Yannan Ren

ORCID: 0000-0003-4436-479X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Vision and Imaging
  • Advanced Image and Video Retrieval Techniques
  • Advanced Image Processing Techniques
  • Advanced Steganography and Watermarking Techniques
  • Image Processing Techniques and Applications
  • Video Surveillance and Tracking Methods
  • Digital Media Forensic Detection
  • Chaos-based Image/Signal Encryption
  • Optical measurement and interference techniques
  • Video Analysis and Summarization
  • Computer Graphics and Visualization Techniques
  • Image Enhancement Techniques
  • Video Coding and Compression Technologies
  • Robotics and Sensor-Based Localization

Shandong Jiaotong University
2021-2024

Shandong University
2011-2019

In recent years, with the rapid development of unmanned aerial vehicle (UAV), images have extended across various industries such as intelligent building, agriculture, transportation, and Industry 4.0. Notably, security UAV‐assisted data acquisition during transmission has become a critical concern. The reversible hiding (RDH) method can hide in for ensure secure communication. general, an image may exhibit substantially different orientation regularity from natural scene image. This casts...

10.1155/int/2796189 article EN cc-by International Journal of Intelligent Systems 2025-01-01

An efficient depth map generation method is presented for static scenes with moving objects. Firstly, background scene reconstructed. Depth of the reconstructed extracted by linear perspective. Then, objects are segmented precisely. values assigned to according their positions in scene. Finally, and integrated into one map. Experimental results show that proposed can generate smooth reliable maps.

10.1109/3dtv.2011.5877196 article EN 2011-05-01

Virtual view synthesis has been considered as a crucial technique in three-dimensional television (3DTV) display, where depth-image-based rendering (DIBR) is key technology. In order to improve the virtual image quality, method without preprocessing depth proposed. During synthesis, hole-flag map fully utilized. A Horizontal, Vertical and Diagonal Extrapolation (HVDE) using information algorithm also proposed for filling tiny cracks. After blending, main obtained. Then generated by filtering...

10.1109/3dtv.2011.5877155 article EN 2011-05-01

In this paper, a depth image up-sampling method is put forward by using pixel classifying and jointed bilateral filtering.By analyzing the edge maps originated from high-resolution color low-resolution map respectively, pixels in up-sampled can be classified into four categories: points, edge-neighbor texture points smooth points.First, joint (JBU) used to generate an initial image.Then, for each category, different refinement methods are employed modify image.Experimental results show that...

10.3837/tiis.2018.07.013 article EN KSII Transactions on Internet and Information Systems 2018-07-31

Semi-automatic 2D-to-3D conversion (2D-3D) is preferred due to its advantage of handling the trade-off between human participation and 3D effects. In this paper, a novel depth propagation algorithm based on consistency proposed, which can be widely employed in semi-automatic 2D-3D. The refers principle that two neighboring pixels should have similar values if their color or intensities are similar. Based observation, estimation modeled as constrained optimization problem. Two contributions...

10.1109/wcsp.2012.6542867 article EN 2012-10-01

Most of depth up‐sampling algorithms are based on the consistent hypothesis, i.e. object boundaries in colour image with discontinuity regions map. However, hypothesis is not always correct. Under combined guidance high‐resolution (HR) edge map and HR gradient map, a simple efficient up‐sampler presented. Firstly, distinguished from other more accurate points found. Then, initial up‐sampled traditional bilinear interpolation refined by an effective depth‐assignment scheme. Extensive...

10.1049/el.2017.2297 article EN Electronics Letters 2017-08-31

This paper presents a novel depth map generation method based on geometric information. Our divides 2d image into two parts-the foreground and the background. Through extracting predominant lines vanishing point of background, background is determined. Then we use this as `scalar' to measure value object. Finally, are integrated one by fusion algorithm.

10.1109/secon.2012.6197062 article EN Proceedings of IEEE Southeastcon 2012-03-01

Three dimensional television (3DTV) has attracted more and attention in the area of TV broadcasting. However, applications are constrained due to content shortage. It is an economical way by converting monoscopic 2D video 3D (2D-3D) so as reuse existed huge amount videos materials using Depth-Image-Based-Rendering (DIBR). In this paper, efficient framework for extracting depth information from single image proposed, which based on scene classification object detection. proposed scheme,...

10.1109/u-media.2014.55 article EN 2014-07-01

This article describes how due to the diversification of electronic equipment in public security forensics, vehicle surveillance video as a burgeoning way attracts us attention. The videos contain useful evidence, and retrieval can help find evidence contained them. In order get accurately effectively, convolution neural network (CNN) is widely applied improve performance retrieval. this article, it proposed that method with deep feature derived from CNN iterative quantization (ITQ)...

10.4018/ijdcf.2018100104 article EN International Journal of Digital Crime and Forensics 2018-07-19

Selective encryption has been widely used in image privacy protection. Visual security assessment is necessary for the effectiveness and practicability of methods, there have a series research studies on this aspect. However, these methods do not take into account perceptual factors. In paper, we propose new visual (VSA) by saliency-weighted structure orientation similarity. Considering that human perception sensitive to characteristics selective encrypted images, extract feature maps, then...

10.1155/2021/6675354 article EN cc-by Security and Communication Networks 2021-01-22
Coming Soon ...