Mamadou Dian Bah
Mamadou Dian Bah has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Adel Hafiane
University d’Orléans
3 shared publications - Raphael Canals
Universit dOrlans, PRISME UR 4229, Orlans, Centre Val de Loire, France
3 shared publications Adel Hafiane
PRISME EA 4229, INSA Centre Val de Loire
2 shared publications- Mohamed Dahmane
Computer Research Institute of Montreal- CRIM, Vision Research Department, Montreal, Canada
2 shared publications - Rajjeshwar Ganguly
CRIM - Computer Research Institute of Montréal
2 shared publications Raphael Canals
PRISME EA 4229, University of Orleans
2 shared publications
Latest Publications
- 4 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Détection des adventices par imagerie aérienne
Dans le contexte agricole actuel, il est nécessaire de réduire l’utilisation des produits phytosanitaires contre les mauvaises herbes. Le désherbage localisé présente une alternative prometteuse pour limiter les coûts et l’impact environnemental. Cependant, la localisation automatique des adventices n’est pas une tâche facile car elle présente plusieurs défis scientifiques et technologiques. L’objectif de cette thèse est de proposer des méthodes de traitement d’images et d’intelligence artificielle pour la localisation des adventices en grandes cultures. Dans ce cadre, nous avons abordé deux problématiques, la détection des rangées de culture et la détection des adventices. Deux méthodes ont été proposées pour la détection des rangées de culture. La première méthode combine la transformée de Hough et l’algorithme de regroupement linéaire itératif SLIC. La deuxième, quant à elle, utilise une approche totalement nouvelle basée sur l’apprentissage profond. Ces deux méthodes ont été utilisées pour détecter les adventices inter-rang et celles qui sont en contact avec les rangées de culture. Pour tendre vers une meilleur efficacité, deux nouvelles méthodes de détection d’adventices par apprentissage machine, entièrement automatiques ont été développées. L’originalité de ces méthodes est que l’apprentissage est effectué sur des données annotées automatiquement. La première méthode est basée sur l’apprentissage profond tandis que la seconde génère des modèles à partir de descripteurs profonds et un classifieur à classe unique. Les résultats obtenus sur des données réelles montrent l’intérêt des approches proposées.
- 4 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Détection des adventices par imagerie aérienne
Dans le contexte agricole actuel, il est nécessaire de réduire l’utilisation des produits phytosanitaires contre les mauvaises herbes. Le désherbage localisé présente une alternative prometteuse pour limiter les coûts et l’impact environnemental. Cependant, la localisation automatique des adventices n’est pas une tâche facile car elle présente plusieurs défis scientifiques et technologiques. L’objectif de cette thèse est de proposer des méthodes de traitement d’images et d’intelligence artificielle pour la localisation des adventices en grandes cultures. Dans ce cadre, nous avons abordé deux problématiques, la détection des rangées de culture et la détection des adventices. Deux méthodes ont été proposées pour la détection des rangées de culture. La première méthode combine la transformée de Hough et l’algorithme de regroupement linéaire itératif SLIC. La deuxième, quant à elle, utilise une approche totalement nouvelle basée sur l’apprentissage profond. Ces deux méthodes ont été utilisées pour détecter les adventices inter-rang et celles qui sont en contact avec les rangées de culture. Pour tendre vers une meilleur efficacité, deux nouvelles méthodes de détection d’adventices par apprentissage machine, entièrement automatiques ont été développées. L’originalité de ces méthodes est que l’apprentissage est effectué sur des données annotées automatiquement. La première méthode est basée sur l’apprentissage profond tandis que la seconde génère des modèles à partir de descripteurs profonds et un classifieur à classe unique. Les résultats obtenus sur des données réelles montrent l’intérêt des approches proposées.
- 2 January 2026
- Published by Springer Nature
- p. 365-376
RowFormer: Multiple Class-Token-Based Vision Transformer for 2D Context-Aware Attention
- 2 January 2026
- Published by Springer Nature
- p. 365-376
RowFormer: Multiple Class-Token-Based Vision Transformer for 2D Context-Aware Attention
- 4 December 2024
- Published by Springer Nature
- p. 228-241
Diffusion Models as a Representation Learner for Deepfake Image Detection
- 4 December 2024
- Published by Springer Nature
- p. 228-241
Diffusion Models as a Representation Learner for Deepfake Image Detection
- 30 December 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 216
Hierarchical graph representation for unsupervised crop row detection in images
- 30 December 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 216
Hierarchical graph representation for unsupervised crop row detection in images
- Open Access
- 19 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 5189-5200
CRowNet: Deep Network for Crop Row Detection in UAV Images
- 19 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 5189-5200
Open AccessCRowNet: Deep Network for Crop Row Detection in UAV Images
- Open Access
- 2 November 2018
- Published by Springer Nature
- p. 176-187
Deep Learning Based Classification System for Identifying Weeds Using High-Resolution UAV Imagery
- 2 November 2018
- Published by Springer Nature
- p. 176-187
Open AccessDeep Learning Based Classification System for Identifying Weeds Using High-Resolution UAV Imagery
- Top Cited PapersOpen Access
- 26 October 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (11) , 1690
Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images
In recent years, weeds have been responsible for most agricultural yield losses. To deal with this threat, farmers resort to spraying the fields uniformly with herbicides. This method not only requires huge quantities of herbicides but impacts the environment and human health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, unmanned aerial vehicles (UAVs) are becoming an interesting acquisition system for weed localization and management due to their ability to obtain images of the entire agricultural field with a very high spatial resolution and at a low cost. However, despite significant advances in UAV acquisition systems, the automatic detection of weeds remains a challenging problem because of their strong similarity to the crops. Recently, a deep learning approach has shown impressive results in different complex classification problems. However, this approach needs a certain amount of training data, and creating large agricultural datasets with pixel-level annotations by an expert is an extremely time-consuming task. In this paper, we propose a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images. The proposed method comprises three main phases. First, we automatically detect the crop rows and use them to identify the inter-row weeds. In the second phase, inter-row weeds are used to constitute the training dataset. Finally, we perform CNNs on this dataset to build a model able to detect the crop and the weeds in the images. The results obtained are comparable to those of traditional supervised training data labeling, with differences in accuracy of 1.5% in the spinach field and 6% in the bean field.
- 26 October 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (11) , 1690
Top Cited PapersOpen AccessDeep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images
In recent years, weeds have been responsible for most agricultural yield losses. To deal with this threat, farmers resort to spraying the fields uniformly with herbicides. This method not only requires huge quantities of herbicides but impacts the environment and human health. One way to reduce the cost and environmental impact is to allocate the right doses of herbicide to the right place and at the right time (precision agriculture). Nowadays, unmanned aerial vehicles (UAVs) are becoming an interesting acquisition system for weed localization and management due to their ability to obtain images of the entire agricultural field with a very high spatial resolution and at a low cost. However, despite significant advances in UAV acquisition systems, the automatic detection of weeds remains a challenging problem because of their strong similarity to the crops. Recently, a deep learning approach has shown impressive results in different complex classification problems. However, this approach needs a certain amount of training data, and creating large agricultural datasets with pixel-level annotations by an expert is an extremely time-consuming task. In this paper, we propose a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images. The proposed method comprises three main phases. First, we automatically detect the crop rows and use them to identify the inter-row weeds. In the second phase, inter-row weeds are used to constitute the training dataset. Finally, we perform CNNs on this dataset to build a model able to detect the crop and the weeds in the images. The results obtained are comparable to those of traditional supervised training data labeling, with differences in accuracy of 1.5% in the spinach field and 6% in the bean field.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Weeds detection in UAV imagery using SLIC and the hough transform
Traditional weeds controlling tended to be spraying herbicides in all the fields. Such method not only requires huge quantities of herbicides but impact environment and humans health. In this paper, we propose a new method of crop/weeds discrimination using imagery provided by an unmanned aerial vehicle (UAV). This method is based on the vegetation skeleton, the Hough transform and the spatial relationship of superpixels created by the simple linear iterative clustering (SLIC). The combination of the spatial relationship of superpixels and their positions in the detected crop lines allows to detect intraline weeds. Our method shows its robustness in presence of weed patches close to crop lines as well as for the detection of crop lines as for weed detection.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Weeds detection in UAV imagery using SLIC and the hough transform
Traditional weeds controlling tended to be spraying herbicides in all the fields. Such method not only requires huge quantities of herbicides but impact environment and humans health. In this paper, we propose a new method of crop/weeds discrimination using imagery provided by an unmanned aerial vehicle (UAV). This method is based on the vegetation skeleton, the Hough transform and the spatial relationship of superpixels created by the simple linear iterative clustering (SLIC). The combination of the spatial relationship of superpixels and their positions in the detected crop lines allows to detect intraline weeds. Our method shows its robustness in presence of weed patches close to crop lines as well as for the detection of crop lines as for weed detection.