Search Results for author: Robert Laganiere

Found 10 papers, 3 papers with code

Sampling Strategies for Real-Time Action Recognition

no code implementations CVPR 2013 Feng Shi, Emil Petriu, Robert Laganiere

We present a real-time action recognition system which integrates fast random sampling method with local spatio-temporal features extracted from a Local Part Model.

Action Recognition Computational Efficiency +1

Gradient Boundary Histograms for Action Recognition

no code implementations3 Dec 2014 Feng Shi, Robert Laganiere, Emil Petriu

This paper introduces a high efficient local spatiotemporal descriptor, called gradient boundary histograms (GBH).

Action Recognition Temporal Action Localization

Multi-scale prediction for robust hand detection and classification

no code implementations23 Apr 2018 Ding Lu, Yong Wang, Robert Laganiere, Xinbin Luo, Shan Fu

In this paper, we present a multi-scale Fully Convolutional Networks (MSP-RFCN) to robustly detect and classify human hands under various challenging conditions.

Classification General Classification +1

Deep Open Space Segmentation using Automotive Radar

no code implementations18 Mar 2020 Farzan Erlik Nowruzi, Dhanvin Kolhatkar, Prince Kapoor, Fahed Al Hassanat, Elnaz Jahani Heravi, Robert Laganiere, Julien Rebut, Waqas Malik

In this work, we propose the use of radar with advanced deep segmentation models to identify open space in parking scenarios.

RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users

1 code implementation2 May 2021 Ao Zhang, Farzan Erlik Nowruzi, Robert Laganiere

In this paper, we collect a novel radar dataset that contains radar data in the form of Range-Azimuth-Doppler tensors along with the bounding boxes on the tensor for dynamic road users, category labels, and 2D bounding boxes on the Cartesian Bird-Eye-View range map.

object-detection Object Detection +1

T-FFTRadNet: Object Detection with Swin Vision Transformers from Raw ADC Radar Signals

1 code implementation29 Mar 2023 James Giroux, Martin Bouchard, Robert Laganiere

Object detection utilizing Frequency Modulated Continous Wave radar is becoming increasingly popular in the field of autonomous systems.

Object object-detection +2

What You See Is What You Detect: Towards better Object Densification in 3D detection

1 code implementation27 Oct 2023 Tianran Liu, Zeping Zhang, Morteza Mousa Pasandi, Robert Laganiere

Considering that our approach focuses only on the visible part of the foreground objects to achieve accurate 3D detection, we named our method What You See Is What You Detect (WYSIWYD).

Depth Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.