Unstructured Road Vanishing Point Detection Using the Convolutional Neural Network and Heatmap Regression
This addresses a challenging perception problem for autonomous vehicles in unstructured environments, representing an incremental improvement over existing methods.
The paper tackles unstructured road vanishing point detection for autonomous driving by combining convolutional neural networks with heatmap regression, achieving state-of-the-art accuracy on Kong's dataset with real-time performance up to 33 fps.
Unstructured road vanishing point (VP) detection is a challenging problem, especially in the field of autonomous driving. In this paper, we proposed a novel solution combining the convolutional neural network (CNN) and heatmap regression to detect unstructured road VP. The proposed algorithm firstly adopts a lightweight backbone, i.e., depthwise convolution modified HRNet, to extract hierarchical features of the unstructured road image. Then, three advanced strategies, i.e., multi-scale supervised learning, heatmap super-resolution, and coordinate regression techniques are utilized to achieve fast and high-precision unstructured road VP detection. The empirical results on Kong's dataset show that our proposed approach enjoys the highest detection accuracy compared with state-of-the-art methods under various conditions in real-time, achieving the highest speed of 33 fps.