Jianqiang Lu

Prof. Dr. Jianqiang Lu

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
11 July 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JXJiaxing Xie
Jiaxing Xie
JHJiajun Hua
Jiajun Hua
SCShaonan Chen
Shaonan Chen
PWPeiwen Wu
Peiwen Wu
鹏高鹏 高
鹏 高
Jianqiang LuJianqiang Lu
Jianqiang Lu
Crop classification of large-scale agricultural land is crucial for crop monitoring and yield estimation. Hyperspectral image classification has proven to be an effective method for this task. Most current popular hyperspectral image classification methods are based on image classification, specifically on convolutional neural networks (CNNs) and recurrent neural networks (RNNs). In contrast, this paper focuses on methods based on semantic segmentation and proposes a new transformer-based approach called HyperSFormer for crop hyperspectral image classification. The key enhancement of the proposed method is the replacement of the encoder in SegFormer with an improved Swin Transformer while keeping the SegFormer decoder. The entire model adopts a simple and uniform transformer architecture. Additionally, the paper introduces the hyper patch embedding (HPE) module to extract spectral and local spatial information from the hyperspectral images, which enhances the effectiveness of the features used as input for the model. To ensure detailed model processing and achieve end-to-end hyperspectral image classification, the transpose padding upsample (TPU) module is proposed for the model’s output. In order to address the problem of insufficient and imbalanced samples in hyperspectral image classification, the paper designs an adaptive min log sampling (AMLS) strategy and a loss function that incorporates dice loss and focal loss to assist model training. Experimental results using three public hyperspectral image datasets demonstrate the strong performance of HyperSFormer, particularly in the presence of imbalanced sample data, complex negative samples, and mixed sample classes. HyperSFormer outperforms state-of-the-art methods, including fast patch-free global learning (FPGA), a spectral–spatial-dependent global learning framework (SSDGL), and SegFormer, by at least 2.7% in the mean intersection over union (mIoU). It also improves the overall accuracy and average accuracy values by at least 0.9% and 0.3%, respectively, and the kappa coefficient by at least 0.011. Furthermore, ablation experiments were conducted to determine the optimal hyperparameter and loss function settings for the proposed method, validating the rationality of these settings and the fusion loss function.

27 December 2021 in Agriculture
Verified
Journal Article
Open access
PDF file
鹏高鹏 高
鹏 高
HQHongbin Qiu
Hongbin Qiu
Yubin LanYubin Lan
Yubin Lan
WWWeixing Wang
Weixing Wang
WCWadi Chen
Wadi Chen
Jianqiang LuJianqiang Lu
Jianqiang Lu
Soil moisture is an important factor determining yield. With the increasing demand for agricultural irrigation water resources, evaluating soil moisture in advance to create a reasonable irrigation schedule would help improve water resource utilization. This paper established a continuous system for collecting meteorological information and soil moisture data from a litchi orchard. With the acquired data, a time series model called Deep Long Short-Term Memory (Deep-LSTM) is proposed in this paper. The Deep-LSTM model has five layers with the fused time series data to predict the soil moisture of a litchi orchard in four different growth seasons. To optimize the data quality of the soil moisture sensor, the Symlet wavelet denoising algorithm was applied in the data preprocessing section. The threshold of the wavelets was determined based on the unbiased risk estimation method to obtain better sensor data that would help with the model learning. The results showed that the root mean square error (RMSE) values of the Deep-LSTM model were 0.36, 0.52, 0.32, and 0.48%, and the mean absolute percentage error (MAPE) values were 2.12, 2.35, 1.35, and 3.13%, respectively, in flowering, fruiting, autumn shoots, and flower bud differentiation stages. The determination coefficients (R2) were 0.94, 0.95, 0.93, and 0.94, respectively, in the four different stages. The results indicate that the proposed model was effective at predicting time series soil moisture data from a litchi orchard. This research was meaningful with regards to acquiring the soil moisture characteristics in advance and thereby providing a valuable reference for the litchi orchard’s irrigation schedule.

7 May 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Jianqiang LuJianqiang Lu
Jianqiang Lu
ZWZhiyun Wu
Zhiyun Wu
Yubin LanYubin Lan
Yubin Lan
XDXiaoling Deng
Xiaoling Deng
JHJiewei Huang
Jiewei Huang
The Internet of Things (IoT) and hyperspectral technology have been widely applied in the field of crop disease monitoring. However, the effective integration of these two data modalities remains an exigent challenge. This study concentrates on the litchi downy blight disease and proposes a model that combines IoT and hyperspectral data for precocious prediction utilizing artificial intelligence algorithms.In this model, IoT data is collected by IoT sensor devices. We proposed 15 sensitive feature factors closely related to litchi downy blight and utilized a long short-term memory (LSTM) network to extract serialized features from IoT data. Hyperspectral data is collected by a ground object spectrometer, and the Savitzky–Golay (S–G) algorithm is applied for data preprocessing. The successive projections algorithm (SPA) is utilized for the extraction of spectral features for subsequent modeling and prediction. Finally, a Bayesian probability model predicated on adaptive kernel density estimation is incorporated into the framework, and an adaptive weight algorithm is devised to construct a multimodal data fusion-based predictive model for litchi downy blight affliction. The results show that the proposed model achieves a prediction accuracy of 89.58%, significantly higher than using only environmental data or hyperspectral data. This method effectively integrates IoT, hyperspectral data and artificial intelligence technologies, providing new insights for the application of IoT technology and the development of modern agriculture.

28 May 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
YMYanheng Mai
Yanheng Mai
JZJiaQi Zheng
JiaQi Zheng
泽骆泽丰 骆
泽丰 骆
CYChaoran Yu
Chaoran Yu
Jianqiang LuJianqiang Lu
Jianqiang Lu
廖仲廖 仲樑
廖 仲樑
The development of precision agriculture requires unmanned aerial vehicles (UAVs) to collect diverse data, such as RGB images, 3D point clouds, and hyperspectral images. Recently, convolutional networks have made remarkable progress in downstream visual tasks, while often disregarding the trade-off between accuracy and speed in UAV-based segmentation tasks. The study aims to provide further valuable insights using an efficient model named Taoism-Net. The findings include the following: (1) Prescription maps in agricultural UAVs requires pixel-level precise segmentation, with many focusing solely on accuracy at the expense of real-time processing capabilities, being incapable of satisfying the expectations of practical tasks. (2) Taoism-Net is a refreshingly segmented model, overcoming the challenges of complexity in deep learning, based on minimalist design, which is used to generate prescription maps through pixel level classification mapping of geodetic coordinates (the lychee tree aerial dataset in Guangdong is used for experiments). (3) Compared with mainstream lightweight models or mature segmentation algorithms, Taoism-Net achieves significant improvements, including an improvement of at least 4.8% in mIoU, and manifested a superior performance in the accuracy–latency curve. (4) “The greatest truths are concise” is a saying widely spread by ancient Taoism, indicating that the most fundamental approach is reflected through the utmost minimalism; moreover, Taoism-Net expects to a build bridge between academic research and industrial deployment, for example, UAVs in precision agriculture.

27 November 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Jianqiang LuJianqiang Lu
Jianqiang Lu
WLWeize Lin
Weize Lin
PCPingfu Chen
Pingfu Chen
Yubin LanYubin Lan
Yubin Lan
XDXiaoling Deng
Xiaoling Deng
SLShengfu Luo
Shengfu Luo
At present, learning-based citrus blossom recognition models based on deep learning are highly complicated and have a large number of parameters. In order to estimate citrus flower quantities in natural orchards, this study proposes a lightweight citrus flower recognition model based on improved YOLOv4. In order to compress the backbone network, we utilize MobileNetv3 as a feature extractor, combined with deep separable convolution for further acceleration. The Cutout data enhancement method is also introduced to simulate citrus in nature for data enhancement. The test results show that the improved model has an mAP of 84.84%, 22% smaller than that of YOLOv4, and approximately two times faster. Compared with the Faster R-CNN, the improved citrus flower rate statistical model proposed in this study has the advantages of less memory usage and fast detection speed under the premise of ensuring a certain accuracy. Therefore, our solution can be used as a reference for the edge detection of citrus flowering.

11 March 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Jianqiang LuJianqiang Lu
Jianqiang Lu
JHJiewei Huang
Jiewei Huang
XHXiongzhe Han
Xiongzhe Han
WWWeixing Wang
Weixing Wang
Yubin LanYubin Lan
Yubin Lan
HTHaiyang Tong
Haiyang Tong
Aiming at the problem of multi-sensor fusion, this paper takes litchi downy blight disease as the research object. The disease is influenced by multiple factors, making IoT environmental data collection and analysis vital for disease prediction. Hyperspectral imaging, a non-invasive sensing technology, can detect changes in litchi leaf disease progression. Multispectral remote sensing offers exceptional real-time and large-scale monitoring capabilities for crop disease surveillance and early warning, quickly acquiring comprehensive orchard health data. Environmental data, hyperspectral data, and multi-temporal multispectral imagery were acquired through IoT sensors, ground-based spectrometers, and unmanned aerial vehicle (UAV)-mounted multispectral cameras, respectively. To overcome the limitations of single-source data for optimal detection timing and enhance early disease monitoring accuracy and reliability, we introduced a Cross-Attention Mechanism-based Multi-modal Feature Fusion Network (CAMF-Net). During feature extraction, the Gray-Level Co-occurrence Matrix (GLCM) extracted texture features from multispectral images, the Successive Projections Algorithm (SPA) extracted hyperspectral feature bands, and the Monte Carlo algorithm combined with Pearson correlation coefficient analyzed sensitive environmental factors. By leveraging the fused texture features, hyperspectral bands, and environmental factors, we conducted comparative experiments with seven mainstream models to demonstrate the effectiveness and superiority of the proposed method. The results indicated that, in the testing experiments conducted on the self-built dataset, the average F1-Score and average Accuracy of CAMF-Net reach 91.88% and 92.68%, respectively.