A review of recent advances in lane detection and departure warning system

Narote, Sandipann P.; Bhujbal, Pradnya N.; Narote, A. S.; Dhane, Dhiraj Manohar

doi:10.1016/j.patcog.2017.08.014

Cited by 219 publications

(107 citation statements)

References 35 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…Knowing the position of the lanes is essential to move the vehicle correctly on the street, and to avoid collisions with other road users. For this reason, lane detection holds great importance for assisted and autonomous driving, as ADAS for both lane departure warning and lane keeping assist [1] need reliable information about lane boundaries. In their general form, lane detection algorithms address the problem using a three-step approach [2]: in a preliminary phase, images are pre-processed, to filter noise and obstacles, and to facilitate further detections.…”

Section: A State Of the Artmentioning

confidence: 99%

Enhanced free space detection in multiple lanes based on single CNN with scene identification

Pizzati

García

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Many systems for autonomous vehicles' navigation rely on lane detection. Traditional algorithms usually estimate only the position of the lanes on the road, but an autonomous control system may also need to know if a lane marking can be crossed or not, and what portion of space inside the lane is free from obstacles, to make safer control decisions. On the other hand, free space detection algorithms only detect navigable areas, without information about lanes. State-ofthe-art algorithms use CNNs for both tasks, with significant consumption of computing resources. We propose a novel approach that estimates the free space inside each lane, with a single CNN. Additionally, adding only a small requirement concerning GPU RAM, we infer the road type, that will be useful for path planning. To achieve this result, we train a multi-task CNN. Then, we further elaborate the output of the network, to extract polygons that can be effectively used in navigation control. Finally, we provide a computationally efficient implementation, based on ROS, that can be executed in real time. Our code and trained models are available online.

show abstract

Section: A State Of the Artmentioning

confidence: 99%

Enhanced free space detection in multiple lanes based on single CNN with scene identification

Pizzati

García

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…Narote et al [9] identifies the following common stages in lane detection systems: image preprocessing, color processing, selection of region-of-interest (ROI), lane modeling and lane detection. Their work includes also stages relative to lane departures systems, but they are not analyzed because exceed the limits of this research.…”

Section: Introductionmentioning

confidence: 99%

“…The success of the application depends strongly of this stage, and the operations performed are associated with environmental conditions, as not-well-marked lanes, smog, rain, sun, shadows, among others. Several image preprocessing techniques are applied by many researchers to increase the lane detection accuracy, and include smoothing via mean, median [9] or Gaussian [11] filters, contrast enhancement, and edge detectors as Canny [12], Sobel [13], Prewitt [14], or Roberts. An empirical study of edge detectors for road lanes is presented in [15] [16], where a Gabor filter is used to estimate each pixel orientation to detect the vanishing point; or as presented in [17] which apply feature extraction of lanes based on the Gaussian Sum Particle filter (GSPF).…”

Section: Introductionmentioning

confidence: 99%

Simple Detection and Classification of Road Lanes based on Image Processing

Araya¹,

Unicen²,

Espada³

et al. 2018

IJITCS

View full text Add to dashboard Cite

Abstract-Road accidents, besides being one of the main causes of mortality, have an economic impact on vehicle owners. Several conditions as driver imprudence, road conditions and obstacles are the main factor that will cause accidents. The most important automotive industries are incorporating technology to reduce risk in vehicles. In this way, lane detection systems have important attention, because from this data is possible to determine risk situations such as presence of obstacles, incorrect lane changes or lane departures. This paper proposes a technique for lane detection, based on image processing, which allows identifying the position of lateral lanes and their type. The method is composed of four stages: edge enhancement, potential lanes detection, post-processing and color lane estimation. The method was proved using image dataset and video captures over 12.000 frames. The accuracy of the system was of 91.9%.

show abstract

“…Corrdinates Conversion: As the lane lines are not always straight, various shapes of lane make it difficult to model lane structure in a unified form. Traditional methods use polynomial curves, splines, parabolic curves, etc[25] to fit Three orthographic views of the trajectories inFig. 2(b) Global view of right lane totally blocked.…”

mentioning

confidence: 99%

Synchronous Maneuver Searching and Trajectory Planning for Autonomous Vehicles in Dynamic Traffic Environments

Qian¹,

Xu²,

Zeng³

et al. 2022

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

In the real-time decision-making and local planning process of autonomous vehicles in dynamic environments, the autonomous driving system may fail to find a reasonable policy or even gets trapped in some situation due to the complexity of global tasks and the incompatibility between upper level maneuver decisions with the lower level trajectory planning. To solve this problem, this paper presents a synchronous maneuver searching and trajectory planning (SMSTP) algorithm based on the topological concept of homotopy. Firstly, a set of alternative maneuvers with boundary limits are enumerated on a multilane road. Instead of sampling numerous paths in the whole spatio-temporal space, we, for the first time, propose using Trajectory Profiles (TPs) to quickly construct the topological maneuvers represented by different routes, and put forward a corridor generation algorithm based on graph-search. The bounded corridor further constrains the maneuver's space in the spatial space. A step-wise heuristic optimization algorithm is then proposed to synchronously generate a feasible trajectory for each maneuver. To achieve real-time performance, we initialize the states to be optimized with the boundary constraints of maneuvers, and we set some heuristic states as terminal targets in the quadratic cost function. The solution of a feasible trajectory is always guaranteed only if a specific maneuver is given. The simulation and realistic driving-test experiments verified that the proposed SMSTP algorithm has a short computation time which is less than 37ms, and the experimental results showed the validity and effectiveness of the SMSTP algorithm.

show abstract

A review of recent advances in lane detection and departure warning system

Cited by 219 publications

References 35 publications

Enhanced free space detection in multiple lanes based on single CNN with scene identification

Enhanced free space detection in multiple lanes based on single CNN with scene identification

Simple Detection and Classification of Road Lanes based on Image Processing

Synchronous Maneuver Searching and Trajectory Planning for Autonomous Vehicles in Dynamic Traffic Environments

Contact Info

Product

Resources

About