Accurate and timely detection of plant diseases can help mitigate the worldwide losses experienced by the horticulture and agriculture industries each year. Thermal imaging provides a fast and non-destructive way of scanning plants for diseased regions and has been used by various researchers to study the effect of disease on the thermal profile of a plant. However, thermal image of a plant affected by disease has been known to be affected by environmental conditions which include leaf angles and depth of the canopy areas accessible to the thermal imaging camera. In this paper, we combine thermal and visible light image data with depth information and develop a machine learning system to remotely detect plants infected with the tomato powdery mildew fungus Oidium neolycopersici. We extract a novel feature set from the image data using local and global statistics and show that by combining these with the depth information, we can considerably improve the accuracy of detection of the diseased plants. In addition, we show that our novel feature set is capable of identifying plants which were not originally inoculated with the fungus at the start of the experiment but which subsequently developed disease through natural transmission.

No abstract

Graphical abstract

The ectoparasitic mite Varroa destructor is considered one of the greatest threats to the honeybee Apis mellifera. To successfully manage mite populations residing in the colony, beekeepers must stay informed of infestation levels in their apiaries. The remote, non-destructive detection of Varroa mites in honeybee hives would therefore be highly desirable.Here we show that an ultra-sensitive (1000 mV/g) accelerometer can detect vibrational waveforms originating from one individual mite. We further focus on a commonly observed pulsing behaviour never before described, characterising its physical features, periodicity and strength. The spectral features of the detected pulses strongly depend on the substrate on which they are produced. The characteristics of the vibrational pulse, particularly its repeatability and strength, indicate that mite vibrations could be successfully detected in a fully populated honeybee hive. These features, combined with the remarkably high varroa muscular power output (up to 810nW) indicate that this pulse may be functional for the mite. Our results uncover an exciting novel behaviour and provide a foundation for the remote detection of mites in beehives using vibration capture.