics, and augmented reality, where precise detection of objects in 3D space is required. Traditional techniques for 3D object classification encompass voxel-based representations, multi-view projections, and point cloud analysis. However, these approaches can be computationally intensive, and might not capture complete structure of the underlying object. This research introduces a novel lightweight model for 3D object classification based on point clouds that achieves higher accuracy while requiring minimal computing overhead. The proposed system incorporates adaptive sampling, an Attentive-Convolution Feature block, a Dualpath feature processing block, and a non-local attention mechanism to enhance feature representation and classification performance. To our knowledge, this is the first study to propose a lightweight TnetLight module as a transformation network that aligns and converts input point clouds, capturing subtle geometric variations and highlighting differences between objects to enhance shape recognition and differentiation accuracy. Additionally, the model integrates an Attentive-Convolution Feature extraction block that combines local geometric features with global contextual information, enhancing the network’s ability to capture both detailed and broader characteristics for better differentiation between objects with slight variations. The network was evaluated on the ModelNet10 dataset, achieving an accuracy of 94.4%.
The agricultural industry prioritizes crop protection, particularly against threats like pink bollworm infestations in cotton crops. This paper presents a comprehensive solution using the Robot Operating System (ROS) to deploy an autonomous robot for detecting pink bollworm infestations and tracking red illnesses. Drones collect multispectral photos of cotton fields, aiding path planning via Normalized Difference Vegetation Index (NDVI) computations. A bespoke dataset of RGB and multispectral images trained a YOLOv8 model for object detection, achieving a mean Average Precision (mAP) of 67.1%, Precision of 67.9%, and Recall of 61.8%. The robot was tested in two separate cotton fields, with rows around 20 meters long and the camera at 60 cm height for optimal real-time detection. The findings, compared to hand counts and confirmed against NDVI estimates, showed an average accuracy of 76.04% for B.T. Cotton and 67.54% for Organic Cotton fields. This study demonstrates the effectiveness of the proposed system in accurately detecting and managing crop threats. Combining ROS, drones, NDVI calculations, and a robust detection model, it provides a scalable approach for autonomous crop monitoring and protection, with the potential for broader agricultural adoption.