Implementation of machine vision for detecting behaviour of cattle and pigs

Lameness has contributed to reproductive inefficiency and increased the risk of culling in dairy cows. We developed a 5-point lameness scoring system that assessed gait and placed a novel emphasis on back posture. Our objective was to determine if this system predicted future reproductive performance and the risk of culling. The study was conducted at a commercial dairy farm with a history of declining reproductive efficiency and an increasing prevalence of lameness. A total of 66 primipara and pluripara calved, received an initial lameness score, and completed their 60-d voluntary waiting period. The overall prevalence of lameness (mean lameness score >2) was 65.2%. Scoring continued at 4-wk intervals and ceased with conception or culling. The percentage of cows confirmed pregnant and culled was 77.3 and 22.7, respectively. For each reproductive endpoint, a 2 x 2 table was constructed with lameness score >2 as the positive risk factor and either performance greater than the endpoint mean or being culled as the positive disease or condition. Positive and negative predictive values, relative risk, Chisquare statistic and regression analysis were used to evaluate the data. The positive predictive values for days to first service, days open, breeding herd days, services per pregnancy and being culled were 58, 68, 65, 39 and 35%, respectively. Similarly, the negative predictive values were 79, 96, 100, 96 and 100%, respectively. Except for one reproductive endpoint, the total number of services, all linear regressions were significant at P 2 predicted that a cow would have extended intervals from calving to first service and to conception, spend or be assigned to (explained herein) more total days in the breeding herd, require more services per pregnancy and be 8.4 times more likely to be culled. We believe that this lameness scoring system effectively identifies lame cows. Observation of the arched-back posture in a standing cow (> or =LS 3) should trigger corrective interventions.

With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual (RGB) sensing has become available for widespread use. The complementary nature of the depth and visual information provided by the Kinect sensor opens up new opportunities to solve fundamental problems in computer vision. This paper presents a comprehensive review of recent Kinect-based computer vision algorithms and applications. The reviewed approaches are classified according to the type of vision problems that can be addressed or enhanced by means of the Kinect sensor. The covered topics include preprocessing, object tracking and recognition, human activity analysis, hand gesture analysis, and indoor 3-D mapping. For each category of methods, we outline their main algorithmic contributions and summarize their advantages/differences compared to their RGB counterparts. Finally, we give an overview of the challenges in this field and future research trends. This paper is expected to serve as a tutorial and source of references for Kinect-based computer vision researchers.

Since the 1980s, efforts have been made to develop sensors that measure a parameter from an individual cow. The development started with individual cow recognition and was followed by sensors that measure the electrical conductivity of milk and pedometers that measure activity. The aim of this review is to provide a structured overview of the published sensor systems for dairy health management. The development of sensor systems can be described by the following 4 levels: (I) techniques that measure something about the cow (e.g., activity); (II) interpretations that summarize changes in the sensor data (e.g., increase in activity) to produce information about the cow's status (e.g., estrus); (III) integration of information where sensor information is supplemented with other information (e.g., economic information) to produce advice (e.g., whether to inseminate a cow or not); and (IV) the farmer makes a decision or the sensor system makes the decision autonomously (e.g., the inseminator is called). This review has structured a total of 126 publications describing 139 sensor systems and compared them based on the 4 levels. The publications were published in the Thomson Reuters (formerly ISI) Web of Science database from January 2002 until June 2012 or in the proceedings of 3 conferences on precision (dairy) farming in 2009, 2010, and 2011. Most studies concerned the detection of mastitis (25%), fertility (33%), and locomotion problems (30%), with fewer studies (16%) related to the detection of metabolic problems. Many studies presented sensor systems at levels I and II, but none did so at levels III and IV. Most of the work for mastitis (92%) and fertility (75%) is done at level II. For locomotion (53%) and metabolism (69%), more than half of the work is done at level I. The performance of sensor systems varies based on the choice of gold standards, algorithms, and test sizes (number of farms and cows). Studies on sensor systems for mastitis and estrus have shown that sensor systems are brought to a higher level; however, the need to improve detection performance still exists. Studies on sensor systems for locomotion problems have shown that the search continues for the most appropriate indicators, sensor techniques, and gold standards. Studies on metabolic problems show that it is still unclear which indicator reflects best the metabolic problems that should be detected. No systems with integrated decision support models have been found.