Simple But Effective: Upper-Body Geometric Features for Traffic Command Gesture Recognition

Wang, SiJia; Jiang, Kun; Chen, Junjie; Yang, Mengmeng; Fu, Zheng; Yang, Daoguo

doi:10.1109/thms.2021.3121649

Cited by 6 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For gesture recognition of police officers, related work processes camera image snippets [3] directly. Due to the advances in human body pose estimation [5,4], related approaches extract the body skeleton data from the images and perform gesture recognition on it [35,22,15]. For processing skeletons to predict the gesture, recurrent neural networks [35] or convolutional neural networks [22] are applied.…”

Section: Related Workmentioning

confidence: 99%

“…Due to the advances in human body pose estimation [5,4], related approaches extract the body skeleton data from the images and perform gesture recognition on it [35,22,15]. For processing skeletons to predict the gesture, recurrent neural networks [35] or convolutional neural networks [22] are applied. Besides the police officer gesture recognition, the actions of other human traffic participants like cyclists [40] or pedestrians [6] are also analyzed in literature.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

Holzbock,

Kern,

Waldschmidt

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adverse weather conditions, we also demonstrate promising performance when one of the sensors lacks functionality.

show abstract