Paper für CVSports @ CVPR 2023 akzeptiert

Das Paper mit dem Titel "All Keypoints You Need: Detecting Arbitrary Keypoints on the Body of Triple, High, and Long Jump Athletes" von Katja Ludwig, Julian Lorenz, Robin Schön and Rainer Lienhart wurde beim 9th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2023 akzeptiert. In diesem Paper beschreiben die Autoren, wie man beliebige Schlüsselpunkte auf dem Körper von Drei-, Weit- und Hochsprung-Athlet*innen erkennen kann. Dazu werden bisherige Methoden um die Detektion auf Händen, Füßen, Köpfen, Ellbögen und Knien erweitert. Unterschiedliche Methoden zur Repräsentation des Kopfs und für den Netzwerk-Input werden im Paper evaluiert.

Abstract

Performance analyses based on videos are commonly used by coaches of athletes in various sports disciplines. In individual sports, these analyses mainly comprise the body posture. This paper focuses on the disciplines of triple, high, and long jump, which require fine-grained locations of the athlete's body. Typical human pose estimation datasets provide only a very limited set of keypoints, which is not sufficient in this case. Therefore, we propose a method to detect arbitrary keypoints on the whole body of the athlete by leveraging the limited set of annotated keypoints and auto-generated segmentation masks of body parts. Evaluations show that our model is capable of detecting keypoints on the head, torso, hands, feet, arms, and legs, including also bent elbows and knees. We analyze and compare different techniques to encode desired keypoints as the model's input and their embedding for the Transformer backbone.

Referenz

Katja Ludwig, Julian Lorenz, Robin Schön and Rainer Lienhart. 2023. All keypoints you need: detecting arbitrary keypoints on the body of triple, high, and long jump athletes. DOI: 10.1109/CVPRW59228.2023.00546
PDF | BibTeX | RIS | DOI

Suche