Fabian B. Flohr

Dr. Fabian B. Flohr

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
MBMarkus Braun
Markus Braun
SKSebastian Krebs
Sebastian Krebs
FFFabian B. Flohr
Fabian B. Flohr
DGDariu M. Gavrila
Dariu M. Gavrila
Big data has had a great share in the success of deep learning in computer vision. Recent works suggest that there is significant further potential to increase object detection performance by utilizing even bigger datasets. In this paper, we introduce the EuroCity Persons dataset, which provides a large number of highly diverse, accurate and detailed annotations of pedestrians, cyclists and other riders in urban traffic scenes. The images for this dataset were collected on-board a moving vehicle in 31 cities of 12 European countries. With over 238200 person instances manually labeled in over 47300 images, EuroCity Persons is nearly one order of magnitude larger than datasets used previously for person detection in traffic scenes. The dataset furthermore contains a large number of person orientation annotations (over 211200). We optimize four state-of-the-art deep learning approaches (Faster R-CNN, R-FCN, SSD and YOLOv3) to serve as baselines for the new object detection benchmark. We analyze the generalization capabilities of these detectors when trained with the new dataset. We furthermore study the effect of the training set size, the dataset diversity (day- vs. night-time, geographical region), the dataset detail (i.e. availability of object orientation information) and the annotation quality on the detector performance. Finally, we analyze error sources and discuss the road ahead.

2 July 2018 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
JKJulian Kooij
Julian Kooij
FFFabian B. Flohr
Fabian B. Flohr
EPEwoud A. I. Pool
Ewoud A. I. Pool
DGDariu M. Gavrila
Dariu M. Gavrila
Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting the path of objects with multiple dynamic modes. The dynamics of such targets can be described by a Switching Linear Dynamical System (SLDS). However, predictions from this probabilistic model cannot anticipate when a change in dynamic mode will occur. We propose to extract various types of cues with computer vision to provide context on the target’s behavior, and incorporate these in a Dynamic Bayesian Network (DBN). The DBN extends the SLDS by conditioning the mode transition probabilities on additional context states. We describe efficient online inference in this DBN for probabilistic path prediction, accounting for uncertainty in both measurements and target behavior. Our approach is illustrated on two scenarios in the Intelligent Vehicles domain concerning pedestrians and cyclists, so-called Vulnerable Road Users (VRUs). Here, context cues include the static environment of the VRU, its dynamic environment, and its observed actions. Experiments using stereo vision data from a moving vehicle demonstrate that the proposed approach results in more accurate path prediction than SLDS at the relevant short time horizon (1 s). It slightly outperforms a computationally more demanding state-of-the-art method.

19 December 2023 in Robotics
Verified
Journal Article
Open access
PDF file
ESErik Schuetz
Erik Schuetz
FFFabian B. Flohr
Fabian B. Flohr
Predicting the trajectory of other road users, especially vulnerable road users (VRUs), is an important aspect of safety and planning efficiency for autonomous vehicles. With recent advances in Deep-Learning-based approaches in this field, physics- and classical Machine-Learning-based methods cannot exhibit competitive results compared to the former. Hence, this paper provides an extensive review of recent Deep-Learning-based methods in trajectory prediction for VRUs and autonomous driving in general. We review the state and context representations and architectural insights of selected methods, divided into categories according to their primary prediction scheme. Additionally, we summarize reported results on popular datasets for all methods presented in this review. The results show that conditional variational autoencoders achieve the best overall results on both pedestrian and autonomous driving datasets. Finally, we outline possible future research directions for the field of trajectory prediction in autonomous driving.