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

An, Xiangjing; Shang, Erke; Song, Jinze; Li, Jian; He, Hangen

doi:10.1186/1687-5281-2013-38

Cited by 36 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Owing to the lack of an efficient direct method, edge-detection results are frequently employed to extract line features [10][11][12][13][14][15]. However, this indirect method often fails to detect lines accurately, especially when the edge signal emanating from a line in an image is weak as compared to noise strength.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Line-Detection Based on the Sum of Gradient Angle Differences

Seo

2019

Applied Sciences

View full text Add to dashboard Cite

This paper presents a method to detect line pixels based on the sum of gradient angle differences (SGAD). The gradient angle differences are calculated by comparing the four pairs of gradients arising from eight neighboring pixels. In addition, a method to classify line pixels into ridges and valleys is proposed. Furthermore, a simple line model is defined for simulation experiments. Experiments are conducted with simulation images generated using the simple line model for three line-detection methods: second-derivatives (SD)-based method, extremity-count (EC)-based method, and proposed method. The results of the simulation experiments show that the proposed method produces more accurate line-detection results than the other methods in terms of the root mean square error when the line width is relatively large. In addition, the experiments conducted with natural images show that the SD-and EC-based methods suffer from bifurcation, fragmentation, and missing pixels. By contrast, for the original and the noise-contaminated versions of the natural images, the proposed SGAD-based line-detection method is affected by such problems to a considerably smaller extent than the other two methods.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In recent years, the demand for efficient extraction of line features from images has grown rapidly owing to advancements in various applications, including lane detection in autonomous driving [10][11][12][13], blood vessel detection in medical imaging [14,15], and road detection in satellite imaging [16].…”

Section: Introductionmentioning

confidence: 99%

Line-Detection Based on the Sum of Gradient Angle Differences

Seo

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Preprocessing helps to reduce calculating time and the noise point, which consists of smoothing operation, enhanced the grayscale image and edge detection. Mean filter [17], median filter [18] or Gaussian filter [19] is used to perform smoothing operation. To overcome different illumination change, Otsu's [20] algorithm of adaptive threshold is performed.…”

Section: Related Workmentioning

confidence: 99%

Multi-Lane Detection Based on Deep Convolutional Neural Network

2019

View full text Add to dashboard Cite

In order to solve the problem of the poor robustness for extracting the multi-lane marking, a multi-lane detection algorithm based on deep convolutional neural network is proposed. Since the results of the feature extraction of lane boundary were affected by various factors, a deep convolutional neural network based on FCN network is used for lane boundary feature extraction, and the neural network can be used to classify the lane images at the pixel level. Then the network parameters are trained on the public Tusimple data set and evaluated at Caltech Lanes data set. The last part combines a linear model with a curved model to realize the establishment of the lane marking equation, Hough transform is used to determine the fit interval and the least square method is used to fit lane marking. The experimental results show that the average accuracy of the algorithm for identifying lane on the Tusimple data set is 98.74%, and the accuracy rate on the Caltech Lanes data set is 96.29%. INDEX TERMS Multi-lane detection, fully convolutional networks, Hough transform, least squares method, perspective transformation.

show abstract

“…In earlier works, many efforts were invested in solving lane detection and tracking problems for Auto-Assist Driving System (ADS) [2], [3]. These methods had been used as a warning system to the driver [4]- [8] and surprisingly, the lane detection also was used as part of the system to analyse the driver behaviour [9]. Symbols, alphabets, and custom markers were also being explored and used as the information to alert drivers [10,11].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Video Processing using Contour Numbers and Angles for Non-urban Road Marker Classification

Sani¹,

Ghani²,

Besar³

et al. 2018

IJECE

View full text Add to dashboard Cite

Road users make vital decisions to safely maneuver their vehicles based on the road markers, which need to be correctly classified. The road markers classification is significantly important especially for the autonomous car technology. The current problems of extensive processing time and relatively lower average accuracy when classifying up to five types of road markers are addressed in this paper. Two novel real time video processing methods are proposed by extracting two formulated features namely the contour number, , and angle, 𝜃 to classify the road markers. Initially, the camera position is calibrated to obtain the best Field of View (FOV) for identifying a customized Region of Interest (ROI). An adaptive smoothing algorithm is performed on the ROI before the contours of the road markers and the corresponding two features are determined. It is observed that the achievable accuracy of the proposed methods at several non-urban road scenarios is approximately 96% and the processing time per frame is significantly reduced when the video resolution increases as compared to that of the existing approach.

show abstract

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

Cited by 36 publications

References 26 publications

Line-Detection Based on the Sum of Gradient Angle Differences

Line-Detection Based on the Sum of Gradient Angle Differences

Multi-Lane Detection Based on Deep Convolutional Neural Network

Real-Time Video Processing using Contour Numbers and Angles for Non-urban Road Marker Classification

Contact Info

Product

Resources

About