A Novel Visual Lane Line Detection System for a NMPC-based Path Following Control Scheme
- PDF / 3,710,037 Bytes
- 13 Pages / 595.224 x 790.955 pts Page_size
- 57 Downloads / 197 Views
A Novel Visual Lane Line Detection System for a NMPC-based Path Following Control Scheme ˜ 1 Iago Jose´ Pattas Bastos Franco1 · Tiago Trindade Ribeiro1 · Andre´ Gustavo Scolari Conceic¸ao Received: 30 May 2020 / Accepted: 21 October 2020 © Springer Nature B.V. 2020
Abstract Tracking a visual path to perform image-based control requires additional processing to extract valuable information even in the presence of inconveniences, such as failures or deformation in the lane line or even restrictive environmental conditions. Dealing with faulty in the path to be followed, non-homogeneous floors and bad lighting condition are some of the difficulties encountered that compromise the accurate of feature extraction and consequently the controller effectiveness. In this paper, a novel visual system is proposed to detect and extract useful lane line parameters and to use them in a NMPC-based Visual Path Following Control Scheme. To cope with the above-mentioned problems, the visual path is approximated by a quadratic function and to robustness improve, this novel algorithm was modified to use RANSAC as a model estimation approach instead of using the classical Least Square Method. Experimental results demonstrate the superiority of the proposed system with respect to two others, in environments with visual disturbance, faulty paths, noise and bad lighting conditions. Keywords Autonomous mobile robots · Visual path following · Computer vision · Nonlinear model predictive control
1 Introduction Currently, the task of detecting and navigate through visual paths, using computer vision techniques, has been widely used in different areas, such as industrial [10], automotive [17, 18] and agriculture [1]. Detecting lane lines that are a reference to a path, is not a trivial task. Eventually, the mobile vehicle encounters some obstacles concerning: missing (faulty) sections, deformities, low contrast, noise or environment luminosity (day, night, rainy, poor lighting, shadow/light spots) in the reference path. The use of some algorithms in visual path tracking
Andr´e Gustavo Scolari Conceic¸a˜ o
[email protected] Iago Jos´e Pattas Bastos Franco [email protected] Tiago Trindade Ribeiro [email protected] 1
LaR - Robotics Laboratory, Department of Electrical and Computer Engineering, Federal University of Bahia, Salvador, Bahia, Brazil
techniques makes the solutions less sensitive to the abovementioned kind of perturbations. It is possible to find in the literature some strategies based on color segmentation. Such techniques, use transformations based on color space, such as HSV and HSI, to increase the robustness of a visual system in front of differences in the environment luminosity [19, 23]. These methods assume that the target object has a well-defined color, generally white or yellow, but can be used with any color. The main uses of the techniques to extract lane line are included in the ADAS (Advanced Driver Assistance) systems [14, 15]. After segmentation, the step taken by many studies is the estimation of a functio
Data Loading...
