Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional Networks
This addresses a critical need for fast and reliable obstacle detection in high-speed autonomous robotics, though it is incremental as it builds on existing deep learning methods with trade-offs in depth accuracy.
The paper tackles the problem of long-range, high-speed obstacle detection for autonomous systems by proposing an appearance-based object detection system that operates at ~300Hz without motion assumptions, achieving robust performance through a deep neural network trained on real and synthetic images.
Obstacle Detection is a central problem for any robotic system, and critical for autonomous systems that travel at high speeds in unpredictable environment. This is often achieved through scene depth estimation, by various means. When fast motion is considered, the detection range must be longer enough to allow for safe avoidance and path planning. Current solutions often make assumption on the motion of the vehicle that limit their applicability, or work at very limited ranges due to intrinsic constraints. We propose a novel appearance-based Object Detection system that is able to detect obstacles at very long range and at a very high speed (~300Hz), without making assumptions on the type of motion. We achieve these results using a Deep Neural Network approach trained on real and synthetic images and trading some depth accuracy for fast, robust and consistent operation. We show how photo-realistic synthetic images are able to solve the problem of training set dimension and variety typical of machine learning approaches, and how our system is robust to massive blurring of test images.