Implementation of semantic segmentation for road and lane detection on an autonomous ground vehicle with LIDAR

Lim, Kai Li; Drage, Thomas; Bra, Thomas

doi:10.1109/mfi.2017.8170358

Cited by 17 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All semantic segmentation models are trained on two K80 GPUs. Road lane marking and road edge detection on Lidar-based autonomous cars are addressed in [5]. This includes obstacle avoidance capability but cannot detect road lane markings.…”

Section: A Deep Learning For Semantic Segmentationmentioning

confidence: 99%

“…Recently, Deep learning has widely been adopted in semantic segmentation and object detection. For example, the two semantic segmentation networks, Efficient Neural Network (ENet) [2], [3] and Segmentation Network (SegNet) [4], [5], utilize a compact encoder-decoder architecture. Both networks consist of an encoder and a corresponding decoder network followed by a pixel-wise classification layer.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Vehicles Perception (AVP) Using Deep Learning: Modeling, Assessment, and Challenges

Jebamikyous

Kashef

2022

IEEE Access

View full text Add to dashboard Cite

Perception is the fundamental task of any autonomous driving system, which gathers all the necessary information about the surrounding environment of the moving vehicle. The decision-making system takes the perception data as input and makes the optimum decision given that scenario, which maximizes the safety of the passengers. This paper surveyed recent literature on autonomous vehicle perception (AVP) by focusing on two primary tasks: Semantic Segmentation and Object Detection. Both tasks play an important role as a vital component of the vehicle's navigation system. A comprehensive overview of deep learning for perception and its decision-making process based on images and LiDAR point clouds is discussed. We discussed the sensors, benchmark datasets, and simulation tools widely used in semantic segmentation and object detection tasks, especially for autonomous driving. This paper acts as a road map for current and future research in AVP, focusing on models, assessment, and challenges in the field.

show abstract

Section: A Deep Learning For Semantic Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Autonomous Vehicles Perception (AVP) Using Deep Learning: Modeling, Assessment, and Challenges

Jebamikyous

Kashef

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The lidar is also unable to detect road markings, which is required for lane keeping. Lim et al (2017) implemented a semantic image segmentation to enhance a lidar-based autonomous ground vehicle for road and lane marking detection. By integrating the semantic segmentation output and lidar measurements for road edges and obstacles, distance measurements for each segmented object are obtained, which allows the vehicle to be programmed to drive autonomously within the road lanes and away from road edges.…”

Section: Implementing Sensors To Perceive the Environmentmentioning

confidence: 99%

A review of vehicle active safety control methods: From antilock brakes to semiautonomy

Ahangarnejad

Radmehr

Ahmadian

2020

Journal of Vibration and Control

View full text Add to dashboard Cite

A comprehensive review of technologies and approaches for active safety systems designed to reduce ground vehicle crashes, as well as the associated severity of injuries and fatalities, is provided. Active safety systems are commonly referred to as systems that can forewarn a driver of a potential safety hazard, or automatically intervene to reduce the likelihood of an accident without requiring driver intervention. The data from naturalistic drivers has shown that such systems are instrumental in improving vehicle safety in various conditions, particularly at higher speeds and under adverse road conditions. The increased integration of sensors, electronics, and real-time processing capabilities has served as one of the critical enabling elements in the widespread integration of active safety systems in modern vehicles. The emphasis is placed on control approaches for active safety systems and their progression over the years from antilock brakes to more advanced technologies that have nearly enabled semiautonomous driving. A review of key active safety control approaches for antilock braking, yaw stability, traction control, roll stability, and various collision avoidance systems is provided.

show abstract

“…In [16], based on spatiotemporal images, the authors proposed a method for lane detection, which proved to be more robust and efficient. In [17], an implementation of semantic image segmentation to enhance LiDAR-based road and lane detection was presented. In [18], using a proposed region of interest, the authors managed to reduce the calculation and high noise level for lane detection.…”

Section: Introductionmentioning

confidence: 99%

Managing Localization Uncertainty to Handle Semantic Lane Information from Geo-Referenced Maps in Evidential Occupancy Grids

Cherfaoui

Yang

2020

Sensors

View full text Add to dashboard Cite

Occupancy grid is a popular environment model that is widely applied for autonomous navigation of mobile robots. This model encodes obstacle information into the grid cells as a reference of the space state. However, when navigating on roads, the planning module of an autonomous vehicle needs to have semantic understanding of the scene, especially concerning the accessibility of the driving space. This paper presents a grid-based evidential approach for modeling semantic road space by taking advantage of a prior map that contains lane-level information. Road rules are encoded in the grid for semantic understanding. Our approach focuses on dealing with the localization uncertainty, which is a key issue, while parsing information from the prior map. Readings from an exteroceptive sensor are as well integrated in the grid to provide real-time obstacle information. All the information is managed in an evidential framework based on Dempster–Shafer theory. Real road results are reported with qualitative evaluation and quantitative analysis of the constructed grids to show the performance and the behavior of the method for real-time application.

show abstract

Implementation of semantic segmentation for road and lane detection on an autonomous ground vehicle with LIDAR

Cited by 17 publications

References 19 publications

Autonomous Vehicles Perception (AVP) Using Deep Learning: Modeling, Assessment, and Challenges

Autonomous Vehicles Perception (AVP) Using Deep Learning: Modeling, Assessment, and Challenges

A review of vehicle active safety control methods: From antilock brakes to semiautonomy

Managing Localization Uncertainty to Handle Semantic Lane Information from Geo-Referenced Maps in Evidential Occupancy Grids

Contact Info

Product

Resources

About