Computer Vision and Deep Learning-Enabled UAVs: Proposed Use Cases for Visually Impaired People in a Smart City

Technological research and innovation have advanced at a rapid pace in recent years, and one group hoping to benefit from this, is visually impaired people (VIP). Technology may enable them to find new ways of travelling around smart cities, thus improving their quality of life (QoL). Currently, there are approximately 110 million VIP worldwide, and continuous research is crucial to find innovative solutions to their mobility problems. Recent advances such as the increase in Unmanned Aerial Vehicles (UAVs), smartphones and wearable devices, together with an ever-growing uptake of deep learning, computer vision, the Internet of Things (IoT), and virtual and augmented reality (VR)/(AR), have provided VIP with the hope of having an improved QoL. In particular, indoor and outdoor spaces could be improved with the use of such technologies to make them suitable for VIP. This paper examines use cases both indoors and outdoors and provides recommendations of how deep learning and computer vision-enabled UAVs could be employed in smart cities to improve the QoL for VIP in the coming years.

[1]  Pascual Campoy Cervera,et al.  A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles , 2017, J. Sensors.

[2]  Hong Yan,et al.  Support System Using Microsoft Kinect and Mobile Phone for Daily Activity of Visually Impaired , 2015 .

[3]  Saeid Nahavandi,et al.  A Classifier Graph Based Recurring Concept Detection and Prediction Approach , 2018, Comput. Intell. Neurosci..

[4]  Markus Funk,et al.  DroneNavigator: Using Drones for Navigating Visually Impaired Persons , 2015, ASSETS.

[5]  Louis-Philippe Morency,et al.  Multimodal Machine Learning: A Survey and Taxonomy , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Nada Philip,et al.  Towards 5G Health for Medical Video Streaming over Small Cells , 2016 .

[7]  George Kozmetsky,et al.  The Technopolis Phenomenon: Smart Cities, Fast Systems, Global Networks , 1992 .

[8]  Per Lynggaard,et al.  Smart Cities and the Ageing Population , 2014 .

[9]  Stefano Mattoccia,et al.  A wearable mobility aid for the visually impaired based on embedded 3D vision and deep learning , 2016, 2016 IEEE Symposium on Computers and Communication (ISCC).

[10]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[11]  Xiaolin Hu,et al.  Recurrent convolutional neural network for object recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[13]  Aaron Steinfeld,et al.  Enhancing the safety of visually impaired travelers in and around transit stations. , 2016 .

[14]  Ali Jasim Ramadhan.  Wearable Smart System for Visually Impaired People , 2018, Sensors.

[15]  Zhe Xu,et al.  Feature Learning Based Approach for Weed Classification Using High Resolution Aerial Images from a Digital Camera Mounted on a UAV , 2014, Remote. Sens..

[16]  Larisa Dunai,et al.  Obstacle detectors for visually impaired people , 2014, 2014 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM).

[17]  David Hyunchul Shim,et al.  Perception, Guidance, and Navigation for Indoor Autonomous Drone Racing Using Deep Learning , 2018, IEEE Robotics and Automation Letters.

[18]  Cheng-Lung Lee,et al.  Assessment of a simple obstacle detection device for the visually impaired. , 2014, Applied ergonomics.

[19]  Daniel Thalmann,et al.  A wearable system for mobility improvement of visually impaired people , 2007, The Visual Computer.

[20]  Hassan A. Karimi,et al.  Context-aware obstacle detection for navigation by visually impaired , 2017, Image Vis. Comput..