Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection
This work addresses vehicle localization challenges in unstructured environments, but it is incremental as it combines existing deep learning and model-based methods.
The paper tackles the problem of robust real-time semantic landmark detection for vehicle localization in unstructured environments with limited training data, achieving promising results and significant speed improvements over pure learning-based state-of-the-art 3D detectors.
Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in various lighting conditions and changing environment (growing vegetation) while only having few training samples available. We propose a new method which leverages Deep Learning as well as model-based methods to overcome the need of a large data set. Using RGB images and light detection and ranging (LiDAR) point clouds, our approach combines state-of-the-art classification results of Convolutional Neural Networks (CNN), with robust model-based methods by taking prior knowledge of previous time steps into account. Evaluations on a challenging real-wold scenario, with trees and bushes as landmarks, show promising results over pure learning-based state-of-the-art 3D detectors, while being significant faster.