Zhenglong Ding

Dr. Zhenglong Ding

School of Artiffcial Intelligence, Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
26 August 2022 in IEEE Access
Verified
Journal Article
Open access
TCTingting Chen
Tingting Chen
Zhenglong DingZhenglong Ding
Zhenglong Ding
BLBiao Li
Biao Li
The problem of aging population in our country is becoming more and more serious, falling on the road accidently has been the first murder for people over 65 years of age. In this article, a real-time detection method for elderly fall behavior based on improved YOLOv5s is proposed to detect whether the elderly fall in real time, so that they can receive timely and effective treatment. First, the asymmetric convolution blocks (ACB) convolution module is used in the Backbone network to replace the existing basic convolution to improve the feature extraction capability. Then, the spatial attention mechanism module is added to the residual structure of the Backbone network to extract more feature location information. Finally, the feature layer structure is improved to remove the feature layer for small targets so that the network can pay more attention to the semantic level information, and at the same time, the classifier is set. The proposed algorithm is trained on the URFD public dataset, and the test set is used for verification. The experimental results show that the average accuracy of all categories of the algorithm reaches 97.2%, which is increased by 3.5% compared to YOLOv5s. Thus the proposed algorithm can accurately detect the fall behavior of the elderly.

22 September 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WXWeijie Xu
Weijie Xu
Zhenglong DingZhenglong Ding
Zhenglong Ding
ZWZiheng Wang
Ziheng Wang
ZCZhiqing Cui
Zhiqing Cui
YHYifan Hu
Yifan Hu
Feng JiangFeng Jiang
Feng Jiang
Infrared small target detection (IRSTD) remains challenging due to the extremely low signal-to-noise ratio (SNR). Existing methods struggle to balance accuracy and speed, especially under limited computational resources. To address these issues, we propose the frequency-spatial contextual fusion network (FSCFNet) based on You Only Look Once (YOLO) v10n architecture. Particularly, the novel frequency-spatial convolution (FSConv) is designed that decomposes input features via Haar Wavelet Transform. High-frequency cues focus on local details to highlight small targets, while low-frequency cues provide global information to complement spatial features. Subsequently, the asymmetric cross-domain attention (ACA) is developed to enhance the local central feature extraction, which reflects the typical spatial Gaussian pattern of small targets. Furthermore, we introduce the customized multi-scale receptive contextual Block (MRCB) to capture the long-range information by leveraging diverse dilated convolutions. In addition, the Wasserstein Distance Loss (WDL) is utilized to improve bounding box quality. Extensive experiments on three public datasets including IRSTD-1k, NUDT-SIRST, and NUAA-SIRST confirm the effectiveness of FSCFNet. Notably, FSCFNet surpasses the baseline by 4.7% in precision, 3.3% in recall, and 3.9% in AP@50 on IRSTD-1k, with only a 3.6% increase in parameters. FSCFNet provides a robust solution for real-time infrared surveillance systems under resource-constrained environments. More comparisons are shown in Fig. 1.

27 October 2025
Verified
Conference Paper
Open access
ZCZhiqing Cui
Zhiqing Cui
JYJiahao Yuan
Jiahao Yuan
HWHanqing Wang
Hanqing Wang
YLYanshu Li
Yanshu Li
CDChenxu Du
Chenxu Du
Zhenglong DingZhenglong Ding
Zhenglong Ding

18 March 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Zhenglong DingZhenglong Ding
Zhenglong Ding
WSWan Song
Wan Song
Shu ZhanShu Zhan
Shu Zhan
Tightness defects on sealed vessels, such as filters, may cause serious environment pollution and potential safety hazards, which means that the tightness measurement of sealed vessels cannot be neglected. For the measurement of microleakage, the traditional methods are greatly affected by the ambient temperature, leading to unstable results. In this article, a novel mechanism and method based on deep learning for tightness detection and quantification of the sealed vessels is proposed. First, you only look once (YOLO)v5 network with asymmetric convolution blocks (Ac.Bs) in the backbone network is applied to tightness measurement, which improves the feature extraction capability of small targets. Second, a filling algorithm for eliminating crack (FEC) is reported. In this algorithm, novel horizontal and vertical marking operators are defined, which can accurately obtain geometric and motion parameters of the bubble. Third, a calculation model is established to calculate the volume of the bubble quickly under the premise of known bubble area and motion parameters. Fourth, an automatic dry-type measuring device for measuring leakage has been developed to provide an experimental platform for the measurement framework. Finally, performance testing is performed on an independent dataset. The mean intersection over union (mIoU) of the proposed bubble detection method is 98.74%, the processing time for a single image is 6 ms, and the measurement precision of the system is 0.03 mL. The experimental results demonstrate that the proposed tightness detection mechanism and method can greatly improve the accuracy and stability of tightness detection of sealed vessels, which have good comprehensive performance.

26 May 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
ZCZhiqing Cui
Zhiqing Cui
JYJiahao Yuan
Jiahao Yuan
HXHaibin Xu
Haibin Xu
YWYamei Wei
Yamei Wei
Zhenglong DingZhenglong Ding
Zhenglong Ding
Object detection algorithm in urban traffic using remote sensing images often suffers from high complexity, low real-time performance, and low accuracy. To address these challenges, we propose RTL-Net, an urban traffic object detection network structure based on You Only Look Once (YOLO) v8s. To enhance real-time performance beyond the benchmark, we implemented lightweight designs for the loss function, backbone, neck, and head components. Firstly, a Powerable-IoU (PIoU) loss function was introduced to make the algorithm more suitable for different scales of targets and reduce false detection. Secondly, the Lightweight Shared Convolutional Detection (LSCD) head was replaced to ensure the detection performance and significantly improve the lightweight performance of the algorithm. Additionally, this paper introduces the Dilatation-wise Residual (DWR) module to facilitate the algorithm’s extraction of detailed features. In addition, we optimize the Bidirectional Feature Pyramid Network (Bi-FPN), enabling the fusion of multiple features to improve overall feature integration and performance. The VisDrone2021 dataset was utilized for experimental training. Experimental results demonstrate that the proposed algorithm achieves a significant 43.9% reduction in parameters and an 18.9% decrease in computational complexity. Moreover, the detection accuracy has improved by 2.3%, while maintaining a real-time detection speed of 263.2 frames per second. For edge computing object detection, our method outperforms YOLOv8s and leading remote sensing algorithms in both speed and accuracy, achieving state-of-the-art performance among single-stage detectors with comparable parameters.

14 May 2019 in Microgravity Science and Technology
Verified
Journal Article
Closed access
PDF file
ZYZongjun Yin
Zongjun Yin
Zhenglong DingZhenglong Ding
Zhenglong Ding
XMXuegang Ma
Xuegang Ma
XZXueping Zhang
Xueping Zhang
YXYun Xia
Yun Xia