Computational Intelligence and Deep Learning for Human Motion Modelling and Analysis
2020 IEEE World Congress on Computational Intelligence (IEEE WCCI 2020, IJCNN)
July 19 – 24, 2020, Glasgow (UK)
Aim and Scope
Deep learning has a significant impact in many areas of Artificial Intelligence (AI), particularly in fundamental tasks such as object detection, tracking, segmentation, classification, and prediction. Features extracted from deep neural networks can be used to build complex applications applying computer vision, image and text processing techniques that are also integral to human motion modelling and analysis (HMMA).
This special session focuses on the application of deep learning and computational intelligence supporting global population who aspire to lead a more active life, improve sport performance, reduce rehabilitation times, and maintain quality of life and wellbeing at older age. Applications may include augmented coaching systems, motion capturing and processing technologies, immersive/augmented reality and ways of enhancing environments where various movement activities occur. Data collections while preserving privacy and diagnostic value for computer models to generate useful feedback are important to sport participants, exergame users and healthcare providers. We encourage paper submissions regarding machine-generated information such as: motion diagnostics, predicting the outcome of activity and recommending interventions and game strategy.
This special session aims to bring together academics and multidisciplinary experts collaborating in the field of computational sports science, sport analytics, rehabilitation and all those interested in technology supporting health benefits of active life.
The main topics of this special session include, but are not limited to the following:
- Human motion modelling and analysis (HMMA)
- Deep learning applications and architectures for HMMA
- Supervised, semi-supervised and unsupervised learning for HMMA, computational sport science and sport analytics
- Knowledge discovery and feature processing techniques for HMMA
- Urban planning, (re)shaping cities and infrastructures in support of a healthy lifestyle, life quality, and active life benefits
- Augmented coaching systems and technology (ACST) e.g. technology for improving coaching practice, human performance, and techniques
- Data-driven game strategy information and visualisation
- Data preprocessing for coaching analytics: safety aspects with performance and privacy diagnostics
- Augmented feedback and visualisation e.g. via near-real time in 2D, 3D, portable computing devices or via Augmented/Immersive Reality (AR/IR)
- Advancement of wearable or sport-equipment technology
- Advancement of motion assistive technology (e.g. intelligent prosthetics and rehabilitation devices)
- Monocular, multi-camera and depth video processing for HMMA including integration with mobile, portable and low-cost consumer devices
- 2D and 3D markerless pose estimation for human body and sport equipment tracking
- Activity monitoring and quantification of movement patterns. Case studies on:
- Video and sensor data fusion for HMMA
- Biomechanics parameters and raw data processing from video, wearable and mobile devices
- Producing replay indexing and interaction e.g. via speech or gesture recognition, smartwatch, mobile or other devices
- Enhancing media coverage e.g. penalty shooting ball trajectory information in soccer/football, scene and game pattern detection from video.
- Motion pattern detection and indexing from video and sensor signals
- Near real-time movement pattern detection and recognition from kinematic and kinetic data sources
- Case studies involving safety and privacy preservation, rehabilitation, exergames, sport or active life contexts including restricted, private or public environments where human motion activities occur
- Movement outcome prediction and cues extraction (e.g. tennis serve, or baseball pitching)
- Balance pattern modelling and analysis related to movement pathomechanics including fall prediction and detection
- Exergames for regaining stability, control, motor skill, and technique adaptation
- Privacy preservation for augmented coaching, on-line data processing and health/elderly care
- Technology-mediated challenges in post-surgery and brain or neuro-motor damage rehabilitation contexts (e.g. providing near-real time diagnostics)
- Open-source software tools and case studies including:
- Deep learning applications for ACST and Computational Sport Science
- Coaching, sport analytics and human motion analysis
- Data analysis, modelling and development tools.
- Brain computer interfaces, EEG, EMG signal processing and modelling for HMMA.
Special session organisers
- Dr. Boris Bačić, Auckland University of Technology, New Zealand
- Dr. Nabin Sharma, University of Technology Sydney, NSW, Australia
- Dr. Muhammad Saqib, University of Technology Sydney, NSW, Australia
Papers should be submitted through the WCCI’s IJCNN paper submission portal. After logging into the submission system, you need to choose Special Session on “Computational Intelligence and Deep Learning for Human Motion Modelling and Analysis”. Authors are encouraged to share links to collected data sets used in their papers.
We look forward to receiving your high-quality submissions.