Ying Jiang

Dr. Ying Jiang


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
6 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
YZYuan Zhang
Yuan Zhang
YSYoupeng Sun
Youpeng Sun
ZWZheng Wang
Zheng Wang
YJYing Jiang
Ying Jiang
Aiming at the problems of high missed detection rates of the YOLOv7 algorithm for vehicle detection on urban roads, weak perception of small targets in perspective, and insufficient feature extraction, the YOLOv7-RAR recognition algorithm is proposed. The algorithm is improved from the following three directions based on YOLOv7. Firstly, in view of the insufficient nonlinear feature fusion of the original backbone network, the Res3Unit structure is used to reconstruct the backbone network of YOLOv7 to improve the ability of the network model architecture to obtain more nonlinear features. Secondly, in view of the problem that there are many interference backgrounds in urban roads and that the original network is weak in positioning targets such as vehicles, a plug-and-play hybrid attention mechanism module, ACmix, is added after the SPPCSPC layer of the backbone network to enhance the network’s attention to vehicles and reduce the interference of other targets. Finally, aiming at the problem that the receptive field of the original network Narrows, with the deepening of the network model, leads to a high miss rate of small targets, the Gaussian receptive field scheme used in the RFLA (Gaussian-receptive-field-based label assignment) module is used at the connection between the feature fusion area and the detection head to improve the receptive field of the network model for small objects in the image. Combining the three improvement measures, the first letter of the name of each improvement measure is selected, and the improved algorithm is named the YOLOv7-RAR algorithm. Experiments show that on urban roads with crowded vehicles and different weather patterns, the average detection accuracy of the YOLOv7-RAR algorithm reaches 95.1%, which is 2.4% higher than that of the original algorithm; the AP50:90 performance is 12.6% higher than that of the original algorithm. The running speed of the YOLOv7-RAR algorithm reaches 96 FPS, which meets the real-time requirements of vehicle detection; hence, the algorithm can be better applied to vehicle detection.

12 September 2023 in IEEE Access
Verified
Journal Article
Open access
LZLiu-Lei Zhang
Liu-Lei Zhang
YJYing Jiang
Ying Jiang
YSYou-Peng Sun
You-Peng Sun
YZYuan Zhang
Yuan Zhang
ZWZheng Wang
Zheng Wang
Bird identification and classification are of great significance in bird conservation. Through proper bird classification, the changes in bird populations in a given area can be effectively predicted, thereby ensuring their effective protection. Nowadays, deep learning has achieved high accuracy in classifying bird images. However, most existing models suffer from poor generalization ability and high complexity. To enhance the model’s generalization ability, this paper constructed a large dataset consisting of 275 bird species and the dataset contains bird pictures in different situations, such as rainy days, foggy days.To reduce model complexity, a lightweight neural network based on ShuffleNetV2 was constructed. In ShuffleNetV2 network, there is no feature fusion module and efficient attention mechanism to assist the feature learning of the model. Therefore, this paper adds a feature fusion module and two attention mechanisms to make up for this shortcoming. A multi-channel feature fusion structure (MCF) was adopted to improve the network’s adaptability to extract information from multiple channel scales. By introducing Squeeze-and-Excitation (SE) Module and Coordinate attention (CA) in the Block module, the model’s ability to refine the global features was enhanced. The experimental results show that the accuracy of the model in identifying 275 bird species on the self-built dataset is 92.3%, which is 6.1% higher than the accuracy of ShuffleNetV1 (86.2%) and 1.8% higher than the accuracy of ShuffleNetV2 (90.5%). At the same time, with smaller parameters and floating point operations (FLOPs), its accuracy is 1.2% higher than ResNet50’s accuracy (ResNet50’s accuracy is 91.1%), which can save the cost better.

20 June 2024 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
YCYuehao Chen
Yuehao Chen
YJYing Jiang
Ying Jiang
ZXZhao-Dong Xu
Zhao-Dong Xu
LZLiulei Zhang
Liulei Zhang
FYFei Yan
Fei Yan
HZHanqing Zong
Hanqing Zong

12 May 2019 in Journal of Low Frequency Noise, Vibration and Active Control
Verified
Journal Article
Open access
PDF file
YJYing Jiang
Ying Jiang
MYMingjin Yu
Mingjin Yu
MZMengqi Zhang
Mengqi Zhang
JLJiyun Lu
Jiyun Lu
Wavelength or light intensity demodulation method for a polarization maintaining fiber loop mirror (PM-FLM) sensor is not only expensive but also unsuitable for vibration monitoring. This paper studies the voltage demodulation principle and explores theoretically the influence of light source on the sensitivity. Then a PM-FLM sensor is applied to vibration monitoring. A low-power narrow-band light source reflected from FBG and a high-power laser light source are used respectively as input. The time domain voltage signals of vibration from a photo-detector are collected by a data acquisition card and converted via a fast Fourier transform algorithm. The experimental result shows that a PM-FLM sensor using a high-power narrow-band light source as input has a higher sensitivity to vibration than the one using a low-power narrow-band light source. In practical application, we can choose a high-power narrow-band light source as input to improve the sensitivity to vibration.

10 December 2013 in Journal of Intelligent Material Systems and Structures
Verified
Journal Article
Closed access
YJYing Jiang
Ying Jiang
JZJie Zeng
Jie Zeng
DLDakai Liang
Dakai Liang
XNXiaoyu Ni
Xiaoyu Ni
It is difficult to make sure that the spliced polarization-maintaining fiber length is the same in every fabricating polarization-maintaining fiber loop mirror sensor, and it is also difficult to make sure that sensing length is the same in every experiment. To find out how these uncertain factors influence the axial strain sensitivity of polarization-maintaining fiber loop mirror, we perform the research on the influences of polarization-maintaining fiber length and sensing length on axial strain sensitivity. In this article, a theoretical model for axial strain sensitivity of polarization-maintaining fiber loop mirror is deduced first. By analyzing the theoretical model, we find that the axial strain sensitivity is unrelated to polarization-maintaining fiber length and sensing length. Then, we experimentally investigate the influences of polarization-maintaining fiber length and sensing length on axial strain sensitivity of polarization-maintaining fiber loop mirror. The axial strain sensitivities in the experiments are almost the same for different polarization-maintaining fiber lengths and different sensing lengths. The experimental results agree with the theoretical ones. The results can provide help for fabricating and applying polarization-maintaining fiber loop mirror sensor. The results can be applied in the temperature, displacement, and vibration sensors of polarization-maintaining fiber loop mirror and can also be applied in photonic crystal fiber loop mirror sensor.

13 February 2014 in Optik
Verified
Journal Article
Closed access
YJYing Jiang
Ying Jiang
JZJie Zeng
Jie Zeng
DLDakai Liang
Dakai Liang
XNXiaoyu Ni
Xiaoyu Ni