Research on Real-Time Lane Line Detection Techonogy Based on Machine Vision

Chen, Huaizhong; Zhang, Jin

doi:10.1109/iptc.2010.124

Cited by 10 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The main purpose of filtering is to eliminate image noise and enhance the effect of the image. Low-pass or high-pass filtering operation can be performed for 2D images, low-pass filtering (LPF) is advantageous for denoising, and image blurring and high-pass filtering (HPF) are used to find image boundaries [24][25][26]. In order to perform the smoothing operation, an average, median [8], or Gaussian [23] filter could be used.…”

Section: Preprocessingmentioning

confidence: 99%

“…In order to perform the smoothing operation, an average, median [8], or Gaussian [23] filter could be used. In [24], in order to preserve detail and remove unwanted noise, Xu and Li firstly use a median filter to filter the image and then use an image histogram in order to enhance the grayscale image [23].…”

Section: Preprocessingmentioning

confidence: 99%

“…There are many common methods used for edge detection, such as Canny transform, Sobel transform, and Laplacian transform [18,24]. We have selected Canny transform which is better.…”

Section: Edge Detectionmentioning

confidence: 99%

“…After completing the lane detection, the next step is to track the lane, which is also a key technology for smart and automated vehicle (SAV) [24].…”

Section: Lane Tracking Using Extended Kalman Filtermentioning

confidence: 99%

See 3 more Smart Citations

Lane Detection Based on Connection of Various Feature Extraction Methods

Jiang

2018

Advances in Multimedia

View full text Add to dashboard Cite

Lane detection is a challenging problem. It has attracted the attention of the computer vision community for several decades. Essentially, lane detection is a multifeature detection problem that has become a real challenge for computer vision and machine learning techniques. Although many machine learning methods are used for lane detection, they are mainly used for classification rather than feature design. But modern machine learning methods can be used to identify the features that are rich in recognition and have achieved success in feature detection tests. However, these methods have not been fully implemented in the efficiency and accuracy of lane detection. In this paper, we propose a new method to solve it. We introduce a new method of preprocessing and ROI selection. The main goal is to use the HSV colour transformation to extract the white features and add preliminary edge feature detection in the preprocessing stage and then select ROI on the basis of the proposed preprocessing. This new preprocessing method is used to detect the lane. By using the standard KITTI road database to evaluate the proposed method, the results obtained are superior to the existing preprocessing and ROI selection techniques.

show abstract

Section: Preprocessingmentioning

confidence: 99%

Section: Preprocessingmentioning

confidence: 99%

“…There are many common methods used for edge detection, such as Canny transform, Sobel transform, and Laplacian transform [18,24]. We have selected Canny transform which is better.…”

Section: Edge Detectionmentioning

confidence: 99%

“…After completing the lane detection, the next step is to track the lane, which is also a key technology for smart and automated vehicle (SAV) [24].…”

Section: Lane Tracking Using Extended Kalman Filtermentioning

confidence: 99%

See 2 more Smart Citations

Lane Detection Based on Connection of Various Feature Extraction Methods

Jiang

2018

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…Com o desenvolvimento contínuo de robôs autônomos e um maior poder de decisão baseados em sistemas de visão, que tendem a aumentar a gama de aplicações potenciais, diversos são os estudos voltadosà detecção e navegação através de caminhos visuais (Lu et al, 2014;Mammeri et al, 2014;Chen et al, 2010).…”

Section: Introductionunclassified

Uma Nova Abordagem para Extração de Parâmetros do Modelo de Seguidores Visuais Baseado em NMPC aplicado ao Husky UGV

Conceição

Ribeiro

Franco

2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

Images captured by cameras, in order to perform image-based control, require processing to extract useful information in the presence of noise and obstacles. The problem of visual path following faces several drawbacks, more precisely in detecting the marks representing the route to be followed. Handling faults along the path on non-homogeneous floors and extracting parameters accurately, are some of the challenges encountered. In this paper, an image detection and parameter extraction system is proposed for path following using NMPC em (Nonlinear Model Predictive Control) controller. To circumvent the above obstacles, the visual path is approximated by a quadratic function. The proposed algorithm was embedded in the Husky UGV (Unmanned Ground Vehicle) mobile robot and compared with the original approach. Experimental results with the use of metrics such as IAE and TV demonstrate the superiority of the proposed new algorithm. Resumo: As imagens captadas por câmeras, com o intuito de realizar controle baseado em imagem, necessitam de processamentos para a extração de informaçõesúteis na presença ruídos e obstáculos. O problema do seguimento de caminhos visuais depara-se com diversas inconveniências, mais precisamente na detecção das marcas que representam a rota a ser seguida. Falhas no caminho em pisos não-homogêneos e extração de parâmetros de controle com elevada precisão, são alguns dos desafios encontrados. Neste artigo,é proposto um sistema de detecção e extração de parâmetros por imagens, para o seguimento de caminhos utilizando controlador NMPC(Nonlinear Model Predictive Control). Para contornar os empecilhos supracitados, faz-se uma aproximação do caminho visual através de uma função quadrática. O algoritmo proposto foi embarcado no robô móvel Husky UGV(Unmanned Ground Vehicle) e comparado com a abordagem original. Resultados experimentais junto a utilização de métricas como IAE e TV demonstram a superioridade do novo algoritmo proposto.

show abstract