Deere & Company

University of Southern Queensland

Horticulture Innovation Australia Limited

Steven Rees

Richard Allen Humpal

Terence Daniel Pickett

Broughton C Boydell

Tarik Loukili

Travis J Davis

Scott Matthew Buse

Michael P Schlax

Mark Michael Chaney

Akira Mizushima

Matthew Tscharke

Tucker J Schoff

A camera is mounted on the front of a sprayer. Targets are identified from images generated by the camera. The location of the target is identified relative to a nozzle on the sprayer. A control signal is generated to control the timing and duration of actuation of the nozzle.

Front-mount cameras on agricultural sprayer with real-time, on-machine target sensor

An agricultural applicator, that applies material to an agricultural field, includes an on-board, real-time image sensor that senses targets for the material to be applied. A controller controls applicators, such as nozzles or other applicators, to apply the material to the sensed targets.

Agricultural sprayer with real-time, on-machine target sensor

In an agricultural machine vision system for the selective treatment of a field employing a boom deployed sensor and treatment device, the system utilizes at least one image sensor mounted on the boom to produce base image data. A boom angle detector detects boom height which is used to correct the base image data into remapped image data including a region of interest to produce corrected image data producing a regularized image of the region of interests for treatment, independent of boom tilt.

Boom mounted agricultural machine vision perspective correction

Systems and methods are provided for enhancing identification of crop conditions and execution of remedial actions in near real-time. An agricultural vehicle may include a crop analysis system having a computing device and an imaging array for capturing a set of images of a crop. The computing device analyzes images acquired by the imaging array to determine whether a crop experiences a particular condition. The computing device, when a condition is identified, can signal an agriculture machine to perform a remedial action.

Virtual SPAD meter

The automated treatment of agricultural fields allows precise application of treatment to only areas of the field requiring treatment, allowing reduced use of agricultural products such as pesticides and the related reduction in environmental stress. Such automated treatment requires the monitoring of image information of the field to detect objects of interest such as weeds. Such monitoring of image information of the field suffers from the real world problem of shadows cast from the agricultural equipment and/or adjacent trees or structures that cast shadows across the field. Shadows are extracted from the image data by smoothing the data, and developing a shadow mask by employing an intensity histogram and identifying a local minima in the darker intensities of the histogram to identify a shadow threshold. The image areas within the shadow area detected by said mask are then corrected by multiplication with correction coefficients to extract the shadow.

Methods, systems, and devices relating to shadow detection for real-time object identification

The various embodiments herein relate to imaging devices and systems that capture an image of a target object and separately capture light from the light source illuminating the target object to compensate for inconsistent lighting of that object. Some systems have scene cameras to capture the images of the target objects and a separate light capturing camera to capture the light from the light source. Other embodiments relate to a single camera capturing an image of the target object while simultaneously capturing light from the light source.

Imaging device with white balance compensation and related systems and methods

The various embodiments disclosed herein relate to identification of one or more specific objects among several other objects. Certain exemplary implementations relate to systems, methods, and devices for identification of one or more specific plant species among several different plants, especially real-time identification of weed plant species in a real-world environment such as a crop field. Other embodiments relate to identification systems, methods, or devices in combination with action components, such as a spraying system for spraying the weed plants identified in real time.

Growing community of inventors

Top Camp, Australia

Steven Rees