Work

Using convolutional neural networks for image semantic segmentation and object detection

Year: 2024

Type: article

Abstract: Convolutional neural networks are widely used for feature extraction in the fields of object detection and image segmentation. However, traditional CNN models often struggle to ensure accuracy in high noise environments. A study proposes an enhanced CNN model to improve its ability to recognize targets of different scales. This model combines multi-scale perceptual aggregation and feature alignment (MPAFA) mechanisms. This new method effectively combines low-level and high-level features, which helps to better identify objects of different sizes. The experimental results show that the proposed model achieved a segmentation accuracy of 99.6 % on the Cityscapes dataset, and maintained an accuracy of 97.3 % even with increased noise. Further experiments have shown that the model outperforms existing methods in terms of accuracy and recall. The experimental results show that the model exhibits excellent performance in object detection and segmentation tasks. This study provides a more effective strategy for processing complex images by optimizing network structure and enhancing feature fusion.

Source: Systems and Soft Computing

DOI: 10.1016/j.sasc.2024.200172

Authors: Shuangmei Li, Chengning Huang

Institution: Pujiang Institute

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,500

Funders: Natural Science Foundation of Jiangsu Province, Nanjing Tech University