The work is devoted to implementing traditional technologies of visual monitoring of plants for precision agriculture technologies, namely data engineering for the improvement of remote monitoring of marker vegetation indices with the help of UAVs. Classic vegetation indices such as NDVI that used to solve a limited range of problems and them mainly used to adjust the number of nitrogen fertilizers during differentiated treatment of field areas. Such indices are poorly adapted to identify the causes of stress. For stresses of a technical nature, in particular, on winter rapeseed crops, marker indices are used, which, with the traditional model of color formation, are difficult to adjust to identify anomalous coloration of affected plants. In addition, the accuracy of classical indices for the additive color formation model is affected by changes in lighting, increasing the accuracy of anomaly identification requires additional adjustment based on the state of the atmosphere at the time of image acquisition. The purpose of the work is the formation of a new approach to the automation of visual diagnostics of plants, which is based on the adaptation of machine vision technologies to the existing technologies of noncontact expert assessment of plants. A hypothesis was put forward about the possibility of creating vegetation indices based on an alternative model of HSL coloration, which would be more resistant to changes in illumination. The research was carried out on winter wheat crops in April-May 2021, archival images of winter rapeseed crops affected by technological stress taken in 2019 were also used. Photography was carried out using a Phantom 2 UAV in the visible range of the spectrum. Data processing was performed in the MathCad environment. The research was conducted on the resistance to changes in lighting during hardware adjustment of the exposure of images, as well as the features of object identification, namely, healthy and affected leaves and soil in th...