.png){kind=icon}
.png){kind=icon}
Return
High-Quality Salient Object Detection and Optimization Method Based on Optical Sensor Data
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2025.3592895.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Salient object detection (SOD) is critical for computer vision tasks such as image segmentation and object tracking. A key challenge in SOD is the effective representation of the semantic properties of objects. However, current saliency models have large network sizes and computational costs, resulting in saliency maps with issues such as blurriness, uneven brightness, and loss of edge details. In this article, we propose a new SOD and optimization method. First, we design an SOD network that includes a multiscale feature extraction (MSFE) module and a multilevel feature fusion (MLFF) module to achieve thorough integration of features from different levels and multiscale contextual information. Next, we perform exponential fusion between the generated saliency map and the saliency map produced by the dual-information progressive optimization network (DIPONet) model to enhance the completeness of object detection. Finally, we design an edge detection network that includes the comprehensive feature refinement loss (CFRL) function and propose a feasible edge-aware optimization module to obtain saliency maps with uniform brightness and smooth edges. We use the neural architecture search network (NASNet)-Mobile network as the backbone, which is pretrained on the ImageNet dataset. Experimental results on four challenging optical sensor datasets—SOD, pattern analysis, statical modeling and computational learning (PASCAL-S), dalian university of technology segmentation-test (DUTS-TE), and DUT-OMRON-demonstrate that our method outperforms other approaches.
Keywords:
Edge-aware optimization
exponential fusion
multilevel feature fusion (MLFF)
multiscale feature extraction (MSFE)
optical sensor data
salient object detection (SOD)