41 citations
- Mercedes-Benz (Germany)DE5 papers
- University of OxfordGB5 papers
- California Institute of TechnologyUS3 papers
- University of ManchesterGB3 papers
- Baden-Wuerttemberg Cooperative State UniversityDE2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Rhodes UniversityZA2 papers
- TH Bingen University of Applied SciencesDE2 papers
- University of FreiburgDE2 papers
- University of StuttgartDE2 papers
- Arizona State UniversityUS1 paper
- Brandenburg University of Technology Cottbus-SenftenbergDE1 paper
4 papers · 1 filter
Neural Rendering for Sensor Adaptation in 3D Object Detection
Felix Embacher, David Holtz, Jonas Uhrig +2
Autonomous vehicles often have varying camera sensor setups, which is inevitable due to restricted placement options for different vehicle types. Training a perception model on one…
Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Framework
Christian Alexander Holz, Christian Bader, Markus Enzweiler +1
We present a modular, production-ready approach that integrates compact Neural Network (NN) into a Kalmanfilter-based Multi-Object Tracking (MOT) pipeline. We design three tiny tas…
StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection
Marcel Vosshans, Omar Ait-Aider, Youcef Mezouar +1
In this work, we present a novel approach for general object segmentation from a monocular image, eliminating the need for manually labeled training data and enabling rapid, straig…
S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations
Simon Doll, Niklas Hanselmann, Lukas Schneider +3
Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches i…