Xiang Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiang Ma has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
Lipengcheng Wan
4 shared publications- Yonglei Li
College of Engineering, China Agricultural University, Beijing 100083, China
4 shared publications Shipu Xu
3 shared publicationsJinqiu Huang
2 shared publicationsJinyu Song
2 shared publicationsMingming An
2 shared publications
Latest Publications
- Open Access
- 23 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8393
YOLO11-FAL: An Improved YOLO11 Model for Tomato Flowering Stage Detection in Greenhouses
Accurate detection of tomato flowering stages is important for greenhouse crop management and automated pollination, but it remains challenging because tomato flowers are small, densely distributed, frequently occluded, and visually similar across adjacent developmental stages. To address these problems, this study proposes YOLO11-FAL, an improved object detection model based on YOLO11 for tomato flowering stage detection in greenhouse environments. The original C3k2 modules are replaced with C3k2_Faster to reduce redundant spatial computation and enhance local structural feature representation. An Attentional Scale Sequence Fusion (ASF) structure is introduced into the neck network to strengthen multi-scale feature interaction, and a Localization Quality Estimation Head (LQEHead) is incorporated to recalibrate classification confidence using bounding-box distribution information. Experiments were conducted on a self-constructed tomato flower dataset containing Bud, Anthesis, and Post-anthesis stages under varying illumination conditions. YOLO11-FAL achieved 92.00% Precision, 88.88% mAP@0.5, 62.21% mAP@0.75, and 56.72% mAP@0.5:0.95. The model contained 2.384 M parameters and achieved 49.58 FPS on an NVIDIA Jetson AGX Orin (NVIDIA Corporation, Santa Clara, CA, USA) using TensorRT FP16, with a measured onboard power consumption of 11.07 W. These results indicate that YOLO11-FAL provides a practical and efficient visual perception approach for greenhouse tomato flowering stage detection.
- 23 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8393
Open AccessYOLO11-FAL: An Improved YOLO11 Model for Tomato Flowering Stage Detection in Greenhouses
Accurate detection of tomato flowering stages is important for greenhouse crop management and automated pollination, but it remains challenging because tomato flowers are small, densely distributed, frequently occluded, and visually similar across adjacent developmental stages. To address these problems, this study proposes YOLO11-FAL, an improved object detection model based on YOLO11 for tomato flowering stage detection in greenhouse environments. The original C3k2 modules are replaced with C3k2_Faster to reduce redundant spatial computation and enhance local structural feature representation. An Attentional Scale Sequence Fusion (ASF) structure is introduced into the neck network to strengthen multi-scale feature interaction, and a Localization Quality Estimation Head (LQEHead) is incorporated to recalibrate classification confidence using bounding-box distribution information. Experiments were conducted on a self-constructed tomato flower dataset containing Bud, Anthesis, and Post-anthesis stages under varying illumination conditions. YOLO11-FAL achieved 92.00% Precision, 88.88% mAP@0.5, 62.21% mAP@0.75, and 56.72% mAP@0.5:0.95. The model contained 2.384 M parameters and achieved 49.58 FPS on an NVIDIA Jetson AGX Orin (NVIDIA Corporation, Santa Clara, CA, USA) using TensorRT FP16, with a measured onboard power consumption of 11.07 W. These results indicate that YOLO11-FAL provides a practical and efficient visual perception approach for greenhouse tomato flowering stage detection.
- Open Access
- 10 August 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 15
An interpretable dual-channel XGBoost-attention model for anomaly detection and fault diagnosis in rice irrigation systems
- 10 August 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 15
Open AccessAn interpretable dual-channel XGBoost-attention model for anomaly detection and fault diagnosis in rice irrigation systems
- Open Access
- 22 May 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 14
Intelligent real-time counting of nursery pigs moving through a hallway based on multi-object detection tracking and cross-line counting
- 22 May 2026
- Published by Elsevier in Smart Agricultural Technology
- Vol. 14
Open AccessIntelligent real-time counting of nursery pigs moving through a hallway based on multi-object detection tracking and cross-line counting
- Open Access
- 15 July 2025
- Published by Elsevier in Agricultural Water Management
- Vol. 317
Intelligent irrigation strategy model for farmland using dung beetle optimization-random forest algorithms
- 15 July 2025
- Published by Elsevier in Agricultural Water Management
- Vol. 317
Open AccessIntelligent irrigation strategy model for farmland using dung beetle optimization-random forest algorithms
- 7 September 2024
- Published by Elsevier in Biosystems Engineering
- Vol. 247, 63-76
Modelling and verification of the liquorice-soil composite based on pulling test
- 7 September 2024
- Published by Elsevier in Biosystems Engineering
- Vol. 247, 63-76
Modelling and verification of the liquorice-soil composite based on pulling test
- Open Access
- 13 September 2023
- Published by MDPI AG in Preprints.org
Vibration Response of Soil under Low-Frequency Vibration Using Discrete Element Method
The vibration response of soil is a key property in the field of agricultural soil tillage. Vibration components of tillage machinery are generally used to reduce tillage resistance and improve work efficiency, the pressure variation under low-frequency vibration will affect the fragmentation and dispersion of farmland soil. However, the gradient of pressure variation, frequency domain response, and effective transmission range are unclear. A new method based on DEM (Discrete Element Method) is presented to study the vibration response and pressure transmission under low-frequency vibration. Bench test results showed that peak pressure positively correlates with the vibration frequency and attenuates rapidly at the vibration distance of 100 to 250 mm. The results data were also selected to determine the simulation model parameters. Amplitude, vibration frequency, and soil depth were used as test factors in single-factor simulation tests, and their effects on the peak pressure, frequency domain response, and effective transmission distance were analyzed. The results showed a positive relationship between the peak pressure and the test factors. The peak pressure increases with a maximum gradient of 19.02 kPa/mm at a vibration distance of 50 mm. The amplitude, vibration frequency, and soil depth positively correlate with the dominant frequency amplitude. The main frequency is independent of amplitude and soil depth. At the vibration distance of 250 mm, the dominant frequency is approximately twice the vibration frequency at 7–11 Hz and approximately equal to the vibration frequency at 13–15 Hz. Multiple exponential functions were used to fit the peak pressure attenuation function, obtaining an effective transmission distance range of 347.15 to 550.37 mm for the 5kPa cut-off pressure. For a soil depth of 300 mm, the vertical shear wave diffusion angle is greater than the horizontal shear wave diffusion angle. The study clarifies the vibration response of soil under low-frequency vibration, which helps to design vibration type soil-engaging components of tillage machinery and match vibration parameters for energy saving and resistance reduction in soil tillage.
- 13 September 2023
- Published by MDPI AG in Preprints.org
Open AccessVibration Response of Soil under Low-Frequency Vibration Using Discrete Element Method
The vibration response of soil is a key property in the field of agricultural soil tillage. Vibration components of tillage machinery are generally used to reduce tillage resistance and improve work efficiency, the pressure variation under low-frequency vibration will affect the fragmentation and dispersion of farmland soil. However, the gradient of pressure variation, frequency domain response, and effective transmission range are unclear. A new method based on DEM (Discrete Element Method) is presented to study the vibration response and pressure transmission under low-frequency vibration. Bench test results showed that peak pressure positively correlates with the vibration frequency and attenuates rapidly at the vibration distance of 100 to 250 mm. The results data were also selected to determine the simulation model parameters. Amplitude, vibration frequency, and soil depth were used as test factors in single-factor simulation tests, and their effects on the peak pressure, frequency domain response, and effective transmission distance were analyzed. The results showed a positive relationship between the peak pressure and the test factors. The peak pressure increases with a maximum gradient of 19.02 kPa/mm at a vibration distance of 50 mm. The amplitude, vibration frequency, and soil depth positively correlate with the dominant frequency amplitude. The main frequency is independent of amplitude and soil depth. At the vibration distance of 250 mm, the dominant frequency is approximately twice the vibration frequency at 7–11 Hz and approximately equal to the vibration frequency at 13–15 Hz. Multiple exponential functions were used to fit the peak pressure attenuation function, obtaining an effective transmission distance range of 347.15 to 550.37 mm for the 5kPa cut-off pressure. For a soil depth of 300 mm, the vertical shear wave diffusion angle is greater than the horizontal shear wave diffusion angle. The study clarifies the vibration response of soil under low-frequency vibration, which helps to design vibration type soil-engaging components of tillage machinery and match vibration parameters for energy saving and resistance reduction in soil tillage.
- 2 January 2023
- Published by Elsevier in Biosystems Engineering
- Vol. 225, 99-117
Optimising the design of ball racks to improve the sorting efficiency of vibrating screen seed cleaners using discrete element method modelling and experiment
- 2 January 2023
- Published by Elsevier in Biosystems Engineering
- Vol. 225, 99-117
Optimising the design of ball racks to improve the sorting efficiency of vibrating screen seed cleaners using discrete element method modelling and experiment