Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Online detection of abnormal chicken manure based on machine vision

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2021 ASABE Annual International Virtual Meeting  2100188.(doi:10.13031/aim.202100188)
Authors:   Junhui Zhu, Min Zhou
Keywords:   Chicken poop, Image Processing, Machine vision, Module matching, Online detection.

Abstract. The excretion status of livestock and poultry is one of the important indicators to monitor their health status. At present, in the stacked chicken coop, the inspectors make preliminary judgment on the health status of chickens by observing the color and trait of chicken feces on the manure belt daily. However, this monitoring method is highly subjective and disturbing to the chickens. In this paper, we propose a chicken manure image recognition method based on machine vision online monitoring to make preliminary judgments on chicken health status. The method firstly preprocesses the online collected chicken manure images, and makes preliminary judgment on abnormal chicken manure by color extraction algorithm, extraction of abnormal area contour detection, calculation of area ratio and comparison with pre-set threshold; then adopts module matching algorithm and analyzes and compares the grayscale characteristics of the sample and the image to be tested to make further judgment on whether the chicken manure is normal or not. The test shows that the method is effective for online monitoring of images with abnormal chicken droppings, and can initially determine the health condition of chickens.

(Download PDF)    (Export to EndNotes)