Jiaqi Jiang

Mr. Jiaqi Jiang

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
14 December 2025
Verified
Conference Paper
Closed access
JZJing Zhang
Jing Zhang
JJJiaqi Jiang
Jiaqi Jiang
XZXiancun Zhou
Xiancun Zhou
ZLZhuangzhuang Liu
Zhuangzhuang Liu
The traditional method for calculating the morphometric parameters of geese is mainly manual, which faces problems such as low efficiency and large errors. This paper proposes a non-contact method that uses a depth camera to obtain 3D point clouds for three-dimensional reconstruction of geese and automatically calculates the morphometric parameters. Firstly, depth images are captured from multiple perspectives using the depth cameras. Then, point cloud matching and 3D reconstruction are completed by using relevant preprocessing methods and the ICP algorithm. Finally, the key anatomical points of the goose body (such as the tip of the beak, tail, sole of the foot) were extracted in combination with morphological features, and the calculation models of parameters such as height, tibial length, semi-diving length, and webbed foot length were constructed. By comparing with the physical model of the measured geese, the accuracy of several body measurements of the geese obtained by the method in this experiment was all above 97%.


3 November 2026 in Animals
Verified
Journal Article
Open access
PDF file
JZJing Zhang
Jing Zhang
JJJiaqi Jiang
Jiaqi Jiang
FLFeixiang Li
Feixiang Li
XZXiancun Zhou
Xiancun Zhou
YZYe Zhang
Ye Zhang
XMXianmeng Meng
Xianmeng Meng
To address low efficiency in manual counting and high costs of data collection and labeling in Landes goose farming, this study developed a simulation-driven video detection and counting method. A three-dimensional simulation environment generated goose scenes under varied densities, perspectives, and lighting conditions, with automatic bounding-box labeling. A YOLO26 detector was pre-trained on the 6000-image training subset of a 10,000-image simulated dataset, which was divided into training, validation, and test subsets at a ratio of 6:2:2 (6000, 2000, and 2000 images, respectively), and was then fine-tuned using 500 real images. A bottom-center trajectory anchor and line-crossing rules were combined with BoT-SORT tracking to construct a detection-tracking-counting pipeline. Evaluation on three real video sequences comprising 1780 reference crossing events yielded an event-level counting accuracy of 99.16% and an aggregate net-count accuracy of 99.38%, with a mean absolute error of 3.7 and a root mean square error of 5.3 across the sequences. In the dense sequence, the predicted count was 1021 against 1030 reference crossings, corresponding to a net-count accuracy of 99.13%. These findings support simulation-assisted training and non-contact line-crossing counting for the evaluated Landes goose passage. Further validation is needed before extending the method to other farm layouts or production environments.