Fundamental Study on Road Detection Method Using Multi-Layered Distance Data with HOG and SVM

Abstract

[abstFig src='/00280006/11.jpg' width='300' text='Road detection method with HOG and SVM' ] This paper describes a road area detection method using a support vector machine (SVM) and histogram of oriented gradient (HOG) features. The boundary lines have many features, such as changes in height, color, and brightness, but these are sensitive to noise. In terms of robustness, it is difficult to match road boundary lines with the boundary lines on 2D maps. Localization methods using texture matching are accurate, but they have disadvantages related to adapting to changes in the environment. We therefore decided to make a classifier to differentiate road areas from other areas by detecting the road plane. First, we calculate the HOG features from range data acquired by 3D LiDAR. We then create the road area classifier by applying SVM. Finally, we evaluate the basic performance of the proposed method in simulation and in the real world.

A Systematic Literature Review About the Impact of Artificial Intelligence on Autonomous Vehicle Safety

“…In addition to that, [34] suggests research to improve the recognition capabilities to distinguish zebra crossing from speed bump. [75] proposed future research about road detection using road lane markers that could be detected by LIDAR, while [21] proposed more research focused on optimizing the lane detection and vehicle recognition algorithms to reduce their computational costs. Also considering the high computational costs, [27] proposed using parallel computing to increase the speed of the image recognition algorithms.…”

“…Road Detection; Road environmental recognition and various objects detection in real driving conditions; How to "automate" manual annotation for images to train visual perception for AVs; [75], [28], [37] Hough Transformation 3 5%…”

“…Sensors and Perception is the topic with the largest number of studies (21). They are mostly related to computer vision and detection techniques necessary for adding the necessary capabilities to detect different aspects of the navigation environment and supporting the autonomy of the AVs, such as: general computer vision [19], Doppler sensing [20], lane detection [21], daylight detection and evaluation [22], obstacles detection [23][24] [25], pedestrian detection [26][27], pedestrian trajectory prediction [28], road detection [24][29] [75], road junction detection [30], road terrain detection [31], traffic signal detection [32][18], situation awareness [33], speed bump detection [25] [34], traffic light detection [35], vehicle detection [36] and virtual worlds for training detection [37].…”

Estimation of Ego-Vehicle’s Position Based on Image Registration

“…Histogram of Oriented Gradients (HOG) of the incline magnitude and direction of the distance data is then calculated. Accordingly, Support Vector Machine (SVM) is applied to detect the road area as detailed in reference (16) . The classification results using the KITTI database are shown in Table 1.…”

Prediction Governors for Input-Affine Nonlinear Systems and Application to Automatic Driving Control

“…Based on this perspective, many previous studies have been conducted on image recognition as a means of recognizing the driving environment with high prediction accuracy [5][6][7]. Moreover, many studies have been conducted on various prediction methods, such as Kalman filtering and machine learning, and automatic driving control systems based on such methods have been proposed [8][9][10][11][12][13]. However, the prediction method, regardless of its accuracy, may produce prediction errors that are unavoidable in an unpredictable real-world situation.…”