Vaishnavi Bhapkar,
Sankita Salvi,
Jankar Tejaswini,
Bandal Rutuja,
K.S. Khamkar,
- Student, RDTC’s Shri Chhatrapati Shivajiraje College of Engineering, Dhangwadi, Bhor, Pune Maharashtra India
- Student RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Dhangwadi, Bhor, Pune Maharashtra India
- Student RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Dhangwadi, Bhor, Pune Maharashtra India
- Student RDTC’s, Shri Chhatrapati Shivajiraje College of Engineering, Dhangwadi, Bhor, Pune Maharashtra India
- Professor, Dhangwadi, Bhor, Pune Maharashtra India
Abstract
Object detection systems are essential tools for identifying and locating objects within images or videos. When integrated into spectacles or wearable devices, these systems provide users with real-time information about objects present in their surroundings. This functionality serves diverse purposes, such as assisting visually impaired individuals in navigating their environment or offering augmented reality data to workers during tasks. Region-based Convolutional Neural Networks (RCNN) represent a prominent machine learning model used extensively for object detection. The RCNN model operates in two main stages: initially employing a convolutional neural network (CNN) to extract distinctive features from the input image. Subsequently, it applies a region proposal algorithm to pinpoint potential object locations within the image. These proposed regions are then processed through a second CNN, which classifies them into either objects or backgrounds. Effectively, the RCNN model has demonstrated its capability to detect a broad spectrum of objects across various types of images and videos. Its proficiency lies in leveraging deep learning techniques to accurately identify and categorize objects, making it a versatile tool for applications ranging from enhancing accessibility for the visually impaired to improving productivity through augmented reality in industrial settings.
Keywords: Moving Object Detection Systems, Machine Learning, Region-based CNN, Spectacles, Algorithm
[This article belongs to International Journal of Optical Innovations & Research(ijoir)]
Browse Figures
References
- Suresh, Aswath & Arora, Chetan & Laha, Debrup & Gaba, Dhruv & Bhambri, Siddhant. (2019). Intelligent Smart Glass for Visually Impaired Using Deep Learning Machine Vision Techniques and Robot Operating System (ROS). 10.1007/978-3-319-78452-6_10.
- Saha, Himadri & Dey, Ratul & Dey, Shopan. (2017). Low cost ultrasonic smart glasses for blind. 10.1109/IEMCON.2017.8117194.
- E. Shreyas, M. H. Sheth and Mohana, “3D Object Detection and Tracking Methods using Deep Learning for Computer Vision Applications,” 2021 International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), 2021, pp. 735-738, doi: 10.1109/RTEICT52294.2021.9573964.
- Dakopoulos D, Bourbakis NG. Wearable obstacle avoidance electronic travel aids for blind: a survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews). 2009 Jul 14;40(1):25-35
- Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems. 2015;28.
- Erhan D, Szegedy C, Toshev A, Anguelov D. Scalable object detection using deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition 2014 (pp. 2147-2154).Jalled F, Voronkov I. Object detection using image processing. arXiv preprint arXiv:1611.07791. 2016 Nov 23.
- Chen X, Kundu K, Zhu Y, Ma H, Fidler S, Urtasun R. 3d object proposals using stereo imagery for accurate object class detection. IEEE transactions on pattern analysis and machine intelligence. 2017 May 19;40(5):1259-72.
- Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition 2014 (pp. 580-587).
- Roopa GM, Prakash C, Pradeep N. Computer Vision-Based Assistive Technology for Blind and Visually Impaired People: A Deep Learning Approach. Computer Assistive Technologies for Physically and Cognitively Challenged Users. 2023 Mar 22:48.
Volume | 02 |
Issue | 01 |
Received | May 31, 2024 |
Accepted | June 27, 2024 |
Published | August 7, 2024 |