Search

In this paper we present the method and performance to detect tomato whitefly and its predatory bugs on yellow sticky traps. These traps are imaged in controlled light conditions with a digital single lens reflex camera and in uncontrolled environment with smartphone camera. The method consists of the following steps. First, image sub setting and data labelling by manual annotation. Secondly, training a deep learning convolutional neural network. Third step is classification of the images. Final step is comparison with hand counted data of insects. The weighted averaged accuracy for deep learning detected insects was 87.4%. The correlation of hand counted insects with deep learning counted insects was over 0.95 for the smartphone images. The methods used show that the training data used on controlledconditions could be transferred to uncontrolled smartphone imaging conditions for the data provide

Robust plant image segmentation under natural illumination condition is still a challenging process for vision-based agricultural applications. One of the challenging aspects of natural condition is the large variation of illumination intensity. Illumination condition in the field continually changes, depending on the sunlight intensity, position, and moving clouds. This change affects RGB pixel values of acquired image and leads to inconsistent colour appearance of plant. Within this condition, plant segmentation based on RGB indices mostly produces poor threshold result. Besides, when shadows are presented in the scene, which is not uncommon in the field, plant segmentation becomes even more challenging. Excessive green (ExG) and other RGB indices have been widely used for plant image segmentation. Although ExG based segmentation is generally accepted as one of the most common and effective methods, it often provides poor segmentation results especially when the image scene contains an extreme illumination difference caused by dark shadows. To build an automated mobile weed control system, within the framework of the SmartBot project with the focus on the detection and control of volunteer potatoes in sugar beet, the vision-based system should first be able to detect plants out from the soil background even under dark shadow region. The objective of this research was to evaluate the segmentation robustness of illuminationinvariant transformation in comparison with ExG method under natural illumination conditions. Using illumination-invariant transformation, global and local thresholds (Otsu with reconstruction) were assessed to segment plant images. The ground shadow detection process was implemented to remove ground shadow region and background. Global threshold outperformed ExG, and local threshold could effectively remove the soil background region. Even under extreme illumination difference in a scene including sharp dark shadows due to bright sunshine, the illumination-invariant transformation produced robust segmentation results.