Dr. Shaowu Peng Profile

Dr. Shaowu Peng

at South China Univ of Technology

SPIE Involvement:

Author

Publications (6)

Proceedings Article | 7 March 2024 Paper

An improved depth reconstruction method for unstable illumination environments in endoscopic surgeries

Shaowu Peng, Zeqi Li

Proceedings Volume 13087, 1308707 (2024) https://doi.org/10.1117/12.3005340

KEYWORDS: Light sources and illumination, Endoscopy, Surgery, Light sources, Endoscopes, 3D modeling, Quantization, Laparoscopy, Feature extraction, Equipment

Read Abstract +

Proceedings Article | 7 March 2024 Paper

A cross-level semantic aggregation segmentation method in aquatic scenes

Shaowu Peng, Kuncheng Huang, Qiong Liu

Proceedings Volume 13086, 130860P (2024) https://doi.org/10.1117/12.3005349

KEYWORDS: Semantics, Feature fusion, Image segmentation, Correlation coefficients, Environmental monitoring, Feature extraction, Object detection, Ablation

Read Abstract +

Semantic segmentation in aquatic scenes is key technology water environment monitoring. Small-scale object detection and segmentation in aquatic scenes are major challenges in semantic segmentation of water bodies. Current typical semantic segmentation methods often use multi-scale feature fusion operations, features of different scales from different network layers are aggregated, enabling the features to have both strong semantic representation from high-level features and strong feature detail expression capability from low-level features. However, current methods, although they focus on the details of small-scale objects, primarily rely on low-level features to determine the presence of objects in the network scale adaptation for small object detection, resulting in the loss of accuracy when using high-level semantic features for prediction. Moreover, cross-scale fusion does not depend on category characteristics. Therefore, existing methods are not ideal for semantic-constrained small object segmentation, such as water surface garbage and plant debris. Our method focuses on the cross-level semantic information aggregation and utilization for object segmentation in aquatic scenes, providing a new approach for small object segmentation in complex semantic environments. In aquatic scenes, the category of objects has strong contextual relevance. Therefore, this paper proposes a cross-level semantic aggregation network to address the problem of small object segmentation in aquatic scenes. The cross-level semantic aggregation method guides the high-level features to perform semantic aggregation using low-level features, enabling the aggregation of features with high-level semantic features of the same category as small objects, while introducing relevant contextual scene features of different categories. Compared to traditional scale fusion, this introduces a new aggregation method within the semantic framework to handle small object segmentation in complex contextual relationships. We conducted extensive experiments on our self-built water body scene dataset, ColorWater, and the public dataset Aeroscapes. In addition to achieving state-of-the-art performance in overall segmentation, we particularly achieved significant advantages in small object categories such as floating garbage on the water surface and plant debris, which are the focus of this paper.

Proceedings Article | 7 March 2024 Paper

Towards object-level semantic RGB-D SLAM in dynamic environments

Shaowu Peng, Dongchang Li

Proceedings Volume 13085, 130850M (2024) https://doi.org/10.1117/12.3005385

KEYWORDS: Semantics, Object detection, Pose estimation, 3D tracking, Optical flow, Visualization, Optical tracking, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 14 February 2020 Paper

Far-infrared pedestrian sequence segmentation based on time domain semantics

Shaowu Peng, Zhenju Wang, Qiong Liu, Junying Chen

Proceedings Volume 11428, 114280R (2020) https://doi.org/10.1117/12.2539449

KEYWORDS: Image segmentation, Far infrared, Roads, Image processing algorithms and systems, Statistical modeling, Infrared imaging

Read Abstract +

Proceedings Article | 14 February 2020 Paper

Real-time semantics based plane object tracking for augmented reality

Shaowu Peng, Ju Chen, Honggang Guan, Ruojing Huang, Shichao Ou

Proceedings Volume 11430, 114301B (2020) https://doi.org/10.1117/12.2539327

KEYWORDS: Augmented reality, Cameras, Target detection, Image fusion, Automatic tracking

Read Abstract +

Proceedings Article | 2 December 2011 Paper

Object recognition based on spatial active basis template

Shaowu Peng, Jingcheng Xu

Proceedings Volume 8004, 80040V (2011) https://doi.org/10.1117/12.902012

KEYWORDS: Wavelets, Object recognition, Image classification, Associative arrays, Feature extraction, Visualization, Detection and tracking algorithms, Machine learning, Image segmentation, Software engineering

Read Abstract +

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years