Solar-Powered Deep Learning-Based Recognition System of Daily Used Objects and Human Faces for Assistance of the Visually Impaired
| Autor: | Paolo Visconti, Nicola Ivan Giannoccaro, Carolina Del-Valle-Soto, Ramiro Velazquez, Bernardo Calabrese, Roberto de Fazio |
|---|---|
| Přispěvatelé: | Calabrese, B., Velázquez, R., del-Valle-Soto, C., De Fazio, R., Giannoccaro, N. I., Visconti, P. |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Control and Optimization
convolutional neural networks (CNN) Computer science mobile computing Mobile computing Energy Engineering and Power Technology Wearable computer Image processing Context (language use) 02 engineering and technology 01 natural sciences Convolutional neural network lcsh:Technology object recognition assistive technology convolutional neural networks (CNN) deep learning faster R-CNN mobile computing object recognition person recognition wearable system assistive technology 0202 electrical engineering electronic engineering information engineering Computer vision Electrical and Electronic Engineering Engineering (miscellaneous) deep learning faster R-CNN person recognition wearable system Renewable Energy Sustainability and the Environment business.industry lcsh:T Deep learning 010401 analytical chemistry Cognitive neuroscience of visual object recognition Process (computing) Object (computer science) 0104 chemical sciences 020201 artificial intelligence & image processing Artificial intelligence business Energy (miscellaneous) |
| Zdroj: | Energies, Vol 13, Iss 6104, p 6104 (2020) Energies; Volume 13; Issue 22; Pages: 6104 |
| ISSN: | 1996-1073 |
| Popis: | This paper introduces a novel low-cost solar-powered wearable assistive technology (AT) device, whose aim is to provide continuous, real-time object recognition to ease the finding of the objects for visually impaired (VI) people in daily life. The system consists of three major components: a miniature low-cost camera, a system on module (SoM) computing unit, and an ultrasonic sensor. The first is worn on the user’s eyeglasses and acquires real-time video of the nearby space. The second is worn as a belt and runs deep learning-based methods and spatial algorithms which process the video coming from the camera performing objects’ detection and recognition. The third assists on positioning the objects found in the surrounding space. The developed device provides audible descriptive sentences as feedback to the user involving the objects recognized and their position referenced to the user gaze. After a proper power consumption analysis, a wearable solar harvesting system, integrated with the developed AT device, has been designed and tested to extend the energy autonomy in the different operating modes and scenarios. Experimental results obtained with the developed low-cost AT device have demonstrated an accurate and reliable real-time object identification with an 86% correct recognition rate and 215 ms average time interval (in case of high-speed SoM operating mode) for the image processing. The proposed system is capable of recognizing the 91 objects offered by the Microsoft Common Objects in Context (COCO) dataset plus several custom objects and human faces. In addition, a simple and scalable methodology for using image datasets and training of Convolutional Neural Networks (CNNs) is introduced to add objects to the system and increase its repertory. It is also demonstrated that comprehensive trainings involving 100 images per targeted object achieve 89% recognition rates, while fast trainings with only 12 images achieve acceptable recognition rates of 55%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|