Deep orientation: Fast and Robust Upper Body orientation Estimation for Mobile Robotic Applications

Lewandowski, Benjamin; Seichter, Daniel; Wengefeld, Tim; Pfennig, Lennard; Drumm, Helge; Groß, Horst–Michael

doi:10.1109/iros40897.2019.8968506

Cited by 27 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison to other works, our approach outperforms [5] and it is -under good conditions-outperformed by [7]. Although [7] reports better results, it requires RGBD cameras, which are an order of magnitude more expensive than low-resolution RGB cameras.…”

Section: Discussionmentioning

confidence: 65%

“…Although there is a considerable number of exceptions (e.g., [5]- [7]) orientation and other social cues are usually acquired using a two-stage pipeline: human body parts are detected as a first step and then passed as input to a second stage algorithm. This second algorithm is frequently implemented using basic trigonometry, considering the coordinates of the shoulders or the hips [1].…”

Section: Introductionmentioning

confidence: 99%

“…In [5] RGBD HOGs were used to provide discrete angle estimations. The work presented in [7] uses RGBD and IR images with IR trackers to train a single-camera Convolutional Neural Network (CNN). Their model provides continuous angle estimation, achieving a mean absolute error close to 6 • .…”

Section: Introductionmentioning

confidence: 99%

“…Their model provides continuous angle estimation, achieving a mean absolute error close to 6 • . The accuracy of the work at hand for torso orientation is below that of [7]. However, this proposal does not only estimate the orientation but also the 3D coordinates of the torsos and it does not require the use of relatively expensive RGBD cameras.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-camera Torso Pose Estimation using Graph Neural Networks

Rodriguez-Criado

Bachiller

Bustos

et al. 2020

2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

Estimating the location and orientation of humans is an essential skill for service and assistive robots. To achieve a reliable estimation in a wide area such as an apartment, multiple RGBD cameras are frequently used. Firstly, these setups are relatively expensive. Secondly, they seldom perform an effective data fusion using the multiple camera sources at an early stage of the processing pipeline. Occlusions and partial views make this second point very relevant in these scenarios. The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125mm for the location and 10 • for the orientation using low-resolution RGB images. The experiments, conducted in an apartment with three cameras, benchmarked two different graph neural network implementations and a third architecture based on fully connected layers. The software used has been released as open-source in a public repository 1 .

show abstract

Section: Discussionmentioning

confidence: 65%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-camera Torso Pose Estimation using Graph Neural Networks

Rodriguez-Criado

Bachiller

Bustos

et al. 2020

2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

show abstract

“…Besides the position, the orientations of persons to be tracked and their postures (standing, sitting, squatting) are important information for making decisions during HRI. Therefore, the detected point cloud segments are further processed by a CNN to classify posture [24] and upper body orientation [27]. The observations of these properties are modeled as discrete distributions with three bins for the posture classes and eight bins for the orientation.…”

Section: Posture and Orientationmentioning

confidence: 99%

A Multi-Modal Person Perception Framework for Socially Interactive Mobile Service Robots

Müller

Wengefeld

Trinh

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

In order to meet the increasing demands of mobile service robot applications, a dedicated perception module is an essential requirement for the interaction with users in real-world scenarios. In particular, multi sensor fusion and human re-identification are recognized as active research fronts. Through this paper we contribute to the topic and present a modular detection and tracking system that models position and additional properties of persons in the surroundings of a mobile robot. The proposed system introduces a probability-based data association method that besides the position can incorporate face and color-based appearance features in order to realize a re-identification of persons when tracking gets interrupted. The system combines the results of various state-of-the-art image-based detection systems for person recognition, person identification and attribute estimation. This allows a stable estimate of a mobile robot’s user, even in complex, cluttered environments with long-lasting occlusions. In our benchmark, we introduce a new measure for tracking consistency and show the improvements when face and appearance-based re-identification are combined. The tracking system was applied in a real world application with a mobile rehabilitation assistant robot in a public hospital. The estimated states of persons are used for the user-centered navigation behaviors, e.g., guiding or approaching a person, but also for realizing a socially acceptable navigation in public environments.

show abstract