Search Results for author: Guillaume-Alexandre Bilodeau

Found 36 papers, 18 papers with code

CenterPoly: real-time instance segmentation using bounding polygons

1 code implementation19 Aug 2021 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier

The models were trained and evaluated on Cityscapes, KITTI and IDD and the results are reported on their public benchmark, which are state-of-the-art at real-time speeds.

Real-time Instance Segmentation Semantic Segmentation

MeNToS: Tracklets Association with a Space-Time Memory Network

no code implementations15 Jul 2021 Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier

We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection.

Instance Segmentation Multi-Object Tracking +5

Multiple Convolutional Features in Siamese Networks for Object Tracking

1 code implementation1 Mar 2021 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed.

Object Tracking

MFST: Multi-Features Siamese Tracker

1 code implementation1 Mar 2021 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

Based on this advanced feature representation, our algorithm achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers.

Local Anomaly Detection in Videos using Object-Centric Adversarial Learning

no code implementations13 Nov 2020 Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud

We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos.

Anomaly Detection

A Grid-based Representation for Human Action Recognition

no code implementations17 Oct 2020 Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier

Human action recognition (HAR) in videos is a fundamental research topic in computer vision.

Action Recognition

An Empirical Analysis of Visual Features for Multiple Object Tracking in Urban Scenes

1 code implementation15 Oct 2020 Mehdi Miah, Justine Pepin, Nicolas Saunier, Guillaume-Alexandre Bilodeau

Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features.

Multiple Object Tracking

Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification

no code implementations30 Jul 2020 Yacine Khraimeche, Guillaume-Alexandre Bilodeau, David Steele, Harshad Mahadik

Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain.

Domain Adaptive Person Re-Identification Person Re-Identification +1

Domain Siamese CNNs for Sparse Multispectral Disparity Estimation

no code implementations30 Apr 2020 David-Alexandre Beaupre, Guillaume-Alexandre Bilodeau

Multispectral disparity estimation is a difficult task for many reasons: it has all the same challenges as traditional visible-visible disparity estimation (occlusions, repetitive patterns, textureless surfaces), in addition of having very few common visual information between images (e. g. color information vs. thermal information).

Disparity Estimation

Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study

no code implementations30 Mar 2020 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework.

Multiple Object Tracking

Tracking Road Users using Constraint Programming

no code implementations10 Mar 2020 Alexandre Pineault, Guillaume-Alexandre Bilodeau, Gilles Pesant

Because our focus is on the data association problem, our MOT method only uses simple image features, which are the center position and color of detections for each frame.

Multiple Object Tracking

SpotNet: Self-Attention Multi-Task Network for Object Detection

1 code implementation13 Feb 2020 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier

We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas.

Instance Segmentation Multi-Task Learning +1

Tracking in Urban Traffic Scenes from Background Subtraction and Object Detection

no code implementations15 May 2019 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we propose to combine detections from background subtraction and from a multiclass object detector for multiple object tracking (MOT) in urban traffic scenes.

Multiple Object Tracking Object Detection +1

Road User Detection in Videos

1 code implementation28 Mar 2019 Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Pierre Gravel

Two new models, RetinaNet-Double and RetinaNet-Flow, are proposed, based respectively on the concatenation of a target frame with a preceding frame, and the concatenation of the optical flow with the target frame.

Video Object Detection

Online Mutual Foreground Segmentation for Multispectral Stereo Videos

1 code implementation8 Sep 2018 Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin

The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications.

Multiple Object Tracking in Urban Traffic Scenes with a Multiclass Object Detector

no code implementations6 Sep 2018 Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier, David-Alexandre Beaupré

Multiple object tracking (MOT) in urban traffic aims to produce the trajectories of the different road users that move across the field of view with different directions and speeds and that can have varying appearances and sizes.

General Classification Multiple Object Tracking

Road User Abnormal Trajectory Detection using a Deep Autoencoder

1 code implementation25 Aug 2018 Pankaj Raj Roy, Guillaume-Alexandre Bilodeau

In this paper, we focus on the development of a method that detects abnormal trajectories of road users at traffic intersections.

Outlier Detection

Multi-Branch Siamese Networks with Online Selection for Object Tracking

no code implementations22 Aug 2018 Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir

In this paper, we propose a robust object tracking algorithm based on a branch selection mechanism to choose the most efficient object representations from multi-branch siamese networks.

Object Tracking

Improving Multiple Object Tracking with Optical Flow and Edge Preprocessing

no code implementations29 Jan 2018 David-Alexandre Beaupré, Guillaume-Alexandre Bilodeau, Nicolas Saunier

In this paper, we present a new method for detecting road users in an urban environment which leads to an improvement in multiple object tracking.

Multiple Object Tracking Object Detection +1

From Superpixel to Human Shape Modelling for Carried Object Detection

no code implementations10 Jan 2018 Farnoosh Ghadiri, Robert Bergevin, Guillaume-Alexandre Bilodeau

We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales.

Object Detection

Domain-Specific Face Synthesis for Video Face Recognition from a Single Sample Per Person

1 code implementation6 Jan 2018 Fania Mokhayeri, Eric Granger, Guillaume-Alexandre Bilodeau

A compact set of synthetic faces is generated that resemble individuals of interest under the capture conditions relevant to the OD.

3D Reconstruction Face Generation +1

Evaluation of trackers for Pan-Tilt-Zoom Scenarios

no code implementations12 Nov 2017 Yucao Tang, Guillaume-Alexandre Bilodeau

Compared to tracking with a still camera, the images captured with a PTZ camera are highly dynamic in nature because the camera can perform large motion resulting in quickly changing capture conditions.

Robust Face Tracking using Multiple Appearance Models and Graph Relational Learning

1 code implementation29 Jun 2017 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios.

Relational Reasoning

Discriminative conditional restricted Boltzmann machine for discrete choice and latent variable modelling

no code implementations1 Jun 2017 Melvin Wong, Bilal Farooq, Guillaume-Alexandre Bilodeau

Our findings show that through non-parametric statistical tests, we can extract useful latent information on the behaviour of latent constructs through machine learning methods and present strong and significant influence on the choice process.

Tracking using Numerous Anchor points

1 code implementation7 Feb 2017 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur.

Object Localization Visual Tracking

SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking

no code implementations23 Oct 2016 François-Xavier Derue, Guillaume-Alexandre Bilodeau, Robert Bergevin

In visual tracking, part-based trackers are attractive since they are robust against occlusion and deformation.

Visual Tracking

Reproducible Evaluation of Pan-Tilt-Zoom Tracking

no code implementations18 May 2015 Gengjie Chen, Pierre-Luc St-Charles, Wassim Bouachir, Thomas Joeisseint, Guillaume-Alexandre Bilodeau, Robert Bergevin

Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in computer vision for many years.

Automatic Image Registration in Infrared-Visible Videos using Polygon Vertices

no code implementations17 Mar 2014 Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger

To achieve a global affine transformation that maximises the overlapping of infrared and visible foreground pixels, the matched keypoints of each local shape polygon are stored temporally in a buffer for a few number of frames.

Affine Transformation Image Registration

A Bag of Words Approach for Semantic Segmentation of Monitored Scenes

no code implementations14 May 2013 Wassim Bouachir, Atousa Torabi, Guillaume-Alexandre Bilodeau, Pascal Blais

This paper proposes a semantic segmentation method for outdoor scenes captured by a surveillance camera.

Semantic Segmentation

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