A refined non-driving activity classification using a two-stream convolutional neural network
dc.contributor.author | Yang, Lichao | |
dc.contributor.author | Yang, Tingyu | |
dc.contributor.author | Liu, Haochen | |
dc.contributor.author | Shan, Xiaocai | |
dc.contributor.author | Brighton, James | |
dc.contributor.author | Skrypchuk, Lee | |
dc.contributor.author | Mouzakitis, Alexandros | |
dc.contributor.author | Zhao, Yifan | |
dc.date.accessioned | 2020-07-23T11:02:28Z | |
dc.date.available | 2020-07-23T11:02:28Z | |
dc.date.issued | 2020-06-29 | |
dc.description.abstract | It is of great importance to monitor the driver’s status to achieve an intelligent and safe take-over transition in the level 3 automated driving vehicle. We present a camera-based system to recognise the non-driving activities (NDAs) which may lead to different cognitive capabilities for take-over based on a fusion of spatial and temporal information. The region of interest (ROI) is automatically selected based on the extracted masks of the driver and the object/device interacting with. Then, the RGB image of the ROI (the spatial stream) and its associated current and historical optical flow frames (the temporal stream) are fed into a two-stream convolutional neural network (CNN) for the classification of NDAs. Such an approach is able to identify not only the object/device but also the interaction mode between the object and the driver, which enables a refined NDA classification. In this paper, we evaluated the performance of classifying 10 NDAs with two types of devices (tablet and phone) and 5 types of tasks (emailing, reading, watching videos, web-browsing and gaming) for 10 participants. Results show that the proposed system improves the averaged classification accuracy from 61.0% when using a single spatial stream to 90.5% | en_UK |
dc.identifier.citation | Yang L, Yang T, Liu H, et al., (2021) A refined non-driving activity classification using a two-stream convolutional neural network. IEEE Sensors Journal, Volume 21, Number 14, July 2021, pp. 15574-15583 | en_UK |
dc.identifier.issn | 1530-437X | |
dc.identifier.uri | https://doi.org/10.1109/JSEN.2020.3005810 | |
dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/15586 | |
dc.language.iso | en | en_UK |
dc.publisher | IEEE | en_UK |
dc.rights | Attribution-NonCommercial 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | * |
dc.subject | 2-stream CNN | en_UK |
dc.subject | optical flow | en_UK |
dc.subject | Level 3 automation | en_UK |
dc.subject | NDA classification | en_UK |
dc.title | A refined non-driving activity classification using a two-stream convolutional neural network | en_UK |
dc.type | Article | en_UK |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Refined_non-driving_activity_classification_using_a_two-stream_convolutional-2020.pdf
- Size:
- 3.18 MB
- Format:
- Adobe Portable Document Format
- Description:
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.63 KB
- Format:
- Item-specific license agreed upon to submission
- Description: