For the time-consuming and stressful body measuring task of Qinchuan cattle and farmers, the demand for the automatic measurement of body dimensions has become more and more urgent. It is necessary to explore automatic measurements with deep learning to improve breeding efficiency and promote the development of industry. In this paper, a novel approach to measuring the body dimensions of live Qinchuan cattle with on transfer learning is proposed. Deep learning of the Kd-network was trained with classical three-dimensional (3D) point cloud datasets (PCD) of the ShapeNet datasets. After a series of processes of PCD sensed by the light detection and ranging (LiDAR) sensor, the cattle silhouettes could be extracted, which after augmentation could be applied as an input layer to the Kd-network. With the output of a convolutional layer of the trained deep model, the output layer of the deep model could be applied to pre-train the full connection network. The TrAdaBoost algorithm was employed to transfer the pre-trained convolutional layer and full connection of the deep model. To classify and recognize the PCD of the cattle silhouette, the average accuracy rate after training with transfer learning could reach up to 93.6%. On the basis of silhouette extraction, the candidate region of the feature surface shape could be extracted with mean curvature and Gaussian curvature. After the computation of the FPFH (fast point feature histogram) of the surface shape, the center of the feature surface could be recognized and the body dimensions of the cattle could finally be calculated. The experimental results showed that the comprehensive error of body dimensions was close to 2%, which could provide a feasible approach to the non-contact observations of the bodies of large physique livestock without any human intervention.
The body dimension measurement of large animals plays a significant role in quality improvement and genetic breeding, and the non-contact measurements by computer vision-based remote sensing could represent great progress in the case of dangerous stress responses and time-costing manual measurements. This paper presents a novel approach for three-dimensional digital modeling of live adult Qinchuan cattle for body size measurement. On the basis of capturing the original point data series of live cattle by a Light Detection and Ranging (LiDAR) sensor, the conditional, statistical outliers and voxel grid filtering methods are fused to cancel the background and outliers. After the segmentation of K-means clustering extraction and the RANdom SAmple Consensus (RANSAC) algorithm, the Fast Point Feature Histogram (FPFH) is put forward to get the cattle data automatically. The cattle surface is reconstructed to get the 3D cattle model using fast Iterative Closest Point (ICP) matching with Bi-directional Random K-D Trees and a Greedy Projection Triangulation (GPT) reconstruction method by which the feature points of cattle silhouettes could be clicked and calculated. Finally, the five body parameters (withers height, chest depth, back height, body length, and waist height) are measured in the field and verified within an accuracy of 2 mm and an error close to 2%. The experimental results show that this approach could be considered as a new feasible method towards the non-contact body measurement for large physique livestock.
Remarkable inter-class similarity and intra-class variability of tomato leaf diseases seriously affect the accuracy of identification models. A novel tomato leaf disease identification model, DWTFormer, based on frequency-spatial feature fusion, was proposed to address this issue. Firstly, a Bneck-DSM module was designed to extract shallow features, laying the groundwork for deep feature extraction. Then, a dual-branch feature mapping network (DFMM) was proposed to extract multi-scale disease features from frequency and spatial domain information. In the frequency branch, a 2D discrete wavelet transform feature decomposition module effectively captured the rich frequency information in the disease image, compensating for spatial domain information. In the spatial branch, a multi-scale convolution and PVT (Pyramid Vision Transformer)-based module was developed to extract the global and local spatial features, enabling comprehensive spatial representation. Finally, a dual-domain features fusion model based on dynamic cross-attention was proposed to fuse the frequency-spatial features. Experimental results on the tomato leaf disease dataset demonstrated that DWTFormer achieved 99.28% identification accuracy, outperforming most existing mainstream models. Furthermore, 96.18% and 99.89% identification accuracies have been obtained on the AI Challenger 2018 and PlantVillage datasets. In-field experiments demonstrated that DWTFormer achieved an identification accuracy of 97.22% and an average inference time of 0.028 seconds in real plant environments. This work has effectively reduced the impact of inter-class similarity and intra-class variability on tomato leaf disease identification. It provides a scalable model reference for fast and accurate disease identification.