40 citations · 42 across the 2 of their papers we have counts for
7 papers
Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection
Nguyen Anh Minh Mai, Pierre Duthon, Louahdi Khoudour +2
The ability to accurately detect and localize objects is recognized as being the most important for the perception of self-driving cars. From 2D to 3D object detection, the most di…
A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera
Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour +3
We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In…
Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks
Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil +2
Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing…
Motorcycle Classification in Urban Scenarios using Convolutional Neural Networks for Feature Extraction
Jorge E. Espinosa, Sergio A. Velastin, John W. Branch
This paper presents a motorcycle classification system for urban scenarios using Convolutional Neural Network (CNN). Significant results on image classification has been achieved u…
Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN
Jorge E. Espinosa, Sergio A. Velastin, John W. Branch
This paper introduces a Deep Learning Convolutional Neural Network model based on Faster-RCNN for motorcycle detection and classification on urban environments. The model is evalua…
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
Huy Hieu Pham, Louahdi Khoudour, Alain Crouzil +2
We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, h…