Xia Yang

Xia Yang

Auto-generated profile, based on publicly available information

Xia Yang

School of Aeronautics and Astronautics, Sun Yat-Sen University, Shenzhen, Guangdong, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
30 April 2023 in Aerospace
Verified
Journal Article
Open access
PDF file
BLBin Lin
Bin Lin
JWJie Wang
Jie Wang
HWHan Wang
Han Wang
LZLijun Zhong
Lijun Zhong
XYXia Yang
Xia Yang
XZXiaohu Zhang
Xiaohu Zhang
Although space targets have different shapes, sizes and intensities, their distributions share certain commonalities. However, it is difficult to summarize a generalized distribution function for space targets. Moreover, most of the existing methods based on deep learning are not suitable to use directly because of the size of targets and the cost of manual labeling for a full image. In this paper, we proposed a pattern for space target detection based on a convolutional neural network (CNN) to learn essential features of the targets from data. In the processing stage, the background is estimated and removed. Then, image techniques are used to search and process region proposals. Different sizes of region proposals are recognized by a discriminator, which is built upon a small CNN trained with the data of several specific targets. Finally, a non-maximum suppression (NMS) operation is used to remove redundant targets. In the network structure, to further enhance the influence of the effective area, the parameters calculated from the center region of the input are utilized as guidance information and added to the features before the full connection. Moreover, the bias loss is applied to increase the weights of unique features. The experimental results demonstrate the outstanding performance of the proposed method in terms of the number of detected targets, accuracy rate and false alarm rate compared with baseline methods. In particular, the proposed method has a simple network structure and a lower computational cost which can be further promoted and implemented in actual engineering.

3 April 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
BLBin Lin
Bin Lin
XXXiangpeng Xu
Xiangpeng Xu
ZSZhihua Shen
Zhihua Shen
XYXia Yang
Xia Yang
LZLijun Zhong
Lijun Zhong
XZXiaohu Zhang
Xiaohu Zhang
The registration of astronomical images, is one of the key technologies to improve the detection accuracy of small and weak targets during astronomical image-based observation. The error of registration has a great influence on the trace association of targets. However, most of the existing methods for point-matching and image transformation lack pertinence for this actual scene. In this study, we propose a registration algorithm based on geometric constraints and homography, for astronomical images. First, the position changes in stars in an image caused by the motion of the platform where the camera had been stationed, were studied, to choose a more targeted registration model, which is based on homography transformation. Next, each image was divided into regions, and the enclosed stable stars were used for the construction of triangles, to reduce the errors from unevenly distributed points and the number of triangles. Then, the triangles in the same region of two images were matched by the geometric constraints of side lengths and a new cumulative confidence matrix. Finally, a strategy of two-stage estimation was applied, to eliminate the influence of false pairs and realize accurate registration. The proposed method was then tested on sequences of real optical images under different imaging conditions and confirmed to have outstanding performance in the dispersion rate of points, the accuracy of matching, and the error of registration, as compared to baseline methods. The mean pixel errors after registration for different sequences are all less than 0.5 when the approximate rotation angle per image is from 0.58 ×10−2 to 5.89 ×10−2.

1 December 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SZSheng Zhuge
Sheng Zhuge
YHYuwei He
Yuwei He
XXXiangpeng Xu
Xiangpeng Xu
SGShuwei Gan
Shuwei Gan
CLChunjun Li
Chunjun Li
XZXiaohu Zhang
Xiaohu Zhang
Capturing the motion of humans without any markers in a moving scene is a challenging issue. Typical methods, such as those based on fixed cameras or wearable sensors, have limits on the measurement range and the number of targets. Therefore, we propose a markerless motion capture technique to estimate the 3D pose of humans through a multi-UAV system. By utilizing the advantage of the large observation baselines between UAVs in the system, an algorithm to estimate the pose of airborne cameras and establish the sparse points cloud of background in overlapping view simultaneously was presented. A 3σ rule based on reprojection error is employed to eliminate the incorrect conjugate keypoint pairs, enhancing the precision of pose estimation for airborne cameras. To verify the accuracy of the developed technique, an indoor test was conducted to compare it with a commercial capture system, the results show that the average measurement error of the 3D joints of humans is less than 30mm. Furthermore, we demonstrate the feasibility of our approach in outdoor scenes, including multi-person scenarios and moving scenarios.

26 September 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
YXYang Xia
Yang Xia
MJMai Jianting
Mai Jianting
ZYZhang Yi
Zhang Yi
LZLijun Zhong
Lijun Zhong
Rotary encoders are commonly used in industry for high precision motor control. This paper proposes a polar transformation of the digital image grating (DIG) method to realize a simple, accurate and low-cost rotary encoder. It measures angles with a rather small camera view to get high accuracy angle results and uses DIG strategy to realize full range measurement. The DIG method estimates the rough angle position by code mark recognition and obtains the accurate angle position by precise image matching. First, a circle image pattern is designed and is put on the top of the rotator. Second, images of the circle image pattern are grabbed and transformed to polar coordinate system with polar transformation method. Last, the angle positions are calculated from the transformed images based on the DIG method. Simulations show that the proposed method is capable of measuring rotary angles with MSER below 1 arcsec. In experiments, the angle result precisions are about 1.6 arcsecs (MSER) with a rotary diameter of 60 mm, and the accuracy is 10 times higher than the existing monocular methods.

8 September 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
ZSZhihua Shen
Zhihua Shen
SCSiyang Chen
Siyang Chen
TZTongsu Zhang
Tongsu Zhang
HWHan Wang
Han Wang
ZZZhixiang Zhang
Zhixiang Zhang
XYXia Yang
Xia Yang
Multi-frame infrared small target detection (IRSTD) plays a crucial role in low-altitude and maritime surveillance. The hybrid architecture combining CNNs and Transformers shows great promise for enhancing multi-frame IRSTD performance. In the paper, we propose LVNet, a simple yet powerful hybrid architecture that emphasizes low-level feature learning in hybrid frameworks for multi-frame IRSTD. Our key insight is that the standard linear patch embeddings in Vision Transformers are insufficient for capturing the scale-sensitive local features critical to infrared small targets. To overcome this limitation, we design a multi-scale CNN frontend that explicitly models local features by leveraging the local spatial bias of convolution. Additionally, we introduce a U-shaped video Transformer for multi-frame spatiotemporal context modeling, effectively capturing the motion characteristics of targets. To the best of our knowledge, we are the first to introduce the concept of “low-level matters” within the CNN-Transformer hybrid architecture for multi-frame IRSTD. Despite its simplicity, with only 1.77 M parameters and 17.88 G FLOPs, LVNet achieves state-of-the-art (SOTA) performance at a speed of 208 FPS. Experiments on multiple public datasets, comparing LVNet with 18 SOTA methods, demonstrate its superior performance and efficiency. Our code and pre-trained models are accessible at https://github.com/ZhihuaShen/LVNet.

19 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
LZLijun Zhong
Lijun Zhong
JQJunyou Qin
Junyou Qin
XYXia Yang
Xia Yang
XZXiaohu Zhang
Xiaohu Zhang
YSYang Shang
Yang Shang
QYQifeng Yu
Qifeng Yu
For the problem of 3D line reconstruction in binocular or multiple view stereo vision, when there are no corresponding points on the line, the method called Direction-then-Point (DtP) can be used, and if there are two pairs of corresponding points on the line, the method called Two Points 3D coordinates (TPS) can be used. However, when there is only one pair of corresponding points on the line, can we get the better accuracy than DtP for 3D line reconstruction? In this paper, a linear and more accurate method called Point-then-Direction (PtD) is proposed. First, we used the intersection method to obtain the 3D point’s coordinate from its corresponding image points. Then, we used this point as a position on the line to calculate the direction of the line by minimizing the image angle residual. PtD is also suitable for multiple camera systems. The simulation results demonstrate that PtD increases the accuracy of both the direction and the position of the 3D line compared to DtP. At the same time, PtD achieves a better result in direction of the 3D line than TPS, but has a lower accuracy in the position of 3D lines than TPS.