Izvorni znanstveni članak
https://doi.org/10.20532/cit.2023.1005740
An Innovative Deep Learning Approach for Image Semantic and Instance Segmentation
Chuangchuang Chen
; School of Network Engineering, Zhoukou Normal University, Zhoukou, Henan, China
*
Guang Gao
; School of Network Engineering, Zhoukou Normal University, Zhoukou, Henan, China
Linlin Liu
; School of Network Engineering, Zhoukou Normal University, Zhoukou, Henan, China
Yangyang Qiao
; School of Information Engineering, Zhengzhou Technology and Business University, Zhengzhou, China
* Autor za dopisivanje.
Sažetak
In this study, we propose a segmentation model based on convolutional neural networks (CNNs) to address image segmentation challenges in computer vision. Prior to designing the model, the activation function and other modules of the convolutional neural network were optimized to meet specific requirements. The segmentation task was transformed into binary classification problem to simplify network calculations and improve efficiency. Additionally, the model utilized a mask map obtained from the semantic segmentation model to aid in instance segmentation. Class activation technology was introduced to extract feature mapping maps. The corresponding thermal maps were obtained to achieve target instance segmentation. To further validate the effectiveness of the segmentation model, simulation experiments were conducted on semantic segmentation and instance segmentation respectively. The results show that the accuracy of the basic semantic segmentation model reached 87.58%, while the average accuracy of the entire class of the optimized instance segmentation model reached 97.9%. Therefore, the research and design of image segmentation models demonstrate high accuracy and good robustness.
Ključne riječi
CNN; Full Supervision; Image Segmentation; Thermal Diagram; Global Pooling
Hrčak ID:
317266
URI
Datum izdavanja:
4.4.2024.
Posjeta: 43 *