Table 1 Historical origins of prominent object detection models.
From: Advancing e-waste classification with customizable YOLO based deep learning models
Model | Origin | Description | Applications |
|---|---|---|---|
CNN-Based Models | CNN-based models have proven to be effective at identifying and classifying e-waste components | Identification and classification of e-waste | |
TensorFlow API | Huang et al.6 | Google’s open-source framework supports the entire object detection model development cycle | Object detection and e-waste detection are understudied |
YOLO | Redmon et al.7 | The original YOLO model, designed for real-time object detection, laid the groundwork for subsequent versions with faster and more accurate detection | Real-time object detection and e-waste detection are understudied |
YOLOv5 | Bochkovskiy et al.8 | An improved version of the YOLO model focuses on enhancing performance and scalability via architectural changes | Real-time object detection and e-waste detection are understudied |
YOLOv7 | Advancements such as Feature Pyramid Networks and additional residual blocks were introduced to improve real-time object detection | Real-time object detection and e-waste detection are understudied | |
YOLOv8 | YOLOv8 is a cutting-edge object detection algorithm known for its speed and accuracy. It has been used in many applications, such as self-driving cars, security cameras, and medical imaging | Pose estimation, object detection, and instance segmentation; e-waste detection is understudied |
