@conference{11577_3373517_Realtime_Object_Detection,
    abstract = {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.},
    author = {Terreran, Matteo and Tramontano, Andrea G. and Lock, Jacobus C. and Ghidoni, Stefano and Bellotto, Nicola},
    booktitle = {IEEE International Conference on Image Processing, Applications and Systems, IPAS},
    doi = {10.1109/IPAS50080.2020.9334933},
    isbn = {978-1-7281-7575-1},
    keywords = {Object detection, real-time, electronic travel aid},
    pages = {89--95},
    title = {Real-time Object Detection using Deep Learning for helping People with Visual Impairments},
    year = {2020}
}

{"_id":"MRfWGwbWz4J4W9JkR","bibbaseid":"terreran-tramontano-lock-ghidoni-bellotto-realtimeobjectdetectionusingdeeplearningforhelpingpeoplewithvisualimpairments-2020","author_short":["Terreran, M.","Tramontano, A. G.","Lock, J. C.","Ghidoni, S.","Bellotto, N."],"bibdata":{"bibtype":"conference","type":"conference","abstract":"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.","author":[{"propositions":[],"lastnames":["Terreran"],"firstnames":["Matteo"],"suffixes":[]},{"propositions":[],"lastnames":["Tramontano"],"firstnames":["Andrea","G."],"suffixes":[]},{"propositions":[],"lastnames":["Lock"],"firstnames":["Jacobus","C."],"suffixes":[]},{"propositions":[],"lastnames":["Ghidoni"],"firstnames":["Stefano"],"suffixes":[]},{"propositions":[],"lastnames":["Bellotto"],"firstnames":["Nicola"],"suffixes":[]}],"booktitle":"IEEE International Conference on Image Processing, Applications and Systems, IPAS","doi":"10.1109/IPAS50080.2020.9334933","isbn":"978-1-7281-7575-1","keywords":"Object detection, real-time, electronic travel aid","pages":"89–95","title":"Real-time Object Detection using Deep Learning for helping People with Visual Impairments","year":"2020","bibtex":"@conference{11577_3373517_Realtime_Object_Detection,\n abstract = {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.},\n author = {Terreran, Matteo and Tramontano, Andrea G. and Lock, Jacobus C. and Ghidoni, Stefano and Bellotto, Nicola},\n booktitle = {IEEE International Conference on Image Processing, Applications and Systems, IPAS},\n doi = {10.1109/IPAS50080.2020.9334933},\n isbn = {978-1-7281-7575-1},\n keywords = {Object detection, real-time, electronic travel aid},\n pages = {89--95},\n title = {Real-time Object Detection using Deep Learning for helping People with Visual Impairments},\n year = {2020}\n}\n\n","author_short":["Terreran, M.","Tramontano, A. G.","Lock, J. C.","Ghidoni, S.","Bellotto, N."],"key":"11577_3373517_Realtime_Object_Detection","id":"11577_3373517_Realtime_Object_Detection","bibbaseid":"terreran-tramontano-lock-ghidoni-bellotto-realtimeobjectdetectionusingdeeplearningforhelpingpeoplewithvisualimpairments-2020","role":"author","urls":{},"keyword":["Object detection","real-time","electronic travel aid"],"metadata":{"authorlinks":{}}},"bibtype":"conference","biburl":"https://raw.githubusercontent.com/LCAS/eprint_cache/refs/heads/main/lcas.bib","dataSources":["eEE9jmfdvY5AQAHXr","4nz8jhch7n66Shnb3","nZg8SaGThANpWb72C"],"keywords":["object detection","real-time","electronic travel aid"],"search_terms":["real","time","object","detection","using","deep","learning","helping","people","visual","impairments","terreran","tramontano","lock","ghidoni","bellotto"],"title":"Real-time Object Detection using Deep Learning for helping People with Visual Impairments","year":2020}