ActiVis: Mobile Object Detection and Active Guidance for People with Visual Impairments

Lock, Jacobus C.; Tramontano, Andrea G.; Ghidoni, Stefano; Bellotto, Nicola

doi:10.1007/978-3-030-30645-8_59

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are many fields not yet explored. An interesting application is the use of object detection to help disabled people with their mobility, as proposed in the ActiVis project [4]. This project aims to enable people Fig.…”

Section: Introductionmentioning

confidence: 99%

“…1: Example of the system proposed in the ActiVis project, during an experiment with a blindfolded participant. Source: [4].…”

Section: Introductionmentioning

confidence: 99%

“…Both networks have been tested on different datasets, in order to investigate which architecture offers the best compromise between speed and accuracy. In particular, we collected a new office-themed dataset with video and image data to test the networks performance in a real scenario, similar to the one used in the project's evaluation [4]. It is important to test the application also on videos to evaluate the robustness of the models under conditions similar to those in which a person uses the system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time Object Detection using Deep Learning for helping People with Visual Impairments

Terreran

Tramontano

Lock

et al. 2020

2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS)

View full text Add to dashboard Cite

Object detection plays a crucial role in the development of Electronic Travel Aids (ETAs), capable to guide a person with visual impairments towards a target object in an unknown indoor environment. In such a scenario, the object detector runs on a mobile device (e.g. smartphone) and needs to be fast, accurate, and, most importantly, lightweight. Nowadays, Deep Neural Networks (DNN) have become the state-of-the-art solution for object detection tasks, with many works improving speed and accuracy by proposing new architectures or extending existing ones. A common strategy is to use deeper networks to get higher performance, but that leads to a higher computational cost which makes it impractical to integrate them on mobile devices with limited computational power. In this work we compare different object detectors to find a suitable candidate to be implemented on ETAs, focusing on lightweight models capable of working in real-time on mobile devices with a good accuracy. In particular, we select two models: SSD Lite with Mobilenet V2 and Tiny-DSOD. Both models have been tested on the popular OpenImage dataset and a new dataset, named L-CAS Office dataset, collected to further test models' performance and robustness in a real scenario inspired by the actual perception challenges of a user with visual impairments.

show abstract

Section: Introductionmentioning

confidence: 99%

“…1: Example of the system proposed in the ActiVis project, during an experiment with a blindfolded participant. Source: [4].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation