Yaowen Lv

Mr. Yaowen Lv


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
4 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YLYaowen Lv
Yaowen Lv
ZAZhiqing Ai
Zhiqing Ai
MCManfei Chen
Manfei Chen
XGXuanrui Gong
Xuanrui Gong
YWYuxuan Wang
Yuxuan Wang
ZLZhenghai Lu
Zhenghai Lu
To solve the problem of low accuracy and slow speed of drone detection in high-resolution images with fixed cameras, we propose a detection method combining background difference and lightweight network SAG-YOLOv5s. First, background difference is used to extract potential drone targets in high-resolution images, eliminating most of the background to reduce computational overhead. Secondly, the Ghost module and SimAM attention mechanism are introduced on the basis of YOLOv5s to reduce the total number of model parameters and improve feature extraction, and α-DIoU loss is used to replace the original DIoU loss to improve the accuracy of bounding box regression. Finally, to verify the effectiveness of our method, a high-resolution drone dataset is made based on the public data set. Experimental results show that the detection accuracy of the proposed method reaches 97.6%, 24.3 percentage points higher than that of YOLOv5s, and the detection speed in 4K video reaches 13.2 FPS, which meets the actual demand and is significantly better than similar algorithms. It achieves a good balance between detection accuracy and detection speed and provides a method benchmark for high-resolution drone detection under a fixed camera.

15 March 2018 in Applied Optics
Verified
Journal Article
Open access
PDF file
YLYaowen Lv
Yaowen Lv
WLWei Liu
Wei Liu
XXXiping Xu
Xiping Xu
This paper focuses on camera calibration with one-dimensional (1D) objects, and novel methods are proposed in this paper. Different from the known 1D object-based camera calibration algorithms, which define the camera coordinate system as the world coordinate system, we assume that the 1D calibration object is located along the X axis of the world coordinate system. Based on this new model, a 3×2 1D homography is defined to relate the points in the 1D objects to the perspective image points thereof. Then, the basic constraint for camera calibration using 1D objects from a single image is derived. Subsequently, two existing motions, namely, rotating around a fixed point and moving on a plane, are discussed, and new algorithms are proposed. In our methods, if the number of points in the 1D objects is more than three, more compact constraints can be obtained when the 1D objects rotate around a fixed point. In the case of planar motion, the estimation of vanishing points is not needed, and the calibration accuracy is significantly improved. Finally, both computer simulations and experiments are performed to validate the effectiveness and robustness of our algorithms.

4 October 2019 in IEEE Access
Verified
Journal Article
Open access
XGXuanrui Gong
Xuanrui Gong
YLYaowen Lv
Yaowen Lv
XXXiping Xu
Xiping Xu
ZJZhaoguo Jiang
Zhaoguo Jiang
ZSZhuang Sun
Zhuang Sun
A distorted checkerboard image affects the precision of omnidirectional camera calibration because of the inaccurate localization of the feature points. To solve this problem, an iterative refinement method is presented. First, the initial parameters are obtained using the traditional calibration method, and the distorted checkerboard is transformed to a distortion-free plane by the projection model that is estimated by initial parameters. Then, the feature point coordinates of the corrected image are extracted. The calibration parameters are recomputed using the refinement of new point locations until the camera parameters converge. This iterative refinement method improves the localization accuracy of feature points and, consequently, of camera calibration. The correctness and effectiveness of the method are verified by a series of simulations and physical experiments. The experiments show that the reprojection errors of feature points are reduced by 39% compared to traditional methods.

23 January 2024 in Journal of the Optical Society of America A
Verified
Journal Article
Closed access
PDF file
KSKe Suo
Ke Suo
YLYaowen Lv
Yaowen Lv
JYJiachao Yin
Jiachao Yin
YYYang Yang
Yang Yang
XHXi Huang
Xi Huang
In order to solve the problems of color shift and incomplete dehazing after image dehazing, this paper proposes an improved image self-supervised learning dehazing algorithm that combines polarization characteristics and deep learning. First, based on the YOLY network framework, a multiscale module and an attention mechanism module are introduced into the transmission feature estimation network. This enables the extraction of feature information at different scales and allocation of weights, and effectively improves the accuracy of transmission map estimation. Second, a brightness consistency loss based on the YCbCr color space and a color consistency loss are proposed to constrain the brightness and color consistency of the dehazing results, resolving the problems of darkened brightness and color shifts in dehazed images. Finally, the network is trained to dehaze polarized images based on the atmospheric scattering model and loss function constraints. Experiments are conducted on synthetic and real-world data, and comparisons are made with six contrasting dehazing algorithms. The results demonstrate that, compared to the contrastive dehazing algorithms, the proposed algorithm achieves PSNR and SSIM values of 23.92 and 0.94, respectively, on synthetic image samples. For real-world image samples, color restoration is more authentic, contrast is higher, and detailed information is richer. Both subjective and objective evaluations show significant improvements. This validates the effectiveness and superiority of the proposed dehazing algorithm.

1 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
YZYu Zhang
Yu Zhang
XXXiping Xu
Xiping Xu
NZNing Zhang
Ning Zhang
YLYaowen Lv
Yaowen Lv
When a traditional visual SLAM system works in a dynamic environment, it will be disturbed by dynamic objects and perform poorly. In order to overcome the interference of dynamic objects, we propose a semantic SLAM system for catadioptric panoramic cameras in dynamic environments. A real-time instance segmentation network is used to detect potential moving targets in the panoramic image. In order to find the real dynamic targets, potential moving targets are verified according to the sphere’s epipolar constraints. Then, when extracting feature points, the dynamic objects in the panoramic image are masked. Only static feature points are used to estimate the pose of the panoramic camera, so as to improve the accuracy of pose estimation. In order to verify the performance of our system, experiments were conducted on public data sets. The experiments showed that in a highly dynamic environment, the accuracy of our system is significantly better than traditional algorithms. By calculating the RMSE of the absolute trajectory error, we found that our system performed up to 96.3% better than traditional SLAM. Our catadioptric panoramic camera semantic SLAM system has higher accuracy and robustness in complex dynamic environments.

23 February 2024 in IEEE Access
Verified
Journal Article
Open access
YLYi Lu
Yi Lu
XXXi Ping Xu
Xi Ping Xu
NZNing Zhang
Ning Zhang
YLYaowen Lv
Yaowen Lv
LXLiang Xu
Liang Xu
To evaluate the ability of space optical systems to suppress off-axis stray light, this paper proposes a stray light testing method for large-field of view, multispectral spatial optical systems based on point source transmittance (PST). And a stray light testing platform was developed using a high-brightness simulated light source, large-aperture off-axis reflective collimator, high-precision positioning mechanism and a double column tank to evaluate the stray light PST index of spatial optical system. On the basis of theoretical analyses, a set of calibration lenses and stray light elimination structures such as hoods, baffle and stop are designed for the accuracy calibration of stray light testing systems. The theoretical PST values of the calibration lens at different off-axis angles are analyzed by Trace Pro software simulation and compared with the measured values to calibrate the accuracy of the system. The testing results show that the PST measurement range of the system reaches 10 -3 ~10 -10 when the off-axis angles of the calibration lens are in the range of ±5°~±60°. The stray light test system has the advantages of wide working band, high automation and large dynamic range, and its test results can be used in the correction of lens hood and other applications.