An Image Processing System for Measuring the Weight of A Dairy Cattle

젖소 체중측정을 위한 영상처리 시스템

The objective of this research was to design and construct an image processing system to measure easily and accurately cow's weight. The image processing system was built for a dairy cattle to be measured and estimated it's weight using camera and personal computer. The pixel numbers, which was derived from the image processing system, were counted to estimate the weight of a dairy cattle. They were utilized various was for finding the relationships between pixel numbers and it's real weight. Based on the results of this research the following conclusions were made: 1. It's weight could be estimated by using pixel numbers, which was captured from top and side cameras to measure it. The correlations with tea-view pixel numbers, side-view pixel numbers, superficial area pixel numbers and the volume pixel numbers were 0.909, 0.939, 0.944 and 0.965. 2. 50 cattle was used to execute an experiment with the image processing system, but average errors were big to make out the good relationship between cow's weight and pixel numbers. In order measure accurately a cattle weight, cattle weight, cattle groups would be divided by the age of cattle and further study should be carried out to be based on the results of this research. 3. The average time it took to perform the image processing to be measure it was 10 seconds, but it took 10 minutes for cattle to enter for measuring it's weight into the weighting system.

본 연구는 영상처리를 통한 보다 간편하고 정확한 젖소의 체중측정을 위해 수행되었다. 카메라와 개인용 컴퓨터를 이용하여 젖소의 영상을 받은 후 이의 화소 값들을 이용하였으며, 또한 여러 가지 방법으로 체중과의 관계를 회귀분석 방법을 하였다. 1. 본 실험의 결과 다중회귀식에 의한 계산체중, 화소표면적, 부피와 체증과의 상관계수는 각각 0.9424, 0.9439, 0.9651로 나타났으며, 젖소의 체중과 상관관계도가 높았다. 2. 실험에 이용된 젖소의 개체수를 50두이었지만, 각각 상태별 체형의 차이고 인하여 일관된 회귀식을 적용하기에는 정확도 문제에서 다소 문제가 있었다. 그래서 각 개체군으로 나누어서 연구할 필요가 있을 것으로 판단되었다. 3. 젖소의 체중 계측시간은 10초에 불과하지만 실험장치까지의 유도과정은 편균 한 마리에 10분 정도가 소요되었다.