Boran Wang

Boran Wang

Auto-generated profile, based on publicly available information

Boran Wang

College of Artificial Intelligence Nankai University 300350 Tianjin China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 December 2024
Verified
Book Chapter
Closed access
PDF file
YCYishuo Chen
Yishuo Chen
BWBoran Wang
Boran Wang
XGXinyu Guo
Xinyu Guo
WZWenbin Zhu
Wenbin Zhu
JHJiasheng He
Jiasheng He
JYJing Yuan
Jing Yuan

14 August 2023 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZHZiqi Hu
Ziqi Hu
JYJing Yuan
Jing Yuan
YGYuanxi Gao
Yuanxi Gao
BWBoran Wang
Boran Wang
XZXuebo Zhang
Xuebo Zhang
Monocular visual odometry (VO) is a fundamental technique for unmanned ground vehicle (UGV) navigation. However, traditional monocular VO methods always suffer from sparse environment maps which cannot be directly used for navigation because of the lack of structural information. In this article, we propose a navigation-oriented LiDAR-guided monocular visual odometry and mapping (NALO-VOM) to obtain scale-consistent camera poses and a semi-dense environment map which is more suitable for navigation of UGVs. The structure representation ability of the 3D LiDAR point cloud is learned by a major-plane prediction network and then transferred into the monocular VO system in NALO-VOM. As a result, NALO-VOM can construct a more dense and high-quality map using only a monocular camera. To be specific, the major-plane prediction network is trained offline using 3D LiDAR geometric information, which predicts major-plane mask (MP-Mask) for each frame of the visual image during the localization. Then, MP-Mask is used for scale optimization and semi-dense map building. Experiments are performed on the public dataset and self-collected sequences. The results show the competitive performance on the localization accuracy and mapping quality compared with other visual odometry methods.

6 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
YCYishuo Chen
Yishuo Chen
BWBoran Wang
Boran Wang
XGXinyu Guo
Xinyu Guo
WZWenbin Zhu
Wenbin Zhu
JHJiasheng He
Jiasheng He
JYJing Yuan
Jing Yuan
Object detection in poor-illumination environments is a challenging task as objects are usually not clearly visible in RGB images. As infrared images provide additional clear edge information that complements RGB images, fusing RGB and infrared images has potential to enhance the detection ability in poor-illumination environments. However, existing works involving both visible and infrared images only focus on image fusion, instead of object detection. Moreover, they directly fuse the two kinds of image modalities, which ignores the mutual interference between them. To fuse the two modalities to maximize the advantages of cross-modality, we design a dual-enhancement-based cross-modality object detection network DEYOLO, in which semantic-spatial cross modality and novel bi-directional decoupled focus modules are designed to achieve the detection-centered mutual enhancement of RGB-infrared (RGB-IR). Specifically, a dual semantic enhancing channel weight assignment module (DECA) and a dual spatial enhancing pixel weight assignment module (DEPA) are firstly proposed to aggregate cross-modality information in the feature space to improve the feature representation ability, such that feature fusion can aim at the object detection task. Meanwhile, a dual-enhancement mechanism, including enhancements for two-modality fusion and single modality, is designed in both DECAand DEPAto reduce interference between the two kinds of image modalities. Then, a novel bi-directional decoupled focus is developed to enlarge the receptive field of the backbone network in different directions, which improves the representation quality of DEYOLO. Extensive experiments on M3FD and LLVIP show that our approach outperforms SOTA object detection algorithms by a clear margin. Our code is available at https://github.com/chips96/DEYOLO.

1 January 2022 in International Journal of Language and Linguistics
Verified
Journal Article
Open access
PDF file
BWBoran Wang
Boran Wang
To cope with the challenges in today’s world, students’ abilities should go well beyond basic reproduction of accumulated knowledge and concomitant acquisition of certain basic skills at school or university. Accordingly, competencies including knowledge, skills, attitudes and values are required for individuals’ sustainable development. This paper provides an overview of key competencies for China’s Secondary Vocational School English Curriculum Standards. The research panel of 11 members entrusted by the Ministry of Education of China (MOE) carried out a project of the key competencies in secondary vocational English since the official launch of the research project in May, 2017. On this basis, the research panel had China’s Secondary Vocational School English Curriculum Standards released in May, 2020. The key terms of competence and competency are first defined. Studies on key competencies abroad and at home are then reviewed. Four key competencies for China’s Secondary Vocational School English Curriculum Standards (2020) are then extracted from the review. These are workplace language communication, perception of thinking mode differences, cross-cultural understanding and autonomous learning – which are relatively independent but mutually integrated in that they form an organic whole. The criteria and process of extracting the four key competencies of secondary vocational English are described and the formulation and interpretation of the key competencies are elaborated upon. While the proposal concerning the key competencies provides conceptual support, the transformation from idea to practice needs considerable effort, especially in integrating these key competencies in curriculum design.