Flow chart of the sample preparation process. حسب Fang Zheng (54278)

"…At the end of the freeze-thaw cycle (FTC), the deformation of the saline soil increased with the decrease of the cold end temperature, and the alternating time between heat and cold did not produce significant changes in the deformation of the saline soil. …"

Particle size curve. حسب Fang Zheng (54278)

"…At the end of the freeze-thaw cycle (FTC), the deformation of the saline soil increased with the decrease of the cold end temperature, and the alternating time between heat and cold did not produce significant changes in the deformation of the saline soil. …"

Compaction curve. حسب Fang Zheng (54278)

"…At the end of the freeze-thaw cycle (FTC), the deformation of the saline soil increased with the decrease of the cold end temperature, and the alternating time between heat and cold did not produce significant changes in the deformation of the saline soil. …"

Quantitative results on WEDU dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Counting results on DRPD dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Quantitative results on RFRB dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Main module structure. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Counting results on MTDC-UAV dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Quantitative results on DRPD dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Architecture of MAR-YOLOv9. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Quantitative results on MTDC-UAV dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Counting results on WEDU dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Example images from four plant datasets. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Counting results on RFRB dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Detection visualization results on WEDU dataset. حسب Dunlu Lu (19964225)

"…This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. …"

Mean parameter values for the selected crops. حسب Gourab Saha (8987405)

"…<div><p>As the world population is increasing day by day, so is the need for more advanced automated precision agriculture to meet the increasing demands for food while decreasing labor work and saving water for crops. …"

Performance comparison of ML models. حسب Gourab Saha (8987405)

"…<div><p>As the world population is increasing day by day, so is the need for more advanced automated precision agriculture to meet the increasing demands for food while decreasing labor work and saving water for crops. …"

Comparative data of different soil samples. حسب Gourab Saha (8987405)

"…<div><p>As the world population is increasing day by day, so is the need for more advanced automated precision agriculture to meet the increasing demands for food while decreasing labor work and saving water for crops. …"

Confusion matrix of random forest model. حسب Gourab Saha (8987405)

"…<div><p>As the world population is increasing day by day, so is the need for more advanced automated precision agriculture to meet the increasing demands for food while decreasing labor work and saving water for crops. …"

Sensor value scenario for fuzzy logic algorithm. حسب Gourab Saha (8987405)

"…<div><p>As the world population is increasing day by day, so is the need for more advanced automated precision agriculture to meet the increasing demands for food while decreasing labor work and saving water for crops. …"