Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis

TL;DR

This paper introduces new datasets and a deep learning model, SYD-Net, for fine-grained recognition of sports, yoga, and dance postures, achieving state-of-the-art accuracy and addressing a significant gap in benchmark datasets.

Contribution

The paper presents four new SYD datasets and a novel attention-based deep model, SYD-Net, for improved classification of complex sports, yoga, and dance postures.

Findings

SYD-Net achieves state-of-the-art accuracy on Yoga-82.

Proposed datasets fill a gap in fine-grained posture recognition.

Attention mechanism enhances feature discrimination.

Abstract

Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification task due to the complex movement of body parts. Deep Convolutional Neural Networks (CNNs) have attained significantly improved performance in solving various human body-pose estimation problems. Though decent progress has been achieved in yoga postures recognition using deep learning techniques, fine-grained sports, and dance recognition necessitates ample research attention. However, no benchmark public image dataset with sufficient inter-class and intra-class variations is available yet to address sports and dance postures classification. To solve this limitation, we have proposed two image datasets, one for 102 sport categories and another for 12 dance styles. Two public datasets, Yoga-82 which contains 82 classes and Yoga-107 represents 107 classes are collected for yoga postures. These four SYD datasets are experimented with the proposed deep model, SYD-Net, which integrates a patch-based attention (PbA) mechanism on top of standard backbone CNNs. The PbA module leverages the self-attention mechanism that learns contextual information from a set of uniform and multi-scale patches and emphasizes discriminative features to understand the semantic correlation among patches. Moreover, random erasing data augmentation is applied to improve performance. The proposed SYD-Net has achieved state-of-the-art accuracy on Yoga-82 using five base CNNs. SYD-Net's accuracy on other datasets is remarkable, implying its efficiency. Our Sports-102 and Dance-12 datasets are publicly available at https://sites.google.com/view/syd-net/home.