Gradient-Based Edge Effects on Lane Marking Detection using a Deep Learning-Based Approach
- PDF / 3,048,188 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 232 Views
RESEARCH ARTICLE-COMPUTER ENGINEERING AND COMPUTER SCIENCE
Gradient-Based Edge Effects on Lane Marking Detection using a Deep Learning-Based Approach Noor Jannah Zakaria1 · Mohd Ibrahim Shapiai1 · Hilman Fauzi1 · Hossamelden Mohamed Amin Elhawary1 · Wira Jazair Yahya2 · Mohd Azizi Abdul Rahman2 · Khairil Anwar Abu Kassim3 · Irfan Bahiuddin2 · Mohd Hatta Mohammed Ariff2 Received: 29 March 2020 / Accepted: 29 August 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract Lane detection is part of the advanced driver assistance system (ADAS) equipped in intelligent vehicles. The system provides the driver with significant geometric information of the road ahead. Numerous deep learning techniques have been employed in lane detection because of the simplicity, ease, and efficiency of these techniques in learning discriminative features from RGB (red, green, and blue) images. However, existing works have rarely considered detecting lane markings during bad weather conditions, which could reduce lane detection performance. Hence, this paper proposed a Fully Convolutional Network (FCN) model with RGB and Canny edge detection used as the model’s spatial input. The proposed platform was developed using two scenarios: FCN-RGB-edge and FCN-edge. The model development was divided into three stages, namely data acquisition, platform development, and benchmarking against existing methods and data. Both scenarios using the proposed method yielded a 4% improvement compared to the original FCN-RGB images (i.e., the previous method). The Canny edge detection method successfully extracted necessary information from the images and neglected the water drops in rainy conditions by treating them as noise. In summary, the proposed method has the potential to boost the performance of the ADAS system in detecting lane markings in rainy conditions. Keywords Advanced driver assistance system · Fully Convolutional Network · Gradient-based edges · Intelligent vehicles · Lane marking detection
1 Introduction The advanced driver assistance system (ADAS) is part of the essential systems in intelligent navigation vehicles that promote a safer environment for drivers and passengers while driving [1]. Some examples of the ADAS modules include Adaptive Cruise Control [2], Automatic Braking/Steer Away
B
Mohd Ibrahim Shapiai [email protected]
1
Centre for Artificial Intelligence & Robotics, Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
2
Advanced Vehicle System Research Group, Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
3
ASEAN NCAP Operational Unit, Malaysian Institute of Road Safety Research, 43000 Kajang, Selangor, Malaysia
[3], a Lane-Keeping System [4], Blind Spot Assist [2], a Lane Departure Warning System [5], and Lane Detection [6]. Lane Detection displays the location of a lane marking by providing the geometric features of the lane lin
Data Loading...
