Search

Cow lameness is a complex locomotion behaviour, and effective characteristics are the key to identifying early lameness. Machine learning methods were used to quantify the movement of the hooves and head of cows, and they showed the possibility of using the head- and back-hoof linkage features extracted from motion analysis to classify early lameness. Firstly, the key points of the body in the side-view walking videos were tracked by DeepLabCut (DLC). Based on the curves of hoof movement and head swing, the head-hoof linkage pattern was analysed. Second, the curve of cow's back was extracted and the back-hoof linkage feature was built when the hoof touched the ground. At the same time, the movement curves were analysed to extract five other gait characteristics, including asymmetry of stride length, tracking up, asymmetry in the proportion of supporting phase, landing speed, and moving speed. Multiple models were trained on a dataset containing 212 videos, and 10-fold cross-validation was used to verify the performance of the algorithm. The classification performance was improved by optimising the model and algorithm. Overall accuracy and recall were 89.2% and 90.7%, respectively. The scores of the importance of features calculated by the Chi-square test showed that the head- and back-hoof linkage features play an important role in the classification of early lame cows. The hooves and their linkage features with the head and back of cows proposed in this paper can thus effectively detect early lameness in cows. • DeepLabCut was used to track four hooves and head of walking cow. • Head- and back-hoof linkage features was analysed. • Seven lameness indicators were used to build the model. • The recall of classification for early lame cows was 90.7%. [ABSTRACT FROM AUTHOR]

To control the key structures vibration of combine harvesters, e.g. the driver's seat, the partial coherence mode of the cutter driving system has been set up based on the structural model. The vibration of the cutter is transmitted to the cutting platform through three connection positions - the cutter chute, the rocker shaft seat and the middle shaft seat of the header. For the three junction points from the cutter system to the cutting platform, the time-domain and frequency-domain characteristics of the vibration response are measured and analysed. The main exciting source sequence of Y direction vibration on seat fixing point is considered as the Y direction of cutter chute, Y direction of rocker shaft, Y direction of the middle shaft of the header, and Z direction of cutter chute. Moreover, the correctness of the order above is verified using partial-coherence method. Considering that the cutter chute is the main source, a nut with a rubber sleeve is designed to reduce the vibration transformed from cutter bar to chute. The experiment has verified that this method is able to reduce the Y direction vibration intensity of the seat fixing points by 10.78%. • Determine vibration transmitted to the platform through 3 connecting positions. • Partial-coherence method used to order the methods of vibration transmission. • Nut with rubber sleeve used to reduce vibration transmission from cutter bar to chute. [ABSTRACT FROM AUTHOR]

Image processing technology has been used in precision dairy farming to support management decisions. Vision-based animal identification systems can become a potential alternative to RFID. In this paper, a vision system is proposed to extract body images and identify Holstein cows. Side view videos of dairy cattle walking in a straight line were collected. Cow mask was detected using Adaptive SOM method. The largest inscribed rectangle was extracted to locate the cow's body area. A total of 528 videos were collected from 66 cows, and 3 videos were randomly selected for each cow to build template datasets, while the rest of the videos were used as test data. Feature points of the body image were extracted and matched with the template dataset to identify the unknown cow. Four feature extraction methods and two matching methods were investigated and evaluated. The results showed that the highest identification accuracy was 96.72% when the FAST, SIFT and FLANN methods were used for feature extraction, descriptor, and matching, respectively. However, the combination of ORB and BruteForce had better computational efficiency on the basis of high accuracy. Software was implemented and can realise accurate identification of dairy cattle in real-time. • Vision system for dairy cow individual identification is proposed. • Body image of cows was extracted automatically. • An identification model was designed on the basis of ACE-V principle. • Accuracy of one-step match is 95.41% using ORB features. [ABSTRACT FROM AUTHOR]

Appropriate discrete element modelling (DEM) parameters are essential for accurate prediction of soil properties and disturbance. This study aims to provide an efficient method for accurately determining DEM parameters of a loose cohesive soil in a range of soil conditions. DEM parameters of the loose cohesive soil modelled using hysteretic spring and linear cohesion contact models were determined by a combination of Plackett–Burman, steepest ascent and central composite tests. The accuracies of DEM models developed under different soil moisture contents (0.27–22%) were evaluated using slumping angle of repose test and funnelling angle of repose test. Heap angles under different soil moisture contents decreased quadratically with time with determination coefficients ranging from 0.750 to 0.969. For the given soil, friction or rolling friction coefficient of soil–soil changed with a cubic function as moisture content increased. Similar coefficients of friction (0.23–0.25) and rolling friction (0.038–0.049) of soil–soil were found for moisture contents from 12 to 22%. Based on ANOVA outputs, soil properties tested were significantly affected by soil moisture content at p < 0.05, including angle of repose (AOR), releasing time, yield strength of soil and coefficients of friction and rolling friction of soil-steel. Low relative errors (<2.8%) were found for simulated AORs using developed soil DEM models under different soil moisture contents. Simulated releasing time agreed well with high-speed video measurements. The suggested method has good potential to accurately determine DEM parameters for loose cohesive soils in a range of conditions. • An efficient method for determining cohesive soil DEM parameters has been developed. • Method has potential to accurately determine DEM parameters for loose cohesive soil. • Soil DEM models with 7 levels of moisture content were calibrated using method. • Relationships between moisture content and soil properties crucial for field models. [ABSTRACT FROM AUTHOR]