Tong Jia

Tong Jia

Auto-generated profile, based on publicly available information

Tong Jia

Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts and Telecommunications Xi'an 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
22 September 2023
Verified
Conference Paper
Open access
XLXia Yan Liang
Xia Yan Liang
MZMeng Zhao
Meng Zhao
GLGuangyue Lu
Guangyue Lu
Jing JiangJing Jiang
Jing Jiang
HHHua He
Hua He
TJTong Jia
Tong Jia
In recent years, deep artificial neural networks have received wide attention because it surpasses the effect of traditional methods by parameter fitting under the condition of data convergence. On the other hand, limited transmission bandwidth and storage capacity lead to necessity of image compression in communications. In this paper, we propose an adaptive image compression algorithm with variable compression rate and learning rate based on the neural network in deep learning. This algorithm can meet various requirements in different situations by adjusting the parameters reasonably. Experiment results show the feasibility, flexibility and effectiveness of our proposed algorithm. Lower errors are obtained compared to other algorithms under the same compression rate.

1 January 2025 in IET Image Processing
Verified
Journal Article
Open access
XLXia Yan Liang
Xia Yan Liang
TJTong Jia
Tong Jia
XLXin Liu
Xin Liu
HZHuanhuan Zhang
Huanhuan Zhang
Unmanned aerial vehicles (UAVs) are widely used but face challenges of limited storage and bandwidth. In this research, we propose an image compression algorithm tailored for UAV communication, termed region of interest extraction for UAV communication (ROIE‐UC). First, image pixels are clustered into super pixel blocks using the simple linear iterative clustering (SLIC). Second, these super pixels are grouped into regions of interest (ROI) using the density‐based spatial clustering of applications with noise (DBSCAN). The image is then segmented into ROI and non‐ROI areas based on these clusters. Lossless compression is applied to the ROI, while lossy compression with a high ratio is used for non‐ROI regions. At the receiving end, the image is decompressed and reconstructed. Experiments show ROIE‐UC gets a peak signal‐to‐noise ratio (PSNR) of 46.37 dB and an feature similarity index (FSIM) of 99.99% for ROI. It outperforms JPEG in PSNR (up to 28.52% improvement), FSIM (0.15% improvement), and compression ratio. When PSNR and FSIM are similar, its max compression ratio is 5.89 times that of JPEG. It also has up to 51.49% higher PSNR than other methods. ROIE‐UC is an effective solution for UAV image processing and data compression.