Vision-based vanishing point detection of autonomous navigation of mobile robot for outdoor applications

The vision-based approach to mobile robot navigation is considered superior due to its affordability. This paper aims to design and construct an autonomous mobile robot with a vision-based system for outdoor navigation. This robot receives inputs from camera and ultrasonic sensor. The camera is used to detect vanishing points and obstacles from the road. The vanishing point is used to detect the heading of the road. Lines are extracted from the environment using a canny edge detector and Houghline Transforms from OpenCV to navigate the system. Then, removed lines are processed to locate the vanishing point and the road angle. A low pass filter is then applied to detect a vanishing point better. The robot is tested to run in several outdoor conditions such as asphalt roads and pedestrian roads to follow the detected vanishing point. By implementing a Simple Blob Detector from OpenCV and ultrasonic sensor module, the obstacle's position in front of the robot is detected. The test results show that the robot can avoid obstacles while following the heading of the road in outdoor environments. Vision-based vanishing point detection is successfully applied for outdoor applications of autonomous mobile robot navigation.

A Robust Road Vanishing Point Detection Adapted to the Real-world Driving Scenes

Vanishing point (VP) provides extremely useful information related to roads in driving scenes for advanced driver assistance systems (ADAS) and autonomous vehicles. Existing VP detection methods for driving scenes still have not achieved sufficiently high accuracy and robustness to apply for real-world driving scenes. This paper proposes a robust motion-based road VP detection method to compensate for the deficiencies. For such purposes, three main processing steps often used in the existing road VP detection methods are carefully examined. Based on the analysis, stable motion detection, stationary point-based motion vector selection, and angle-based RANSAC (RANdom SAmple Consensus) voting are proposed. A ground-truth driving dataset including various objects and illuminations is used to verify the robustness and real-time capability of the proposed method. The experimental results show that the proposed method outperforms the existing motion-based and edge-based road VP detection methods for various illumination conditioned driving scenes.

Vanishing point detection with direct and transposed fast Hough transform inside the neural network

In this paper, we suggest a new neural network architecture for vanishing point detection in images. The key element is the use of the direct and transposed fast Hough transforms separated by convolutional layer blocks with standard activation functions. It allows us to get the answer in the coordinates of the input image at the output of the network and thus to calculate the coordinates of the vanishing point by simply selecting the maximum. Besides, it was proved that calculation of the transposed fast Hough transform can be performed using the direct one. The use of integral operators enables the neural network to rely on global rectilinear features in the image, and so it is ideal for detecting vanishing points. To demonstrate the effectiveness of the proposed architecture, we use a set of images from a DVR and show its superiority over existing methods. Note, in addition, that the proposed neural network architecture essentially repeats the process of direct and back projection used, for example, in computed tomography.