Enhanced Object Detection With Deep Convolutional Neural Networks for Advanced Driving Assistance
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1417
- Type
- D - Journal article
- DOI
-
10.1109/tits.2019.2910643
- Title of journal
- IEEE Transactions on Intelligent Transportation Systems
- Article number
- -
- First page
- 1572
- Volume
- 21
- Issue
- 4
- ISSN
- 1524-9050
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
C - Communications and Networking (Comms)
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposed an enhanced object detection approach for advanced driving assistance systems (ADAS). Its significance is from improved detection accuracy and speed combined with enhancements to tackle the object scale variation and occlusion. The approach was ranked top on car and pedestrian detection in the KITTI benchmark for ADAS; today it remains amongst the top performers. The work led to an H2020 research grant (£1.2 million, COSAFE#824092), an invited paper (DOI: 10.1109/ICNP.2019.8888126) and a joint grant with UESTC, Chinese Ministry of Science and Technology. It was widely followed by national and international groups (including DOI: 10.1016/j.patcog.2019.107182, DOI:10.1109/ACCESS.2019.2929432, DOI: 10.1109/TITS.2019.2961145).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -