Robust scene understanding is one of the main keys for safe autonomous vehicles and for competent advanced driver assistance systems. Deep neural networks are powerful tools for scene understanding, but they do not provide high-quality predictions in challenging illumination conditions with camera data. We implement three deep learning models that are able to predict the driveable road area in real-time with low latency (10.4 ms inference) from color image data (90.5 IoU) and from illumination invariant lidar data (86.2 IoU) achieving almost comparable accuracies with both modalities. We experiment with virtual multispectral solid state lidar data, that has been generated from real-world georeferenced point clouds, and show that the spectra...
In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic s...
Autonomous vehicles rely on target tracking to predict the future positions of people, vehicles and ...
For autonomous vehicles, it is an important requirement to obtain integrate static road information ...
Autonomous vehicles have previously used road markings as a reference for drivable area detection. F...
Understanding and interpreting a scene is a key task of environment perception for autonomous drivin...
In the near future, the communication between autonomous cars will produce a network of sensors that...
Autonomous vehicles perceive objects through various sensors. Cameras, radar, and LiDAR are generall...
In recent years, the usage of 3D deep learning techniques has seen a surge,mainly driven by advancem...
The captivating hopes for a future with autonomous vehicles promises to free us from one of the most...
Deep learning for safe autonomous transport is rapidly emerging. Fast and robust perception for auto...
Generating of a highly precise map grows up with development of autonomous driving vehicles. The hig...
Light Detection and Ranging (LiDAR) sensors have many different application areas, from revealing ar...
In this work, a deep learning approach has been developed to carry out road detection using only LID...
Autonomous driving is challenging on roads without lane markings and in difficult weather conditions...
In recent years a lot of research has been carried out by big tech companies in the field of autonom...
In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic s...
Autonomous vehicles rely on target tracking to predict the future positions of people, vehicles and ...
For autonomous vehicles, it is an important requirement to obtain integrate static road information ...
Autonomous vehicles have previously used road markings as a reference for drivable area detection. F...
Understanding and interpreting a scene is a key task of environment perception for autonomous drivin...
In the near future, the communication between autonomous cars will produce a network of sensors that...
Autonomous vehicles perceive objects through various sensors. Cameras, radar, and LiDAR are generall...
In recent years, the usage of 3D deep learning techniques has seen a surge,mainly driven by advancem...
The captivating hopes for a future with autonomous vehicles promises to free us from one of the most...
Deep learning for safe autonomous transport is rapidly emerging. Fast and robust perception for auto...
Generating of a highly precise map grows up with development of autonomous driving vehicles. The hig...
Light Detection and Ranging (LiDAR) sensors have many different application areas, from revealing ar...
In this work, a deep learning approach has been developed to carry out road detection using only LID...
Autonomous driving is challenging on roads without lane markings and in difficult weather conditions...
In recent years a lot of research has been carried out by big tech companies in the field of autonom...
In this paper, we introduce a deep encoder-decoder network, named SalsaNet, for efficient semantic s...
Autonomous vehicles rely on target tracking to predict the future positions of people, vehicles and ...
For autonomous vehicles, it is an important requirement to obtain integrate static road information ...