Search

Your search keyword '"Hu, Weijie"' showing total 326 results
Start Over Author "Hu, Weijie"
326 results on '"Hu, Weijie"'

4. Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

Author

Wang, Gaoang, Gu, Renshu, Liu, Zuozhu, Hu, Weijie, Song, Mingli, and Hwang, Jenq-Neng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motion-based trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. However, doing so requires extra computation while appearance information is sensitive to occlusion as well. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information. We address the tracklet embedding issue with the proposed reconstruct-to-embed strategy based on deep graph convolutional neural networks (GCN). Comprehensive experiments on the KITTI-car tracking dataset and UA-Detrac dataset show that the proposed method, though without appearance information, could achieve competitive performance with the state-of-the-art (SOTA) trackers. The source code will be available at https://github.com/GaoangW/LGMTracker.

Published
2021

9. Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking

Author

Wang, Gaoang, Wang, Yizhou, Gu, Renshu, Hu, Weijie, and Hwang, Jenq-Neng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast development of deep learning technology in recent years, MOT has achieved great improvement. However, some challenges still remain, such as sensitiveness to occlusion, instability under different lighting conditions, non-robustness to deformable objects, etc. To address such common challenges in most of the existing trackers, in this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker. The motivation is simple and straightforward: split tracklets on potential ID-switch positions and then connect multiple tracklets into one if they are from the same object. In other words, the tracklet booster consists of two parts, i.e., Splitter and Connector. First, an architecture with stacked temporal dilated convolution blocks is employed for the splitting position prediction via label smoothing strategy with adaptive Gaussian kernels. Then, a multi-head self-attention based encoder is exploited for the tracklet embedding, which is further used to connect tracklets into larger groups. We conduct sufficient experiments on MOT17 and MOT20 benchmark datasets, which demonstrates promising results. Combined with the proposed tracklet booster, existing trackers usually can achieve large improvements on the IDF1 score, which shows the effectiveness of the proposed method.

Published
2021

27. Geo-Semiotic Analysis of Shared Streets in Urban Historical Districts: The Case of Jiefangbei, Chongqing, China.

Author

Chen, Junli and Hu, Weijie

Subjects
CROSS-cultural studies, PUBLIC spaces, HISTORIC districts, OUTDOOR furniture, CENTRAL business districts
Abstract

This study examines the design and utilization of shared streets in the Jiefangbei Business District of Chongqing through the lens of geographical semiotics. Employing photo content analysis, video observation, and questionnaire surveys, this research delves into visual semiotics, place semiotics, and users' interaction order, including social interactions and traffic experiences within these shared spaces. The findings reveal that two distinct systems guide pedestrians and vehicles on Jiefangbei's shared streets, ensuring safety and cultural expression. Paving is identified as the most important method for realizing the sharing of space between people and vehicles. Street furniture emphasizes multifunctional composite use and reflects Jiefangbei's eclectic style since its era as a financial center of the Republic of China, responding to cultural resources and functional positioning. The study also indicates that social functions and public space attributes need enhancement, recommending more greenery and leisure facilities. Interaction order analysis shows that participants' perception of street sharing does not affect their sense of safety and effectiveness. Thus, future practice should base decisions on specific traffic conditions and urban functions. A limitation of this study is the inability to accurately sample the population structure of the Jiefangbei commercial district, preventing more adaptable conclusions. The authors suggest viewing shared space as an evolving process and recommend future research on long-term effects and cross-cultural comparative studies to provide valuable insights into global shared-street design. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

30. Satisfaction Evaluation and Renewal Strategies for Urban Parks Based on the Importance–Performance Analysis: A Case of Shaping Park in Chongqing, China.

Author

Wang, Yiting and Hu, Weijie

Subjects
*URBAN renewal, *WETLANDS, *SATISFACTION, *URBAN parks, *CULTURAL values, *SOCIAL values
Abstract

This study addresses the imperative to revitalize aging urban parks to meet the evolving demands of China's rapidly urbanizing population. Focusing on the Shaping Park in Chongqing, China, as a case study, the research analyses 281 surveys on park satisfaction and employs the importance–performance analysis (IPA) method to interpret the importance and performance values of 30 critical attributes in a four-quadrant satisfaction evaluation map. The findings reveal five major issues in the park and propose five renewal design strategies to accommodate the changing needs of park users, including enhancing access to cultural activities, recreational spaces, and park facilities while considering the significance of high-quality landscapes and natural features. The study reaffirms existing research that underscores the importance of enduring social and cultural values in satisfying contemporary users' satisfaction. It also highlights the necessity of adapting innovative design principles to evolving user behaviors and demands. The insights gained from this regional Chinese case study can enrich the literature and holds broader implications for park renewal projects on a global scale. Future studies should explore evaluation methods applicable to urban–suburban and wetland parks and subsequently redefine design strategies based on the findings derived from the IPA model. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

41. 3D‐Printed Biomimetic Structural Colors

Author

Bi, Ran, primary, Li, Xiaohong, additional, Ou, Xingcheng, additional, Huang, Jiaqi, additional, Huang, Dantong, additional, Chen, Guoliang, additional, Sheng, Yu, additional, Hong, Wei, additional, Wang, Yan, additional, Hu, Weijie, additional, and Guo, Shuang‐Zhuang, additional

Published
2023
Full Text
View/download PDF

48. Contemporary urban employment patterns among Chinese peasant workers in the 2020s

Author

Hu, Weijie and Gao, Xinrui

Abstract

ABSTRACTThe urban employment dynamics of Chinese peasant workers have transformed in the 2020s, influenced by factors like COVID-19, demographic shifts, China’s economy, urbanization, and globalization. The data presented in this paper comes from China’s national and local authorities, official publications, and reports. The findings reveal a growing trend of these workers seeking jobs closer to their hometowns, causing hiring challenges in city manufacturing sectors. We also found that young workers struggle to secure employment in emerging tertiary industries due to skill gaps, while older workers confront employment barriers from policy restrictions and market biases. This study provides an analysis of the current employment situation for peasant workers in urban areas. It offers valuable insights for policymakers to create measures that foster stable and sustainable employment opportunities for this vulnerable demographic in China.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results