Timm Linder

Timm Linder

Auto-generated profile, based on publicly available information

Timm Linder

Robert Bosch GmbH, Corporate Research, Stuttgart, Germany

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
11 November 2020 in IEEE Transactions on Biometrics, Behavior, and Identity Science
Verified
Journal Article
Closed access
ISIstvan Sarandi
Istvan Sarandi
TLTimm Linder
Timm Linder
KAKai Oliver Arras
Kai Oliver Arras
BLBastian Leibe
Bastian Leibe
Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and Z to metric depth around the subject. To obtain metric-scale predictions, 2.5D methods need a separate post-processing step to resolve scale ambiguity. Further, they cannot localize body joints outside the image boundaries, leading to incomplete estimates for truncated images. To address these limitations, we propose metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are all defined in metric 3D space, instead of being aligned with image space. This reinterpretation of heatmap dimensions allows us to directly estimate complete, metric-scale poses without test-time knowledge of distance or relying on anthropometric heuristics, such as bone lengths. To further demonstrate the utility our representation, we present a differentiable combination of our 3D metric-scale heatmaps with 2D image-space ones to estimate absolute 3D pose (our MeTRAbs architecture). We find that supervision via absolute pose loss is crucial for accurate non-root-relative localization. Using a ResNet-50 backbone without further learned layers, we obtain state-of-the-art results on Human3.6M, MPI-INF-3DHP and MuPoTS-3D. Our code is publicly available.

11 May 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
LBLucas Beyer
Lucas Beyer
AHAlexander Hermans
Alexander Hermans
TLTimm Linder
Timm Linder
KAKai Oliver Arras
Kai Oliver Arras
BLBastian Leibe
Bastian Leibe
Detecting humans is a key skill for mobile robots and intelligent vehicles in a large variety of applications. While the problem is well studied for certain sensory modalities such as image data, few works exist that address this detection task using 2D range data. However, a widespread sensory setup for many mobile robots in service and domestic applications contains a horizontally mounted 2D laser scanner. Detecting people from 2D range data is challenging due to the speed and dynamics of human leg motion and the high levels of occlusion and self-occlusion particularly in crowds of people. While previous approaches mostly relied on handcrafted features, we recently developed the deep learning based wheelchair and walker detector DROW. In this paper, we show the generalization to people, including small modifications that significantly boost DROW's performance. Additionally, by providing a small, fully online temporal window in our network, we further boost our score. We extend the DROW dataset with person annotations, making this the largest dataset of person annotations in 2D range data, recorded during several days in a real-world environment with high diversity. Extensive experiments with three current baseline methods indicate it is a challenging dataset, on which our improved DROW detector beats the current state-of-the-art.

13 September 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ESElisa Stefanini
Elisa Stefanini
LPLuigi Palmieri
Luigi Palmieri
ARAndrey Rudenko
Andrey Rudenko
THTill Hielscher
Till Hielscher
TLTimm Linder
Timm Linder
LPLUCIA PALLOTTINO
LUCIA PALLOTTINO
With the goal of creating efficient human-aware robot navigation systems, we present a Context-aware Model Predictive Control (MPC) formulation designed specifically for dynamic and crowded environments. State-of-the-art approaches use mainly geometric information and predictions of human motion, thus being proactive about human positions and intents but less aware of high-level behaviors encoded in contextual cues of human activities. In contrast to that, we propose a holistic planning solution that considers additional contextual information such as 3D human body poses with their velocities and recognized activities. We carefully design the MPC formulation to facilitate the integration of modern perception systems and the usage of fast solvers for embedded robot motion optimization. Compared to a set of baselines, our proposed system not only ensures safety but also significantly improves task and computational efficiency. Through extensive simulations and real-life experiments, our planner demonstrates reliable operation in terms of smooth and efficient navigation in human-populated areas.

10 February 2016
Verified
Book Chapter
Closed access
PDF file
TLTimm Linder
Timm Linder
KAKai O. Arras
Kai O. Arras

11 August 2023 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Closed access
SMSergi Molina
Sergi Molina
AMAnna Mannucci
Anna Mannucci
MMMartin Magnusson
Martin Magnusson
DADaniel Adolfsson
Daniel Adolfsson
HAHenrik Andreasson
Henrik Andreasson
ALAchim J. Lilienthal
Achim J. Lilienthal
Current intralogistics services require keeping up with e-commerce demands, reducing delivery times and waste, and increasing overall flexibility. As a consequence, the use of automated guided vehicles (AGVs) and, more recently, autonomous mobile robots (AMRs) for logistics operations is steadily increasing.

29 August 2018 in arXiv
Verified
Preprint
Open access
PDF file
ISIstván Sárándi
István Sárándi
TLTimm Linder
Timm Linder
KAKai O. Arras
Kai O. Arras
BLBastian Leibe
Bastian Leibe
Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.