MULHAM FAWAKHERJI

Dottore di ricerca

ciclo: XXXIV


supervisore: Daniele Nardi

Titolo della tesi: Deep Learning On Imagery In Precision Agriculture

Artificial Intelligence (AI) is a key tool in agriculture for implementing sustainable strategies for weed control. In traditional weed control, the agrochemical inputs are uniformly applied to the field, while innovative approaches using AI aim at minimizing the usage of chemical inputs, thanks to local applications. Therefore, An effective perception system is a fundamental component for farming robots, as it enables them to properly perceive the surrounding environment and to carry out targeted operations. In this thesis, we focus on agricultural robotics systems that address the weeding problem by means of selective spraying or mechanical removal of the detected weeds. We present a set of deep learning methods designed to enable a robot to efficiently perform an accurate weed/crop classification from RGB or RGB+NIR (Near Infrared) images and overcome the current limitation in the state-of-the-art approaches. In particular, we present the following contributions: - Two novel pipelines for crops/weeds segmentation that simplify and accelerate the training process as well as improve generalization to different kinds of crops properties with minimal labeling effort. - An approach that uses multichannel deep feature learning to make segmentation more robust to changes in the environment. - A novel methodology that exploits a reduced encoder-decoder segmentation network to efficiently estimate crop and weed local statistics for setups with limited resources, like small UAVs (Unmanned Aerial Vehicles). - A novel approach for multi-spectral synthetic data generation based on conditional generative adversarial network, designed to overcome the augmentation problem of unbalancing crop/weed datasets. Quantitative experimental results are obtained using multiple publicly available datasets to demonstrate the effectiveness of the proposed approaches. Moreover, assessing the generalization capability, of the proposed solutions, we present two implementations in different challenging tasks. In the first one, we study the effect of multi-channel deep feature learning on medical images segmentation specifically on oral squamous cell carcinoma cancer. The second study concerns grape cluster segmentation, precisely implementing the target class augmentation approach trying to balance the data distribution and diversity among the target class. A further important outcome of this thesis was a set of open-source software modules and datasets, which I hope will be useful to the research community.

Produzione scientifica

11573/1665050 - 2023 - Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data
Ciarfuglia, Thomas A.; Motoi, Ionut M.; Saraceni, Leonardo; Fawakherji, Mulham; Sanfeliu, Alberto; Nardi, Daniele - 01a Articolo in rivista
rivista: COMPUTERS AND ELECTRONICS IN AGRICULTURE (Elsevier BV:PO Box 211, 1000 AE Amsterdam Netherlands:011 31 20 4853757, 011 31 20 4853642, 011 31 20 4853641, EMAIL: nlinfo-f@elsevier.nl, INTERNET: http://www.elsevier.nl, Fax: 011 31 20 4853598) pp. - - issn: 0168-1699 - wos: WOS:000976573900001 (6) - scopus: 2-s2.0-85146434282 (11)

11573/1678148 - 2021 - Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming
Fawakherji, M.; Potena, C.; Pretto, A.; Bloisi, D. D.; Nardi, D. - 01a Articolo in rivista
rivista: ROBOTICS AND AUTONOMOUS SYSTEMS (Elsevier BV:PO Box 211, 1000 AE Amsterdam Netherlands:011 31 20 4853757, 011 31 20 4853642, 011 31 20 4853641, EMAIL: nlinfo-f@elsevier.nl, INTERNET: http://www.elsevier.nl, Fax: 011 31 20 4853598) pp. - - issn: 0921-8890 - wos: WOS:000702779200004 (24) - scopus: 2-s2.0-85114121190 (34)

11573/1487860 - 2020 - Data Augmentation Using GANs for Crop/Weed Segmentation in Precision Farming
Fawakherji, M.; Potena, C.; Prevedello, I.; Pretto, A.; Bloisi, D. D.; Nardi, D. - 04b Atto di convegno in volume
congresso: 4th IEEE Conference on Control Technology and Applications, CCTA 2020 (Virtual, Online)
libro: CCTA 2020 - 4th IEEE Conference on Control Technology and Applications - (978-1-7281-7140-1)

11573/1609132 - 2020 - Crop and Weed Classication Using Pixel-wise Segmentation on Ground and Aerial Images
Fawakherji, Mulham; Youssef, Ali; Bloisi, Domenico D.; Pretto, Alberto; Nardi, Daniele - 01a Articolo in rivista
rivista: INTERNATIONAL JOURNAL OF ROBOTIC COMPUTING (Newport Beach CA: KS Press, 2019- Institute for Semantic Computing Foundation.) pp. 39-57 - issn: 2641-9521 - wos: (0) - scopus: (0)

11573/1487858 - 2020 - Deep learning-based pixel-wise lesion segmentation on oral squamous cell carcinoma images
Martino, F.; Bloisi, D. D.; Pennisi, A.; Fawakherji, M.; Ilardi, G.; Russo, D.; Nardi, D.; Staibano, S.; Merolla, F. - 01a Articolo in rivista
rivista: APPLIED SCIENCES (Basel: MDPI AG, 2011-) pp. 1-14 - issn: 2076-3417 - wos: WOS:000594871500001 (15) - scopus: 2-s2.0-85096394211 (24)

11573/1382499 - 2019 - On Field Gesture-Based Robot-to-Robot Communication with NAO Soccer Players
Di Giambattista, V.; Fawakherji, M.; Suriani, V.; Bloisi, D. D.; Nardi, D. - 04b Atto di convegno in volume
congresso: 23rd Annual RoboCup International Symposium, RoboCup 2019 (Sydney; Australia)
libro: RoboCup 2019: Robot World Cup XXIII - (978-3-030-35698-9; 978-3-030-35699-6)

11573/1320635 - 2019 - UAV image based crop and weed distribution estimation on embedded GPU boards
Fawakherji, Mulham; Potena, C.; Bloisi, D. D.; Imperoli, M.; Pretto, A.; Nardi, D. - 04b Atto di convegno in volume
congresso: 1st Workshop on Deep-learning based Computer Vision for UAV, DL-UAV 2019, and 1st Workshop on Visual Computing and Machine Learning for Biomedical Applications, ViMaBi 2019 held at the 18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019 (Salerno; Italy)
libro: Computer Analysis of Images and Patterns - (978-3-030-29929-3; 978-3-030-29930-9)

11573/1261462 - 2019 - Crop and Weeds Classification for Precision Agriculture Using Context-Independent Pixel-Wise Segmentation
Fawakherji, Mulham; Youssef, Ali; Bloisi, Domenico; Pretto, Alberto; Nardi, Daniele - 04b Atto di convegno in volume
congresso: 3rd IEEE International Conference on Robotic Computing, IRC 2019 (Napoli; Italy)
libro: 2019 Third IEEE International Conference on Robotic Computing (IRC) - (9781538692455)

11573/1609160 - 2019 - Robotics for Precision Agriculture @DIAG
Potena, Ciro; Fawakherji, Mulham; Carlos, Carbone; Imperoli, Marco; Nardi, Daniele; Pretto, Alberto - 04b Atto di convegno in volume
congresso: Italian Conference on Robotics and Intelligent Machines(I-RIM), (Rome, Italy)
libro: Robotics for Precision Agriculture @DIAG - ()

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma