Shang Gao

Shang Gao

Auto-generated profile, based on publicly available information

Shang Gao

Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 June 2023
Verified
Conference Paper
Closed access
JYJinyu Yang
Jinyu Yang
SGShang Gao
Shang Gao
ZLZhe Li
Zhe Li
FZFeng Zheng
Feng Zheng
ALAles Leonardis
Ales Leonardis
Aerial robots are now able to fly in complex environments, and drone-captured data gains lots of attention in object tracking. However, current research on aerial perception has mainly focused on limited categories, such as pedestrian or vehicle, and most scenes are captured in urban environments from a birds-eye view. Recently, UAVs equipped with depth cameras have been also deployed for more complex applications, while RGBD aerial tracking is still unexplored. Compared with traditional RGB object tracking, adding depth information can more effectively deal with more challenging scenes such as target and background interference. To this end, in this paper, we explore RGBD aerial tracking in an overhead space, which can greatly enlarge the development of drone-based visual perception. To boost the research, we first propose a large-scale benchmark for RGBD aerial tracking, containing 1,000 drone-captured RGBD videos with dense annotations. Then, as drone-based applications require for real-time processing with limited computational resources, we also propose an efficient RGBD tracker named EMT. Our tracker runs at over 100 fps on GPU, and 25 fps on the edge platform of NVidia Jetson NX Xavier, benefiting from its efficient multimodal fusion and feature matching. Extensive experiments show that our EMT achieves promising tracking performance. All resources are available at https://github.com/yjybuaa/RGBDAerialTracking.

8 April 2024 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
SGShang Gao
Shang Gao
XQXiaoqi Qin
Xiaoqi Qin
LCLi Chen
Li Chen
Yunfei ChenYunfei Chen
Yunfei Chen
KHKaifeng Han
Kaifeng Han
PZPing Zhang
Ping Zhang
Semantic communication shows great promise in reducing network traffic and alleviating spectrum shortage. While many semantic theories have been put forward, how to measure the importance of semantic information theoretically remains an open issue. In this paper, we propose semantic value, a metric that measures the importance of semantic information, for text transmission. First, we model a semantic communication system for text transmission, in which semantic information is represented by semantic triplets. Then, we propose a hybrid communication mechanism to ensure the success of text transmission. Finally, we compare the performances of the conventional mode and the semantic mode in terms of latency and derive conditions leading to minimum latency.

24 November 2023
Verified
Conference Paper
Closed access
NDNa Dong
Na Dong
YZYimeng Zhang
Yimeng Zhang
Tao ZhangTao Zhang
Tao Zhang
WZWeixin Zhang
Weixin Zhang
BLBin Liang
Bin Liang
SGShang Gao
Shang Gao
The development of new energy vehicles has driven the vigorous development of the charging pile industry. The mandatory verification system can ensure the accuracy and fairness of electric vehicle charging piles measurement, protect consumer rights, and thus promote the development of the electric vehicle market. In terms of China's national conditions, the large number of charging piles makes it difficult to carry out periodic verification of charging piles in operation. Currently, there are still problems such as low efficiency, high cost, and difficulty in implementation. Therefore, it is increasingly important to continuously explore the full-life-cycle management of charging piles in operation through the construction of a charging pile data monitoring platform, utilize digital measurement methods, break through the regular measurement and verification mode of charging piles, and achieve continuous and effective supervision and management of large-scale charging piles.