6 October 2023 in IEEE Transactions on Instrumentation and Measurement
Given the potential diminishment of semantic information caused by previous non-region-specific maximum or weighted intensity losses under different lighting conditions, we propose a novel high-level semantic perception fusion framework, termed Semantic Region Adaptive Fusion (SRAFusion). We establish a prioritized preservation scheme for high-level semantic information (HLSI), gradient information, and intensity information, ranked in descending order of priority. Based on this prioritization scheme and prior knowledge of semantic distribution in the source images, we construct a ground-truth for the fusion task. Specifically, we capture the HLSI distribution of the source images by utilizing two independent semantic segmentation networks. Subsequently, we introduce Semantic Region Decision Blocks (SRDB) to partition the original scene into region with bimodal HLSI, region with unimodal HLSI, and region lacking HLSI. We then design specific loss functions to constrain the aforementioned regions, facilitating the integration of complete semantic information. Furthermore, taking into account the susceptibility of the visible segmentation network to lighting conditions, we employ a two-stage training strategy involving coarse-tuning and fine-tuning. This method aims to optimize one-stage training strategy and achieve a more accurate region delineation. Finally, qualitative and quantitative experiments conducted on publicly available datasets such as MFNet , RoadScene , and TNO demonstrate the superiority of our SRAFusion over state-of-the-art methods. Our code will be available: https://github.com/WenziCao/SRAFusion.
10 April 2025 in Measurement Science and Technology
Structured light projection methods are widely used in three-dimensional (3D) shape measurement. However, overexposure on highly reflective surfaces results in the inaccurate acquisition of phase information, thereby severely degrading the performance of structured light-based 3D measurements. Traditional structured light techniques are only applicable to surfaces with favorable characteristics. In this paper, we propose a multi-scale exposure fusion method based on Weighted Guided Image Filtering integrated with structured light technology. This method fuses image sequences captured under different exposure times into a well-exposed image by combining the properly exposed regions from each image, effectively reducing brightness disparities on high-reflectivity surfaces. To evaluate the performance of the proposed approach, experiments were conducted on specimens with high reflectivity, including a steel rod and an aluminum plane. The experimental results indicate that, compared with other methods, our approach effectively handles both saturated and dark regions, reconstructing the 3D shape of the objects completely and accurately. Moreover, the proposed method also demonstrates excellent performance in high dynamic range scene reconstruction.