A cost-effective imaging system for monitoring poultry behaviour in small-scale kenyan poultry sheds

J.D.K. Morgan¹, S. Peets¹* and E. Mashatise²

¹Harper Adams University, Engineering Department, TF10 8NB Newport, United Kingdom
²Harper Adams University, Agriculture and Environment Department, TF10 8NB Newport, United Kingdom
*Correspondence: speets@harper-adams.ac.uk

Abstract:

The objective of this paper was to develop a low-cost prototype poultry behaviour imaging and analysis system for monitoring intensively-reared flocks suitable for small-scale Kenyan poultry sheds. An image processing and analysis programme was developed using Python programming language and the OpenCV image processing package. This was tested on overhead images of Ross 308 birds collected over a number of days using a Raspberry Pi V2 camera. A second experiment using toy-chicks was conducted with an angled camera (Wansview W3). Linear transformation (LT) and background subtraction (BS) methods were applied and compared for effectiveness at detecting yellow and brown toy-chicks on woodchip bedding. Perspective transformation (PT) was applied and evaluated for its ability to transform the angled images into two-dimensional views. In the first experiment, where white birds were detected against a dark background, LT object detection successfully detected 99.8% of birds in the sampled images. However, in the second experiment, the LT method was just 56.5% effective at detecting the yellow toy-chicks against the light-coloured background. In contrast, the BS method was more effective, detecting 91.5% of the yellow toy-chicks. The results showed that BS detection success was worse for yellow toy-chicks in the far section, detecting 83% as opposed to 100% of those in the near-section. Edge processing of the image processing algorithm was tested on a Raspberry Pi 3 series B+ computer. This prototype provides a solid foundation for further development and testing of low-cost, automated poultry monitoring systems capable of reporting on thermal comfort inferred from cluster index.

Key words:

background subtraction, cluster index, image processing, linear transformation, poultry

Performance optimization of a rotary mower using Taguchi method

S. Saeid Hosseini and Mohsen Shamsi

Department of mechanics of Agricultural Machinery, Shahid Bahonar University of
Kerman, Kerman, Iran; e-mail: saeid_hossaini@yahoo.com

Abstract:

Optimum energy consumption and prevention of energy losses are important issues in various fields including agricultural engineering. Mower is one of the agricultural machineries that can waste too much energy if does not function properly. In this study, the performance of a single disc rotary mower was studied and optimized by measurement of cutting quality of the stem cross section (cutting quality) as a criterion. Taguchi L9 orthogonal arrays table was used to find the optimum combination of parameters to reach the best cutting quality. The selected factors are: mower forward velocity, disc rotational speed, number of disc blades and shape of the blade, each one at 3 different levels. To measure the quality of the cut hay, ENVI image processing software was used. This software has been developed for texture qualification of image processing studies. The texture of the images captured from the cross section of cut stems by the mower is analyzed according to the reflected wavelength from the surface. ENVI software assigns a number to the cutting quality of each stem, which is called eigenvalue. The results then were imported to the orthogonal arrays table of the Taguchi method. Minitab software was used to calculate the optimal level of the studied variables. Analysis of the results show that 886 rpm of the disc rotational speed, 1m s-1 of the forward speed, four symmetrical triangular serrated blades on the mower disc are the optimal values of the factors and offer the highest cutting quality. The optimum value predicted by the Taguchi method was approved by an experimental method.

Key words: