Real Time Object Distance and Dimension Measurement using Deep Learning and OpenCV
Mahesh Basavaraj, H Raghuram, Mohana
Abstract
Deep learning is a subset of machine learning based on artificial neural networks in which multiple layers of processing are used to extract progressively higher-level features from data. Deep learning is focused on improving the AI process of having machines learning new things on its own. In this paper, proposed real time object dimension detection and dimension analysis using python. For ML and AI-based papers, python programming language offers consistency, simplicity, and access to excellent libraries and frameworks. It also offers platform freedom, flexibility, and a large developer community. Proposed work, explorations were done on some methodologies, including You Only Look Once (YOLO), for object identification that is meant for speed and real-time application use, and Region-Based Convolutional Neural Networks (R-CNNs) built for model performance and analysis. To make it better, a canny edge detection algorithm is being used. Canny edge detector is a multistage algorithm-based on edge detection operator that can identify a variety of edges in image.