The principle of Partial Convolution. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Ablation experiments results of YOLOv5s. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Overall network architecture of FCMI-YOLO. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

The principle of MLCA mechanism. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Parameters of the dataset. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Comparison of mAP@0.5 for different ratios. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Primary training parameters for the model. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Distribution of the dataset. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Parameters of the FasterNext and C3. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Performance comparison of mainstream algorithms. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

System diagram. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Schematic diagram of Inner-IoU. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

Model train environment. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

The structure of FasterNext. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"

The structure of MLCA mechanism. حسب Junjie Lu (160350)

"…<div><p>The rapid development of Internet of Things (IoT) technology and deep learning has propelled the deployment of vision-based fire detection algorithms on edge devices, significantly exacerbating the trade-off between accuracy and inference speed under hardware resource constraints. …"