Dr. sc. comp. Kaspars Sudars

K.Sudars has been working at the EDI since 2006. He has received PhD in Computer Science from University of Latvia, Faculty of Computing and he is co-author of 19 SCOPUS scientific publications focusing on R&D in signal processing, deep learning and computer vision. Currently his scientific interests are covering explainable AI, semantic image segmentation and object detection in images. Also K.Sudars is co-founder at start-up company WeedBot dedicated to AI based weeding for delicate crops.

Scopus Author ID 24512667900

Recent projects

• Automotive Intelligence for/at Connected Shared Mobility (AI4CSM) #H2020
• Artifical intelligence for more precise diagnostics (AI4DIAG) #ESIF
• Development of a robotic weed management equipment (RONIN) #ESIF
• Pētījums par datorredzes paņēmienu attīstību industrijas procesu norises automatizācijai (DIPA) #ESIF
• Cyber-physical systems, ontologies and biophotonics for safe&smart city and society (VPP SOPHIS) #SRP (VPP)
• Cyber-physical systems, ontologies and biophotonics for safe&smart city and society (GUDPILS) #SRP (VPP)
• Smart non-contact phenotyping of raspberries and quinces using machine learning methods, hyperspectral and 3D images (AKFen) #SRP (VPP)
• Programmable Systems for Intelligence in Automobiles (PRYSTINE) #H2020
• A Deep Learning Approach for Osteoporosis Identification using Cone-beam Computed Tomography (OSTAK) #H2020
• New technology to produce hydrogen from Renewable Energy Sources based on AI with optimized costs for environmental applications (HydroG(re)EnergY-Env) #H2020

Recent publications

• Sudars, K., Jasko, J., Namatevs I., Ozola L., Badaukis, N. (2020). Dataset of annotated food crops and weed images for robotic computer vision control, Data in Brief, 31. doi:10.1016/j.dib.2020.105833
• Namatevs, I., Sudars, K., Polaka, I., Automatic data labeling by neural networks for the counting of objects in videos, Procedia Computer Science, Vol.149, pp. 151-158, 2019
• Sudars, Kaspars, Ivars Namatēvs, and Kaspars Ozols. 2022. "Improving Performance of the PRYSTINE Traffic Sign Classification by Using a Perturbation-Based Explainability Approach" Journal of Imaging 8, no. 2: 30. https://doi.org/10.3390/jimaging8020030
• Vitalijs Komasilovs, Aleksejs Zacepins, Armands Kviesis, Kaspars Ozols, Artūrs Ņikuļins, Kaspars Sudars “Development of an MCTS Model for Hydrogen Production Optimisation”, Processes (2023) (pp.16). https://www.mdpi.com/2227-9717/11/7/1977.
• Ivars Namatēvs, Kaspars Sudars, Artis Dobrājs. Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models.
• Edīte Kaufmane, Kaspars Sudars, Ivars Namatēvs, Ieva Kalniņa, Jānis Judvaitis, Rihards Balašs, Sarmīte Strautiņa. QuinceSet: Dataset of annotated Japanese quince images for object detection
• Kaspars Sudars, Ivars Namatevs, Arturs Nikulins, Rihards Balass, Astile Peter, Sarmite Strautina, Edite Kaufmane, Ieva Kalnina "Semantic Segmentation Using U-Net Deep Learning Network for Quince Phenotyping on RGB and HyperSpectral Images", 27th International Conference "Electronics" (2023). https://ieeexplore.ieee.org/document/10177638.
• Kaspars Sudars, Ivars Namatēvs, Jānis Judvaitis, Rihards Balašs, Artūrs Ņikuļins, Astile Peter, Sarmīte Strautiņa, Edīte Kaufmane, Ieva Kalniņa. YOLOv5 Deep Neural Network for Quince and Raspberry Detection on RGB Images