Deep Multi-modal Object Detection for Autonomous Driving
Amal Ennajar, Nadia Khouja, Rémi Boutteau, Fethi Tlili · 2021
Robust perception in autonomous vehicles is a huge challenge that is the main tool for detecting and tracking the different kinds of objects around the vehicle. The aim is to reach the capability of the human level, which is frequently realized by taking utility of several sensing modalities. This lead to make the sensor combination a main part of the recognition system. In this paper, we present methods that have been proposed in the literature for the different deep multi-modal perception techniques. We focus on works dealing with the combination of radar information with other sensors. The radar data are in fact very important mainly when weather conditions and precipitation affect the quality of the data. In this case, it is crucial to have at least some sensors that are immunized against different weather conditions and radar is one of them.