Detection of Plant Saplessness with Image Processing

The importance of ubiquitous computing is gained in the agricultural area. Field servers are developed and used as a remote monitoring tool in recent agricultural industries. The field server handles weather data, measuring and taking photo images for analyzing visualized information. However, image data acquired by the field server is not adequately used for automatic control in current systems even though the conditions of plants, pests and thieves are detected from the images. The purpose of this research is to develop an application which controls peripherals on the basis of features extracted from image data. As our first proposal we developed the farmer support system which pours water to wilting plants automatically. For the system the following methods were used as indicators of wilting plants: 1) the degrees of leaves from center line of processing region to both sides, 2) the area of leaves region, 3) the area of circumscribed quadrangle of the leaves region and 4) the degrees of each leaf. The methods of 1-3 are used for plants of dense leaves. And method the 4) is for plants having sparse leaves. Based on these strategies, experiments were employed on using plants which are observed by a field server located outside. The result of experiments showed that we could detect the wilting of plants by using these image processing methods