Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People
This paper examines an importance rank learning method of objects in urban scenes for assisting visually impaired people. Object detection methods have been used to assist visually impaired people in identifying obstacles in urban scenes, such as cars and trees. However, these existing methods are n...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10154050/ |
| _version_ | 1827915294331371520 |
|---|---|
| author | Yasuhiro Nitta Mariko Isogawa Ryo Yonetani Maki Sugimoto |
| author_facet | Yasuhiro Nitta Mariko Isogawa Ryo Yonetani Maki Sugimoto |
| author_sort | Yasuhiro Nitta |
| collection | DOAJ |
| description | This paper examines an importance rank learning method of objects in urban scenes for assisting visually impaired people. Object detection methods have been used to assist visually impaired people in identifying obstacles in urban scenes, such as cars and trees. However, these existing methods are not dedicated to predicting which obstacle is important. Thus, we propose a method that estimates the importance of objects and warns them to users in order of importance ranking. We introduce a neural network-based ranking estimation method to predict the importance ranking of objects. In particular, our method uses optical flow from the previous frame and region data of detected objects as input. It helps to consider states of moving objects (<italic>e.g.</italic>, cars, motorbikes, people) in a scene. Experimental results show that our model outperforms three other baselines qualitatively and quantitatively. Furthermore, our method was highly evaluated than the baseline methods by qualified caregivers of the visually impaired people. |
| first_indexed | 2024-03-13T02:57:26Z |
| format | Article |
| id | doaj.art-42867c8a4b4249d4b3fded160111c5a4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T02:57:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-42867c8a4b4249d4b3fded160111c5a42023-06-27T23:00:39ZengIEEEIEEE Access2169-35362023-01-0111629326294110.1109/ACCESS.2023.328714710154050Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired PeopleYasuhiro Nitta0https://orcid.org/0009-0005-9985-1247Mariko Isogawa1https://orcid.org/0000-0001-9560-0276Ryo Yonetani2https://orcid.org/0000-0002-2724-6233Maki Sugimoto3https://orcid.org/0000-0002-8383-9228Graduate School of Science and Technology, Keio University, Yokohama, Kanagawa, JapanGraduate School of Science and Technology, Keio University, Yokohama, Kanagawa, JapanGraduate School of Science and Technology, Keio University, Yokohama, Kanagawa, JapanGraduate School of Science and Technology, Keio University, Yokohama, Kanagawa, JapanThis paper examines an importance rank learning method of objects in urban scenes for assisting visually impaired people. Object detection methods have been used to assist visually impaired people in identifying obstacles in urban scenes, such as cars and trees. However, these existing methods are not dedicated to predicting which obstacle is important. Thus, we propose a method that estimates the importance of objects and warns them to users in order of importance ranking. We introduce a neural network-based ranking estimation method to predict the importance ranking of objects. In particular, our method uses optical flow from the previous frame and region data of detected objects as input. It helps to consider states of moving objects (<italic>e.g.</italic>, cars, motorbikes, people) in a scene. Experimental results show that our model outperforms three other baselines qualitatively and quantitatively. Furthermore, our method was highly evaluated than the baseline methods by qualified caregivers of the visually impaired people.https://ieeexplore.ieee.org/document/10154050/Visually impaired peopleobject detectionlearning-to-rankdifferentiable sorting |
| spellingShingle | Yasuhiro Nitta Mariko Isogawa Ryo Yonetani Maki Sugimoto Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People IEEE Access Visually impaired people object detection learning-to-rank differentiable sorting |
| title | Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People |
| title_full | Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People |
| title_fullStr | Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People |
| title_full_unstemmed | Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People |
| title_short | Importance Rank-Learning of Objects in Urban Scenes for Assisting Visually Impaired People |
| title_sort | importance rank learning of objects in urban scenes for assisting visually impaired people |
| topic | Visually impaired people object detection learning-to-rank differentiable sorting |
| url | https://ieeexplore.ieee.org/document/10154050/ |
| work_keys_str_mv | AT yasuhironitta importanceranklearningofobjectsinurbanscenesforassistingvisuallyimpairedpeople AT marikoisogawa importanceranklearningofobjectsinurbanscenesforassistingvisuallyimpairedpeople AT ryoyonetani importanceranklearningofobjectsinurbanscenesforassistingvisuallyimpairedpeople AT makisugimoto importanceranklearningofobjectsinurbanscenesforassistingvisuallyimpairedpeople |