Centre dedocumentation
scientifique

Pedestrian trajectory prediction with convolutional neural networks / Simone Zamboni in Pattern recognition, vol 121 (January 2022)  

Public [article]  inPattern recognition > vol 121 (January 2022) . - n° 108252 Titre : Pedestrian trajectory prediction with convolutional neural networks Type de document : Article/Communication Auteurs : Simone Zamboni, Auteur ; Zekarias Tilahun Kefato, Auteur ; Sarunas Girdzijauskas, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108252 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] distance euclidienne [Termes IGN] filtre de Gauss [Termes IGN] itinéraire piétionnier [Termes IGN] modèle de simulation [Termes IGN] navigation pédestre [Termes IGN] piéton [Termes IGN] prévision à court terme [Termes IGN] réseau social [Termes IGN] trajectoire Résumé : (auteur) Predicting the future trajectories of pedestrians is a challenging problem that has a range of application, from crowd surveillance to autonomous driving. In literature, methods to approach pedestrian trajectory prediction have evolved, transitioning from physics-based models to data-driven models based on recurrent neural networks. In this work, we propose a new approach to pedestrian trajectory prediction, with the introduction of a novel 2D convolutional model. This new model outperforms recurrent models, and it achieves state-of-the-art results on the ETH and TrajNet datasets. We also present an effective system to represent pedestrian positions and powerful data augmentation techniques, such as the addition of Gaussian noise and the use of random rotations, which can be applied to any model. As an additional exploratory analysis, we present experimental results on the inclusion of occupancy methods to model social information, which empirically show that these methods are ineffective in capturing social interaction. Numéro de notice : A2022-109 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.patcog.2021.108252 Date de publication en ligne : 13/08/2021 En ligne : https://doi.org/10.1016/j.patcog.2021.108252 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99615 [article]

Self-attention and generative adversarial networks for algae monitoring / Nhut Hai Huynh in European journal of remote sensing, vol 55 n° 1 (January 2022)  

Public [article]  inEuropean journal of remote sensing > vol 55 n° 1 (January 2022) . - pp 10 - 22 Titre : Self-attention and generative adversarial networks for algae monitoring Type de document : Article/Communication Auteurs : Nhut Hai Huynh, Auteur ; Gordon Boër, Auteur ; Hauke Schramm, Auteur Année de publication : 2022 Article en page(s) : pp 10 - 22 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algue [Termes IGN] analyse en composantes principales [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] image hyperspectrale [Termes IGN] plancton [Termes IGN] réseau antagoniste génératif [Termes IGN] réseau neuronal artificiel Résumé : (auteur) Water is important for the natural environment and human health. Monitoring algae concentrations yield information on the water quality. Compared with in situ measurements of water quality parameters, which are often complex and expensive, remote sensing techniques, using hyperspectral data analysis, are fast and cost-effective. The objectives of this study are (1) to estimate the algae concentrations from hyperspectral data using deep learning techniques, (2) to investigate the applicability of attention mechanisms in the analysis of hyperspectral data, and (3) to augment the training data using generative adversarial networks (GANs). The results show that the accuracy of deep learning techniques is 7.6% higher than that of simpler artificial neural networks. Compared to noise injection and principal component analysis-based data augmentation, the use of a GAN-based data augmentation method significantly improves the accuracy of algae concentration estimates (>5%). In addition, models with added attention mechanisms yield an on average 3.13% higher accuracy than those without attention techniques. This result demonstrates the improvement of spectral features of artificial hyperspectral data based on the self-attention approach, revealing the potential of attention techniques in hyperspectral remote sensing. Numéro de notice : A2022-097 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : https://doi.org/10.1080/22797254.2021.2010605 Date de publication en ligne : 02/01/2022 En ligne : https://doi.org/10.1080/22797254.2021.2010605 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99547 [article]

Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles / Nico Lang in Remote sensing of environment, vol 268 (January 2022)  

Public [article]  inRemote sensing of environment > vol 268 (January 2022) . - n* 112760 Titre : Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles Type de document : Article/Communication Auteurs : Nico Lang, Auteur ; Nicolai Kalischek, Auteur ; John Armston, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n* 112760 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] biomasse aérienne [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] estimation bayesienne [Termes IGN] forme d'onde [Termes IGN] Global Ecosystem Dynamics Investigation lidar [Termes IGN] modèle numérique de surface de la canopée [Termes IGN] semis de points Résumé : (auteur) NASA's Global Ecosystem Dynamics Investigation (GEDI) is a key climate mission whose goal is to advance our understanding of the role of forests in the global carbon cycle. While GEDI is the first space-based LIDAR explicitly optimized to measure vertical forest structure predictive of aboveground biomass, the accurate interpretation of this vast amount of waveform data across the broad range of observational and environmental conditions is challenging. Here, we present a novel supervised machine learning approach to interpret GEDI waveforms and regress canopy top height globally. We propose a probabilistic deep learning approach based on an ensemble of deep convolutional neural networks (CNN) to avoid the explicit modelling of unknown effects, such as atmospheric noise. The model learns to extract robust features that generalize to unseen geographical regions and, in addition, yields reliable estimates of predictive uncertainty. Ultimately, the global canopy top height estimates produced by our model have an expected RMSE of 2.7 m with low bias. Numéro de notice : A2022-086 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112760 Date de publication en ligne : 03/11/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112760 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99495 [article]

MLMT-CNN for object detection and segmentation in multi-layer and multi-spectral images / Majedaldein Almahasneh in Machine Vision and Applications, vol 33 n° 1 (January 2022)  

Public [article]  inMachine Vision and Applications > vol 33 n° 1 (January 2022) . - n° 9 Titre : MLMT-CNN for object detection and segmentation in multi-layer and multi-spectral images Type de document : Article/Communication Auteurs : Majedaldein Almahasneh, Auteur ; Adeline Paiement, Auteur ; Xianghua Xie, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 9 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] atmosphère solaire [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couche thématique [Termes IGN] détection d'objet [Termes IGN] image multibande [Termes IGN] segmentation d'image Résumé : (auteur) Precisely localising solar Active Regions (AR) from multi-spectral images is a challenging but important task in understanding solar activity and its influence on space weather. A main challenge comes from each modality capturing a different location of the 3D objects, as opposed to typical multi-spectral imaging scenarios where all image bands observe the same scene. Thus, we refer to this special multi-spectral scenario as multi-layer. We present a multi-task deep learning framework that exploits the dependencies between image bands to produce 3D AR localisation (segmentation and detection) where different image bands (and physical locations) have their own set of results. Furthermore, to address the difficulty of producing dense AR annotations for training supervised machine learning (ML) algorithms, we adapt a training strategy based on weak labels (i.e. bounding boxes) in a recursive manner. We compare our detection and segmentation stages against baseline approaches for solar image analysis (multi-channel coronal hole detection, SPOCA for ARs) and state-of-the-art deep learning methods (Faster RCNN, U-Net). Additionally, both detection and segmentation stages are quantitatively validated on artificially created data of similar spatial configurations made from annotated multi-modal magnetic resonance images. Our framework achieves an average of 0.72 IoU (segmentation) and 0.90 F1 score (detection) across all modalities, comparing to the best performing baseline methods with scores of 0.53 and 0.58, respectively, on the artificial dataset, and 0.84 F1 score in the AR detection task comparing to baseline of 0.82 F1 score. Our segmentation results are qualitatively validated by an expert on real ARs. Numéro de notice : A2022-089 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01261-y Date de publication en ligne : 29/11/2021 En ligne : https://doi.org/10.1007/s00138-021-01261-y Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99500 [article]

Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea / Yang Xu in Computers, Environment and Urban Systems, vol 92 (March 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 92 (March 2022) Titre : Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea Type de document : Article/Communication Auteurs : Yang Xu, Auteur ; Dan Zou, Auteur ; Sangwon Park, Auteur ; et al., Auteur Année de publication : 2022 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] chaîne de Markov [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] Corée du sud [Termes IGN] durée de déplacement [Termes IGN] mobilité [Termes IGN] modèle de simulation [Termes IGN] prévision à court terme [Termes IGN] téléphone intelligent [Termes IGN] téléphonie mobile [Termes IGN] tourisme [Termes IGN] voyage Résumé : (auteur) The abilities to predict tourist movements are critical to many urban applications, such as travel recommendations, targeted advertising, and infrastructure planning. Despite its importance, our understanding on the movement predictability of urban tourists and visitors is still limited, partially due to difficulties in accessing large scale mobility observations. In this study, we aim to bridge this gap by analyzing a nationwide mobile phone dataset. The dataset captures movement traces of a large number of international travelers who visited South Korea in 2018. By introducing two prediction models, one being Markov chain and the other with a recurrent neural network architecture, we assess how well travelers’ movements can be predicted under different model settings, and examine how predictability relates to travelers’ length of stay and activeness in travel patterns. Since travelers’ destination choices are quite diverse in South Korea, this enables us to further investigate the geographic variation of the models’ performance. Results show that the Markov chain model achieves an overall accuracy between 33.4% (@Acc1 metric) and 64.2% (@Acc5 metric), compared to 41.9% (@Acc1) and 67.7% (@Acc5) for the recurrent neural network model. The prediction capabilities of both models are largely unequal across individuals, with active travelers being more predictable in general. There is a notable geographic variation in the models’ performance, meaning that travelers’ movements are more predictable in some cities, but less in others. We believe this study represents a new effort in portraying the movement predictability of urban tourists and visitors. The analytical framework can be applied to assist tourism planning and service deployment in cities. Numéro de notice : A2022-085 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2021.101753 Date de publication en ligne : 06/01/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2021.101753 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99490 [article]

Classification of mediterranean shrub species from UAV point clouds / Juan Pedro Carbonell-Rivera in Remote sensing, vol 14 n° 1 (January-1 2022)  

Permalink

Detection of windthrown tree stems on UAV-orthomosaics using U-Net convolutional networks / Stefan Reder in Remote sensing, vol 14 n° 1 (January-1 2022)  

Permalink

A GIS-based landslide susceptibility mapping and variable importance analysis using artificial intelligent training-based methods / Pengxiang Zhao in Remote sensing, vol 14 n° 1 (January-1 2022)  

Permalink

An internal-external optimized convolutional neural network for arbitrary orientated object detection from optical remote sensing images / Sihang Zhang in Geo-spatial Information Science, vol 24 n° 4 (December 2021)  

Permalink

Deep image translation with an affinity-based change prior for unsupervised multimodal change detection / Luigi Tommaso Luppino in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)  

Permalink

A novel unmixing-based hypersharpening method via convolutional neural network / Xiaochen Lu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)  

Permalink

Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+ / Zhimin Wang in Computers & geosciences, vol 158 (January 2022)  

Permalink

Efficient occluded road extraction from high-resolution remote sensing imagery / Dejun Feng in Remote sensing, vol 13 n° 24 (December-2 2021)  

Permalink

VGI3D: an interactive and low-cost solution for 3D building modelling from street-level VGI images / Chaoquan Zhang in Journal of Geovisualization and Spatial Analysis, vol 5 n° 2 (December 2021)  

Permalink

Automatic extraction of indoor spatial information from floor plan image: A patch-based deep learning methodology application on large-scale complex buildings / Hyunjung Kim in ISPRS International journal of geo-information, vol 10 n° 12 (December 2021)  

Permalink