Yang Feng

Yang Feng


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
30 January 2019 in Sensors
Verified
Journal Article
Open access
PDF file
FZFukai Zhang
Fukai Zhang
Ce LiCe Li
Ce Li
YFYang Feng
Yang Feng
Vehicle detection with category inference on video sequence data is an important but challenging task for urban traffic surveillance. The difficulty of this task lies in the fact that it requires accurate localization of relatively small vehicles in complex scenes and expects real-time detection. In this paper, we present a vehicle detection framework that improves the performance of the conventional Single Shot MultiBox Detector (SSD), which effectively detects different types of vehicles in real-time. Our approach, which proposes the use of different feature extractors for localization and classification tasks in a single network, and to enhance these two feature extractors through deconvolution (D) and pooling (P) between layers in the feature pyramid, is denoted as DP-SSD. In addition, we extend the scope of the default box by adjusting its scale so that smaller default boxes can be exploited to guide DP-SSD training. Experimental results on the UA-DETRAC and KITTI datasets demonstrate that DP-SSD can achieve efficient vehicle detection for real-world traffic surveillance data in real-time. For the UA-DETRAC test set trained with UA-DETRAC trainval set, DP-SSD with the input size of 300 × 300 achieves 75.43% mAP (mean average precision) at the speed of 50.47 FPS (frames per second), and the framework with a 512 × 512 sized input reaches 77.94% mAP at 25.12 FPS using an NVIDIA GeForce GTX 1080Ti GPU. The DP-SSD shows comparable accuracy, which is better than those of the compared state-of-the-art models, except for YOLOv3.

23 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FLFanruo Li
Fanruo Li
YFYang Feng
Yang Feng
RYRui Yan
Rui Yan
XQXu Qiao
Xu Qiao
HXHongjia Xing
Hongjia Xing
YLYijin Li
Yijin Li
Currently, ground penetrating radar is the major technology for the detection of urban road collapses and disaster sources. Vehicle-mounted GPR collects tens of GB of data on site every day, but the present interpretation of abnormal regions detected by radar relies on manual interpretation with low process efficiency. The abnormal region images of GPR are different from the surrounding normal images. In terms of the features of abnormal regions in GPR images with an obvious brightness change and obvious directional characteristics, an abnormal region detection algorithm based on visual attention mechanism is proposed. Firstly, the complex background noise in the GPR images is suppressed by wavelet denoising and gamma transform, and the brightness and directional characteristics of the abnormal regions are enhanced. Secondly, by building a multi-scale image brightness and orientation feature pyramid model, the features of abnormal regions of interest are continuously enhanced, and the rapid screening of abnormal regions has been achieved. The effectiveness of the algorithm has been verified by actual tests on different types of abnormal radar image data.

12 December 2018 in Sensors
Verified
Journal Article
Open access
PDF file
ZXZheng Xiangtian
Zheng Xiangtian
XYXiaolin Yang
Xiaolin Yang
HMHaitao Ma
Haitao Ma
GRGuiwen Ren
Guiwen Ren
KZKeli Zhang
Keli Zhang
Ce LiCe Li
Ce Li
An integrated sensor system comprised of a terrestrial laser scanner (TLS), corner reflectors (CRs), and high precision linear rail is utilized to validate ground-based synthetic aperture radar (GB-SAR) interferometric micro-displacement measurements. A rail with positioning accuracy of 0.1 mm is deployed to ensure accurate and controllable deformation. The rail is equipped with a CR on a sliding platform for mobility. Three smaller CRs are installed nearby, each with a reflective sticker attached to the CR’s vertex; the CRs present as high-amplitude points both in the GB-SAR images and the TLS point cloud to allow for accurate data matching. We analyze the GB-SAR zero-baseline repeated rail differential interferometry signal model to obtain 2D interferograms of the test site in time series, and then use TLS to obtain a 3D surface model. The model is matched with interferograms to produce more intuitive 3D products. The CR displacements can also be extracted via surface reconstruction algorithm. Finally, we compared the rail sensor measurement and TLS results to optimize coherent scatterer selection and filter the data. The proposed method yields accurate target displacement results via quantitative analysis of GB-SAR interferometry.

6 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MXMaoxuan Xu
Maoxuan Xu
YFYang Feng
Yang Feng
RYRui Yan
Rui Yan
In order to solve the current problems that conventional video inspection can only detect, as an internal pipeline defect and drainage pipeline radar inspection device detects in a single direction and at radar frequency in water pipeline defect detection, a three-channel drainage pipeline ground penetrating radar (GPR) inspection device was designed and developed, the assembly and commissioning of the device prototype were completed, and an actual engineering test application was carried out. Focusing on the problem that the detection direction and depth of the single-channel detection device are limited, a three-channel drainage pipeline GPR inspection device is designed to realize the synchronous detection of the inside of the pipeline, the pipeline body, and the external environment of the pipeline, improving the detection depth and efficiency. According to the design scheme of the three-channel drainage pipeline GPR inspection device, the assembly of the device prototype was completed. The device contains three radar channels, the top of the main frequency of the antenna is 1.4 GHz, the two sides are 750 MHz, the video camera has a pixel count of 4 million, and the positioning accuracy is less than 1 mm, the waterproof grade is IP68, the detection accuracy of pipe deformation (slope) is 0.1°, the detection depth outside the pipe is 1.2 m, and the detection accuracy of corrosion thickness is 15 mm. In a practical application of the device, the Jianguomenqiao sewage pipeline in Beijing, China, was tested, resulting in the discovery of 87 defects, including 39 loose soil areas at the bottom of the pipe exterior, 40 void areas, and 8 cavities.

7 October 2023 in Sensors
Verified
Journal Article
Open access
PDF file
LFLiang Fang
Liang Fang
YFYang Feng
Yang Feng
MXMaoxuan Xu
Maoxuan Xu
FLFengyu Liu
Fengyu Liu
This paper describes the development of a new 3D ground-penetrating radar (GPR) acquisition and control technology for road underground diseases with dual-band antenna arrays. The 3D GPR system can be mounted on a vehicle-loading device and used by vehicles to detect road underground diseases at regular speeds. Compared with existing 3D GPR systems, this new type of 3D GPR has the following design features: it has dual-band antenna arrays, including a 16-channel 400 MHz antenna array and an 8-channel 200 MHz antenna array, which not only improves the detection efficiency, but also effectively balances the detection depth and detection resolution. A novel antenna switching method for time division step multiplexing (TDSM) is realized via field programmable gate array (FPGA), which not only avoids the crosstalk of antenna echo signals of different frequencies, but also ensures the interval of the same antenna working time. By combining the advantages of the FPGA and micro-control unit (MCU), and utilizing the high-speed transmission of the network port, the high-speed real-time transmission of the 3D GPR echo data is achieved. Finally, the integration of all software and hardware verified the correctness of the system, with good results.

26 February 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XHXinxin Huang
Xinxin Huang
JLJialin Liu
Jialin Liu
YFYang Feng
Yang Feng
XQXu Qiao
Xu Qiao
LGLiang Gao
Liang Gao
JZJianshe Zhao
Jianshe Zhao
In urban road detection using Ground Penetrating Radar (GPR), challenges arise from complex and variable road structures and diversified detection environments. These unstable factors decrease GPR detection signal strength and cause signal shape distortion, negatively affecting detection accuracy. This reduces the interpretive accuracy of GPR images, impacting precise diagnosis of underground structures and hidden defects in urban roads. Therefore, understanding and overcoming these challenges is practically important for improving GPR performance and interpretive efficiency in urban road detection. To address these issues, this study proposes an innovative strategy using unsupervised learning for GPR image restoration. Specifically, it utilizes the Cycle-Consistent Adversarial Network (CycleGAN) with the Convolutional Block Attention Module (CBAM) generator and integrates the Multi-Scale Structural Similarity Index (MS-SSIM) loss function to enhance restoration quality. The method is trained and validated using field experimentally collected datasets with and without road surface interference, and the performance is evaluated through qualitative and quantitative analysis of restored GPR B-scan images. The experimental results show that the proposed method improves image restoration by 4.9% in SSIM, 39.15% in PSNR, and 76.88% in MAE, confirming its significant effect in GPR image restoration.