Authors :
Praneeth Yennamaneni; Vickram R; Samyak Sabannawar; SreePriya Naroju; Bharani Kumar Depuru
Volume/Issue :
Volume 8 - 2023, Issue 11 - November
Google Scholar :
https://tinyurl.com/yjm8scpz
Scribd :
https://tinyurl.com/3nyx42we
DOI :
https://doi.org/10.5281/zenodo.10276587
Abstract :
This research paper tackles the challenges
associated with manual pallet counting within industrial
environments and explores the integration of deep
learning techniques to enhance operational efficiency.
YOLOv8, recognized as a leading object detection
algorithm, serves as the foundational framework for this
study.
The initial phase involved the extensive collection of
images and videos from diverse warehouse settings to
curate a comprehensive dataset, instrumental for
training and refining the YOLOv8 model. Dataset
annotation was meticulously carried out utilising the
Roboflow platform. Subsequently, the YOLOv8 model
was trained with the custom dataset, achieving an
impressive average precision of (insert percentage). The
optimal model weights were meticulously saved,
facilitating deployment in real-world scenarios.
To extend the practicality of this research, the
model was seamlessly integrated into a user-friendly web
application powered by Flask, enhancing the
accessibility of this technology. The implementation of
the model yielded substantial enhancements in efficiency,
substantially mitigating the occurrence of operational
errors within warehouse management.
This study underscores the remarkable potential of
deep learning algorithms, not only within the realm of
warehouse management but also in a broad spectrum of
real-world applications. The implications of this research
extend beyond the domain of pallet counting, illustrating
the transformative impact of advanced technology in
streamlining industrial processes and contributing to the
broader landscape of automation and optimization.
In conclusion, the successful integration of
YOLOv8 in this context underscores the transformative
power of deep learning, promising ground-breaking
solutions for enhanced efficiency and precision in
various operational domains.
Keywords :
Manual Pallet Counting, YOLOv8, Deep Learning Techniques, Warehouse Management, Object Detection, Operational Efficiency, Roboflow.
This research paper tackles the challenges
associated with manual pallet counting within industrial
environments and explores the integration of deep
learning techniques to enhance operational efficiency.
YOLOv8, recognized as a leading object detection
algorithm, serves as the foundational framework for this
study.
The initial phase involved the extensive collection of
images and videos from diverse warehouse settings to
curate a comprehensive dataset, instrumental for
training and refining the YOLOv8 model. Dataset
annotation was meticulously carried out utilising the
Roboflow platform. Subsequently, the YOLOv8 model
was trained with the custom dataset, achieving an
impressive average precision of (insert percentage). The
optimal model weights were meticulously saved,
facilitating deployment in real-world scenarios.
To extend the practicality of this research, the
model was seamlessly integrated into a user-friendly web
application powered by Flask, enhancing the
accessibility of this technology. The implementation of
the model yielded substantial enhancements in efficiency,
substantially mitigating the occurrence of operational
errors within warehouse management.
This study underscores the remarkable potential of
deep learning algorithms, not only within the realm of
warehouse management but also in a broad spectrum of
real-world applications. The implications of this research
extend beyond the domain of pallet counting, illustrating
the transformative impact of advanced technology in
streamlining industrial processes and contributing to the
broader landscape of automation and optimization.
In conclusion, the successful integration of
YOLOv8 in this context underscores the transformative
power of deep learning, promising ground-breaking
solutions for enhanced efficiency and precision in
various operational domains.
Keywords :
Manual Pallet Counting, YOLOv8, Deep Learning Techniques, Warehouse Management, Object Detection, Operational Efficiency, Roboflow.