Ahmet Oğuz Saltık

Ahmet Oğuz Saltık

Auto-generated profile, based on publicly available information

Ahmet Oğuz Saltık

University of Hohenheim

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2023 in Agricultural and Forest Meteorology
Verified
Journal Article
Closed access
MBMalte von Bloh
Malte von Bloh
RJRogério de S. Nóia Júnior
Rogério de S. Nóia Júnior
XWXaver Wangerpohl
Xaver Wangerpohl
ASAhmet Oğuz Saltık
Ahmet Oğuz Saltık
VHVivian Haller
Vivian Haller
SASenthold Asseng
Senthold Asseng

12 May 2025
Verified
Book Chapter
Open access
PDF file
ASAhmet Oğuz Saltık
Ahmet Oğuz Saltık
AAAlicia Allmendinger
Alicia Allmendinger
ASAnthony Stein
Anthony Stein
This paper presents a comprehensive evaluation of state-of-the-art object detection models, including YOLOv9, YOLOv10, and RT-DETR, for the task of weed detection in smart-spraying applications focusing on three classes: Sugarbeet, Monocot, and Dicot. The performance of these models is compared based on mean Average Precision (mAP) scores and inference times on different GPU and CPU devices. We consider various model variations, such as nano, small, medium, large alongside different image resolutions (320px, 480px, 640px, 800px, 960px). The results highlight the trade-offs between inference time and detection accuracy, providing valuable insights for selecting the most suitable model for real-time weed detection. This study aims to guide the development of efficient and effective smart spraying systems, enhancing agricultural productivity through precise weed management.


26 February 2026 in Journal of Systems Architecture
Verified
Journal Article
Open access
SMSourav Modak
Sourav Modak
ASAhmet Oğuz Saltık
Ahmet Oğuz Saltık
ASAnthony Stein
Anthony Stein

16 July 2025 in arXiv
Verified
Preprint
Open access
PDF file
ASAhmet Oğuz Saltık
Ahmet Oğuz Saltık
MVMax Voigt
Max Voigt
SMSourav Modak
Sourav Modak
MBMike Beckworth
Mike Beckworth
ASAnthony Stein
Anthony Stein
Weed detection is a critical component of precision agriculture, facilitating targeted herbicide application and reducing environmental impact. However, deploying accurate object detection models on resource-limited platforms remains challenging, particularly when differentiating visually similar weed species commonly encountered in plant phenotyping applications. In this work, we investigate Channel-wise Knowledge Distillation (CWD) and Masked Generative Distillation (MGD) to enhance the performance of lightweight models for real-time smart spraying systems. Utilizing YOLO11x as the teacher model and YOLO11n as both reference and student, both CWD and MGD effectively transfer knowledge from the teacher to the student model. Our experiments, conducted on a real-world dataset comprising sugar beet crops and four weed types (Cirsium, Convolvulus, Fallopia, and Echinochloa), consistently show increased AP50 across all classes. The distilled CWD student model achieves a notable improvement of 2.5% and MGD achieves 1.9% in mAP50 over the baseline without increasing model complexity. Additionally, we validate real-time deployment feasibility by evaluating the student YOLO11n model on Jetson Orin Nano and Raspberry Pi 5 embedded devices, performing five independent runs to evaluate performance stability across random seeds. These findings confirm CWD and MGD as an effective, efficient, and practical approach for improving deep learning-based weed detection accuracy in precision agriculture and plant phenotyping scenarios.

4 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
SMSourav Modak
Sourav Modak
ASAhmet Oğuz Saltık
Ahmet Oğuz Saltık
ASAnthony Stein
Anthony Stein
Deep learning-based weed control systems often suffer from limited training data diversity and constrained on-board computation, impacting their real-world performance. To overcome these challenges, we propose a framework that leverages Stable Diffusion-based inpainting to augment training data progressively in 10% increments -- up to an additional 200%, thus enhancing both the volume and diversity of samples. Our approach is evaluated on two state-of-the-art object detection models, YOLO11(l) and RT-DETR(l), using the mAP50 metric to assess detection performance. We explore quantization strategies (FP16 and INT8) for both the generative inpainting and detection models to strike a balance between inference speed and accuracy. Deployment of the downstream models on the Jetson Orin Nano demonstrates the practical viability of our framework in resource-constrained environments, ultimately improving detection accuracy and computational efficiency in intelligent weed management systems.