Now showing items 1-14 of 14

    • A new relational geometric feature for human action recognition 

      Vinagre Ruiz, Manuel; Aranda López, Juan; Casals Gelpi, Alicia (Springer, 2015-01)
      Article
      Restricted access - publisher's policy
      Pose-based features have demonstrated to outperform low-levelappearance features in human action recognition. New RGB-D cameras provide locations of human joints with which geometric correspondences can be easily calculated. ...
    • A trajectory-driven 3D channel model for human activity recognition 

      Abdelgawwad, Ahmed Abdelmonem; Català Mallofré, Andreu; Pätzold, Matthias (Institute of Electrical and Electronics Engineers (IEEE), 2021-07-28)
      Article
      Open Access
      This paper concerns the design, analysis, and simulation of a 3D non-stationary channel model fed with inertial measurement unit (IMU) data. The work in this paper provides a framework for simulating the micro-Doppler ...
    • Activity recognition using wearable sensors in people with neuromuscular impairments 

      Siliato Robles, Cecilia (Universitat Politècnica de Catalunya / Universitat de Barcelona, 2020-06)
      Master thesis
      Restricted access - author's decision
      This TFM focus on the development of algorithms to analyze the arm activity measured with wearable sensors. The main objective is to provide a feedback to specialists about arm usage in people with neuromuscular impairments ...
    • BoVDW: Bag-of-Visual-and-Depth-Words for gesture recognition 

      Hernandez Vela, Antonio; Bautista, Miguel Angel; Perez-Sala, Xavier; Ponce, Víctor; Baró, Xavier; Pujol, Oriol; Angulo Bahón, Cecilio; Escalera, Sergio (2012)
      Conference report
      Restricted access - publisher's policy
      We present a Bag-of-Visual-and-Depth-Words (BoVDW) model for gesture recognition, an extension of the Bag-of-Visual-Words (BoVW) model, that benefits from the multimodal fusion of visual and depth features. State-of-the-art ...
    • Detección de transiciones posturales basado en un acelerómetro y un sensor de presión mediante algoritmos de aprendizaje automático 

      Pilataxi Pilataxi, Jhon Ivan (Universitat Politècnica de Catalunya, 2019-01-31)
      Master thesis
      Restricted access - author's decision
      [CASTELLÀ] Los sensores inerciales basados en Sistemas Micro Electro Mecánicos, gracias a su reducido tamaño y bajo consumo de energía, han permitido el desarrollo de sistemas portables orientados al reconocimiento de ...
    • Disseny d'un algorisme per l'avaluació de l'activitat física i l'intensitat de l'exercici basat en l'Smartphone 

      Carbonés Fargas, Bernat (Universitat Politècnica de Catalunya, 2014-07-23)
      Bachelor thesis
      Open Access
      [ANGLÈS] The designed algorithm allows non-intrusive physical activity recognition using accelerometer data from the smartphone. Fourteen subjects of the same age (mean = 22 years) have used the Android application RSAF ...
    • Energy efficient smartphone-based activity recognition using fixed-point arithmetic 

      Anguita, Davide; Ghio, Alessandro; Oneto, Luca; Llanas Parra, Francesc Xavier; Reyes Ortiz, Jorge Luis (2013)
      Article
      Open Access
      In this paper we propose a novel energy efficient approach for the recognition of human activities using smartphones as wearable sensing devices, targeting assisted living applications such as remote patient activity ...
    • Human action recognition by means of subtensor projections and dense trajectories 

      Carmona Leyva, José María; Climent Vilaró, Joan (2018-09)
      Article
      Open Access
      In last years, most human action recognition works have used dense trajectories features, to achieve state-of-the-art results. Histograms of Oriented Gradients (HOG), Histogram of Optical Flow (HOF) and Motion Boundary ...
    • Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine 

      Anguita, Davide; Ghio, Alessandro; Oneto, Luca; Llanas Parra, Francesc Xavier; Reyes Ortiz, Jorge Luis (Springer, 2012)
      Conference report
      Open Access
      Activity-Based Computing aims to capture the state of the user and its environment by exploiting heterogeneous sensors in order to provide adaptation to exogenous computing resources. When these sensors are attached to the ...
    • Posture transition analysis with barometers: contribution to accelerometer-based algorithms 

      Rodríguez Martín, Daniel Manuel; Samà Monsonís, Albert; Pérez López, Carlos; Català Mallofré, Andreu; Cabestany Moncusí, Joan (2018-10-15)
      Article
      Restricted access - publisher's policy
      Posture transitions are one of the most mechanically demanding tasks and are useful to evaluate the motor status of patients with motor impairments, frail individuals or the elderly, among others. So far, wearable inertial ...
    • Robust multi-dimensional motion features for first-person vision activity recognition 

      Abebe, Girmaw; Cavallaro, Andrea; Llanas Parra, Francesc Xavier (2016-08)
      Article
      Open Access
      We propose robust multi-dimensional motion features for human activity recognition from first-person videos. The proposed features encode information about motion magnitude, direction and variation, and combine them with ...
    • Training computationally efficient smartphone–based human activity recognition models 

      Anguita, Davide; Ghio, Alessandro; Oneto, Luca; Llanas Parra, Francesc Xavier; Reyes Ortiz, Jorge Luis (2013)
      Conference report
      Restricted access - publisher's policy
      The exploitation of smartphones for Human Activity Recognition (HAR) has been an active research area in which the development of fast and efficient Machine Learning approaches is crucial for preserving battery life and ...
    • Using conventional cell phones to recognize basic physical movements 

      Tormashova, Oxana (Universitat Politècnica de Catalunya, 2012-07-24)
      Master thesis
      Open Access
      [ANGLÈS] Human activity recognition system via wearable sensors can provide valuable information about person's life-style and can help to monitor human activities in order to improve person's interaction with environment. ...
    • WiWeHAR: multimodal human activity recognition using Wi-Fi and wearable sensing modalities 

      Muaaz, Muhammad; Chelli, Ali; Abdelgawwad, Ahmed Abdelmonem; Català Mallofré, Andreu; Pätzold, Matthias (Institute of Electrical and Electronics Engineers (IEEE), 2020-09-21)
      Article
      Open Access
      Robust and accurate human activity recognition (HAR) systems are essential to many human-centric services within active assisted living and healthcare facilities. Traditional HAR systems mostly leverage a single sensing ...