In order to safely navigate traffic, automated vehicles need to face a variety of challenges such as the uncertainty of typical road environments. A key component of road traffic, that both illustrates such uncertainty and highly influences traffic participants behavior, is parked cars. For instance, mistakenly considering a car as parked directly increases the collision risk and, on the other hand, expecting parked cars to move leads to over-precautions, inefficient, and potentially confusing planned trajectories. Despite being a major component of traffic prediction, little work addresses the parked car detection, and to our knowledge none in the context of autonomous driving. This paper introduces the problem of parked car classification and illustrates some of its challenges and corner cases. For generality, we focus on sensor-set independent classification and in particular we ignore vehicle light information which further increases the difficulty of the problem. Our contribution includes introducing, discussing, and comparing a list of features as candidate predictors of parked car classification. More precisely, we collect and annotate 180,469 vehicle occurrences over a duration of approximately 21 minutes; we then compare the classification accuracy of a list of features over a few classification methods. Based on sensor set independent detections and map information, we achieve an accuracy of 92.9% on our test-set and discuss how this can likely be improved.

Reliable traffic light detection and classification is crucial for automated driving in urban environments. Currently, there are no systems that can reliably perceive traffic lights in real-time, without map-based information, and in sufficient distances needed for smooth urban driving. We propose a complete system consisting of a traffic light detector, tracker, and classifier based on deep learning, stereo vision, and vehicle odometry which perceives traffic lights in real-time. Within the scope of this work, we present three major contributions. The first is an accurately labeled traffic light dataset of 5000 images for training and a video sequence of 8334 frames for evaluation. The dataset is published as the Bosch Small Traffic Lights Dataset and uses our results as baseline. It is currently the largest publicly available labeled traffic light dataset and includes labels down to the size of only 1 pixel in width. The second contribution is a traffic light detector which runs at 10 frames per second on 1280×720 images. When selecting the confidence threshold that yields equal error rate, we are able to detect traffic lights as small as 4 pixels in width. The third contribution is a traffic light tracker which uses stereo vision and vehicle odometry to compute the motion estimate of traffic lights and a neural network to correct the aforementioned motion estimate.

Reliable lane detection is a fundamental necessity for driver assistance, driver safety functions and fully automated vehicles. Based on other detection and classification tasks, deep learning based methods are likely to yield the most accurate outputs for detecting lane markers, but require vast amounts of labeled data. We propose to train a deep neural network for detecting lane markers in camera images without manually labeling any images. To achieve this, we project high definition maps for automated driving into our image and correct for misalignments due to inaccuracies in localization and coordinate frame transformations. The corrections are performed by calculating the offset between features within our map and detected ones in the images. By using detections in the actual image for refining the projections, our labels become close to pixel perfect. After a fast, visual quality check, our projected lane markers can be used for training a fully convolutional network to segment lane markers in images. A single worker can easily generate 20,000 of those labels within a single day. Our fully convolutional network is trained only on automatically generated labels. All of our detections are based solely on gray-scale mono camera inputs without any additional information. The resulting network regularly detects clean lane markers at distances of around 150 meters on a 1 Megapixel camera.