Illumination invariant road detection based on learning method

Kim, Bongjoe; Son, Jongin; Sohn, Kwanghoon

doi:10.1109/itsc.2011.6082917

Cited by 12 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A UV-disparity based resolution can only create a real-time map of the surroundings on a well-structured road, such as the highways. However, it does not work well in a complex environment like urban areas [63,64]. Interestingly, as stated in [11], according to a database, with a total number of 610 disengagement affairs, only around 16% related to cloudy weather, and another 1% to rainy and snowy days.…”

Section: Statisticsmentioning

confidence: 99%

A Study on Recent Developments and Issues with Obstacle Detection Systems for Automated Vehicles

Маринов

2020

Sustainability

View full text Add to dashboard Cite

This paper reviews current developments and discusses some critical issues with obstacle detection systems for automated vehicles. The concept of autonomous driving is the driver towards future mobility. Obstacle detection systems play a crucial role in implementing and deploying autonomous driving on our roads and city streets. The current review looks at technology and existing systems for obstacle detection. Specifically, we look at the performance of LIDAR, RADAR, vision cameras, ultrasonic sensors, and IR and review their capabilities and behaviour in a number of different situations: during daytime, at night, in extreme weather conditions, in urban areas, in the presence of smooths surfaces, in situations where emergency service vehicles need to be detected and recognised, and in situations where potholes need to be observed and measured. It is suggested that combining different technologies for obstacle detection gives a more accurate representation of the driving environment. In particular, when looking at technological solutions for obstacle detection in extreme weather conditions (rain, snow, fog), and in some specific situations in urban areas (shadows, reflections, potholes, insufficient illumination), although already quite advanced, the current developments appear to be not sophisticated enough to guarantee 100% precision and accuracy, hence further valiant effort is needed.

show abstract

Section: Statisticsmentioning

confidence: 99%

A Study on Recent Developments and Issues with Obstacle Detection Systems for Automated Vehicles

Маринов

2020

Sustainability

View full text Add to dashboard Cite

show abstract

“…2D Techniques Purely image based methods that use lowlevel cues such as color [1,36,21,38] or a combination of color and texture [25] have been used to model free space detection more like a road segmentation/detection problem. Siagian et al [34] use road segment detection through edge detection, and voting of vanishing points.…”

Section: Related Workmentioning

confidence: 99%

“…Based on the modality of input data, the methods for free space detection can be broadly classified into image based methods, 3D sensor based methods, and hybrid methods which utilise both (3D and 2D data). Purely image based 2D methods use low-level cues such as color or a combination of color and texture [1,36,21,38,25] and model the problem as a road segmentation/detection problem. With the tremendous suc-cess of deep networks in other computer vision problems, researchers have also proposed learning based methods for this problem [2,26].…”

Section: Introductionmentioning

confidence: 99%

A Joint 3D-2D Based Method for Free Space Detection on Roads

Patra

Maheshwari

Yadav

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

In this paper, we address the problem of road segmentation and free space detection in the context of autonomous driving. Traditional methods either use 3-dimensional (3D) cues such as point clouds obtained from LIDAR, RADAR or stereo cameras or 2-dimensional (2D) cues such as lane markings, road boundaries and object detection. Typical 3D point clouds do not have enough resolution to detect fine differences in heights such as between road and pavement. Image based 2D cues fail when encountering uneven road textures such as due to shadows, potholes, lane markings or road restoration. We propose a novel free road space detection technique combining both 2D and 3D cues. In particular, we use CNN based road segmentation from 2D images and plane/box fitting on sparse depth data obtained from SLAM as priors to formulate an energy minimization using conditional random field (CRF), for road pixels classification. While the CNN learns the road texture and is unaffected by depth boundaries, the 3D information helps in overcoming texture based classification failures. Finally, we use the obtained road segmentation with the 3D depth data from monocular SLAM to detect the free space for the navigation purposes. Our experiments on KITTI odometry dataset [12], Camvid dataset [7] as well as videos captured by us validate the superiority of the proposed approach over the state of the art.

show abstract

“…Numerous line detection algorithms and techniques have recently been proposed [7][8][9][10][11][12]. Among these algorithms, the Hough transform is one of the most robust and extensively used [13][14][15][16][17].The Hough transform is implemented according to (1):…”

Section: Line Detection Algorithmsmentioning

confidence: 99%

Real-time lane departure warning system based on a single FPGA

Shang

Song

et al. 2013

J Image Video Proc

View full text Add to dashboard Cite

This paper presents a camera-based lane departure warning system implemented on a field programmable gate array (FPGA) device. The system is used as a driver assistance system, which effectively prevents accidents given that it is endowed with the advantages of FPGA technology, including high performance for digital image processing applications, compactness, and low cost. The main contributions of this work are threefold. (1) An improved vanishing point-based steerable filter is introduced and implemented on an FPGA device. Using the vanishing point to guide the orientation at each pixel, this algorithm works well in complex environments. (2) An improved vanishing point-based parallel Hough transform is proposed. Unlike the traditional Hough transform, our improved version moves the coordinate origin to the estimated vanishing point to reduce storage requirements and enhance detection capability. (3) A prototype based on the FPGA is developed. With improvements in the vanishing point-based steerable filter and vanishing point-based parallel Hough transform, the prototype can be used in complex weather and lighting conditions. Experiments conducted on an evaluation platform and on actual roads illustrate the effective performance of the proposed system.

show abstract

Illumination invariant road detection based on learning method

Cited by 12 publications

References 12 publications

A Study on Recent Developments and Issues with Obstacle Detection Systems for Automated Vehicles

A Study on Recent Developments and Issues with Obstacle Detection Systems for Automated Vehicles

A Joint 3D-2D Based Method for Free Space Detection on Roads

Real-time lane departure warning system based on a single FPGA

Contact Info

Product

Resources

About