Ruihong Yin

Ms. Ruihong Yin

Beihang University Beijing China
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
15 November 2020 in Sensors
Verified
Journal Article
Open access
PDF file
Ruihong YinRuihong Yin
Ruihong Yin
WZWei Zhao
Wei Zhao
Xudong FanXudong Fan
Xudong Fan
Yongfeng YinYongfeng Yin
Yongfeng Yin
There are a large number of studies on geospatial object detection. However, many existing methods only focus on either accuracy or speed. Methods with both fast speed and high accuracy are of great importance in some scenes, like search and rescue, and military information acquisition. In remote sensing images, there are some targets that are small and have few textures and low contrast compared with the background, which impose challenges on object detection. In this paper, we propose an accurate and fast single shot detector (AF-SSD) for high spatial remote sensing imagery to solve these problems. Firstly, we design a lightweight backbone to reduce the number of trainable parameters of the network. In this lightweight backbone, we also use some wide and deep convolutional blocks to extract more semantic information and keep the high detection precision. Secondly, a novel encoding–decoding module is employed to detect small targets accurately. With up-sampling and summation operations, the encoding–decoding module can add strong high-level semantic information to low-level features. Thirdly, we design a cascade structure with spatial and channel attention modules for targets with low contrast (named low-contrast targets) and few textures (named few-texture targets). The spatial attention module can extract long-range features for few-texture targets. By weighting each channel of a feature map, the channel attention module can guide the network to concentrate on easily identifiable features for low-contrast and few-texture targets. The experimental results on the NWPU VHR-10 dataset show that our proposed AF-SSD achieves superior detection performance: parameters 5.7 M, mAP 88.7%, and 0.035 s per image on average on an NVIDIA GTX-1080Ti GPU.

20 August 2020 in IEEE Access
Verified
Journal Article
Open access
Ruihong YinRuihong Yin
Ruihong Yin
RZRufei Zhang
Rufei Zhang
WZWei Zhao
Wei Zhao
FJFeng Jiang
Feng Jiang
Pedestrian detection plays an important role in some areas such as autonomous driving, but due to heavy occlusion and various scales, it is still challenging. In this paper, we propose an improved pedestrian detection method called DA-Net based on the two-stage detector Feature Pyramid Network (FPN). DA-Net adds Dense Connected Block (DCB), a combination of channel-wise attention module (CWAM) and global attention module (GAM) to the network. FPN can produce features with various scales and semantic information, which is good for the detection of pedestrians on various scales. Due to many small-scale targets in pedestrian detection, we only regard the low layers with enough details of targets in FPN as prediction layers. After several DCBs to deepen the network, prediction layers in our network can encode richer semantic information of targets, which can make the location of a target more precisely. In order to highlight visible parts of occluded pedestrians and ignore occluded parts, CWAM weights each channel of features with different importance. GAM aggregates global information and long-range dependencies for small-scale and occluded targets. Thus, the combination of CWAM and GAM is not only beneficial for coping with occlusion problem in pedestrian detection, but also for gaining environmental information for small-scale targets. Evaluation results on CUHK and CityPersons datasets show that our proposed method achieves improved performance with log-average miss rate reduction of 9.6% on the CUHK dataset and 6.1% on the Heavy subset of CityPersons dataset compared with FPN.

28 October 2024
Verified
Conference Paper
Open access
XZXuemei Zhou
Xuemei Zhou
IVIrene Viola
Irene Viola
Ruihong YinRuihong Yin
Ruihong Yin
PCPablo Cesar
Pablo Cesar
As 3D immersive media continues to gain prominence, Point Cloud Quality Assessment (PCQA) is essential for ensuring high-quality user experiences. This paper introduces ViSam-PCQA, a no-reference PCQA metric guided by visual saliency information across three modalities, which facilitates the performance of the quality prediction. Firstly, we project the 3D point cloud to acquire 2D texture, depth, and normal maps. Secondly, we extract the saliency map based on the texture map and refine it with the corresponding depth map. This refined saliency map is used to weight low-level feature maps to highlight perceptually important areas in the texture channel. Thirdly, high-level features from the texture, normal, and depth maps are then processed by a Transformer to capture global and local point cloud representations across the three modalities. Lastly, saliency along with global and local embeddings, are concatenated and processed through a multi-task decoder to derive the final quality scores. Our experiments on the SJTU, WPC, and BASICS datasets show high Spearman rank order correlation coefficients/Pearson linear correlation coefficients of 0.953/0.962, 0.920/0.920 and 0.887/0.936 respectively, demonstrating superior performance compared to current state-of-the-art methods. The code is available at https://github.com/cwi-dis/ViSam-PCQA_MM2024Workshop.

5 December 2024
Verified
Book Chapter
Closed access
PDF file
Ruihong YinRuihong Yin
Ruihong Yin
YCYunlu Chen
Yunlu Chen
SKSezer Karaoglu
Sezer Karaoglu
TGTheo Gevers
Theo Gevers

5 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
Ruihong YinRuihong Yin
Ruihong Yin
VYVladimir Yugay
Vladimir Yugay
YLYue Li
Yue Li
SKSezer Karaoglu
Sezer Karaoglu
TGTheo Gevers
Theo Gevers
The field of novel view synthesis from images has seen rapid advancements with the introduction of Neural Radiance Fields (NeRF) and more recently with 3D Gaussian Splatting. Gaussian Splatting became widely adopted due to its efficiency and ability to render novel views accurately. While Gaussian Splatting performs well when a sufficient amount of training images are available, its unstructured explicit representation tends to overfit in scenarios with sparse input images, resulting in poor rendering performance. To address this, we present a 3D Gaussian-based novel view synthesis method using sparse input images that can accurately render the scene from the viewpoints not covered by the training images. We propose a multi-stage training scheme with matching-based consistency constraints imposed on the novel views without relying on pre-trained depth estimation or diffusion models. This is achieved by using the matches of the available training images to supervise the generation of the novel views sampled between the training frames with color, geometry, and semantic losses. In addition, we introduce a locality preserving regularization for 3D Gaussians which removes rendering artifacts by preserving the local color structure of the scene. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance of our method in few-shot novel view synthesis compared to existing state-of-the-art methods.

28 August 2024 in arXiv
Verified
Preprint
Open access
PDF file
Ruihong YinRuihong Yin
Ruihong Yin
YCYunlu Chen
Yunlu Chen
SKSezer Karaoglu
Sezer Karaoglu
TGTheo Gevers
Theo Gevers
Existing methods in neural scene reconstruction utilize the Signed Distance Function (SDF) to model the density function. However, in indoor scenes, the density computed from the SDF for a sampled point may not consistently reflect its real importance in volume rendering, often due to the influence of neighboring objects. To tackle this issue, our work proposes a novel approach for indoor scene reconstruction, which instead parameterizes the density function with the Signed Ray Distance Function (SRDF). Firstly, the SRDF is predicted by the network and transformed to a ray-conditioned density function for volume rendering. We argue that the ray-specific SRDF only considers the surface along the camera ray, from which the derived density function is more consistent to the real occupancy than that from the SDF. Secondly, although SRDF and SDF represent different aspects of scene geometries, their values should share the same sign indicating the underlying spatial occupancy. Therefore, this work introduces a SRDF-SDF consistency loss to constrain the signs of the SRDF and SDF outputs. Thirdly, this work proposes a self-supervised visibility task, introducing the physical visibility geometry to the reconstruction task. The visibility task combines prior from predicted SRDF and SDF as pseudo labels, and contributes to generating more accurate 3D geometry. Our method implemented with different representations has been validated on indoor datasets, achieving improved performance in both reconstruction and view synthesis.