Autonomous agricultural observation and treatment system to apply precsion treatments to agricultural objects

Abstract

Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an agricultural observation and treatment system and method of operation. The agricultural treatment system may determine a first real-world geo-spatial location of the treatment system. The system can receive captured images depicting real-world agricultural objects of a geographic scene. The system can associate captured images with the determined geo-spatial location of the treatment system. The treatment system can identify, from a group of mapped and indexed images, images having a second real-word geo-spatial location that is proximate with the first real-world geo-spatial location. The treatment system can compare at least a portion of the identified images with at least a portion of the captured images. The treatment system can determine a target object and emit a fluid projectile at the target object using a treatment device.

What is claimed is: 
     
         1 . A method comprising:
 receiving image data comprising one or more images in a real-world agricultural scene;   detecting one or more objects in a first image of the one or more images;   performing object detection on the first image to locate and identify one or more agricultural objects within the first image;   classifying each of the one or more agricultural objects detected including a first classification assigned to a first agricultural object within the first image;   determining a real-world location of the first agricultural object in the real-world agricultural scene;   determining one or more treatment parameters for treating the first agricultural object; and   performing a treatment on the first agricultural object comprising emitting a fluid projectile onto a surface of at least a portion of the first agricultural object.   
     
     
         2 . The method of  claim 1 , further comprising assigning a second classification to a second agricultural object within the first image. 
     
     
         3 . The method of  claim 2 , wherein the second classification of the second agricultural object and the first classification assigned to the first agricultural object are classifications of a same type. 
     
     
         4 . The method of  claim 2 , wherein the second classification of the second agricultural object and the first classification assigned to the first agricultural object are classifications of different types. 
     
     
         5 . The method of  claim 2 , further comprising, determining a plurality of labels for each classification of each of the one or more agricultural objects and assigning a label to each of the one or more agricultural objects. 
     
     
         6 . The method of  claim 5 , further comprising assigning the first agricultural object with a first label and assigning the second agricultural object with a second label. 
     
     
         7 . The method of  claim 6 , wherein the first label and second label are of a same type. 
     
     
         8 . The method of  claim 6 , wherein the first label and the second label are of different types. 
     
     
         9 . The method of  claim 1 , wherein at least one classification of a plurality of different classifications for the one or more agricultural objects corresponds to a stage of growth of a crop. 
     
     
         10 . The method of  claim 1 , wherein detecting one or more objects in the first image comprises image segmentation, edge detection, corner detection, or a combination thereof. 
     
     
         11 . The method of  claim 1 , wherein the one or more treatment parameters for treating the first agricultural object is based, at least in part, on the classification of the of the agricultural object assigned to the first agricultural object. 
     
     
         12 . The method of  claim 1 , wherein the real-world agricultural scene includes real world agricultural objects. 
     
     
         13 . The method of  claim 1 , wherein the one or more images can be received with one or more image sensors including a camera, a depth sensing camera, a 3D camera, an infrared camera, a light detection and ranging (LiDar) sensor, or a combination thereof. 
     
     
         14 . The method of  claim 13 , wherein the one or more images comprise two dimensional (2D) images, three dimensional (3D) images, or a combination thereof. 
     
     
         15 . The method of  claim 13 , further comprising determining a localization and pose of a vehicle supporting the one or more image sensors within a geographic boundary of the real-world agricultural scene. 
     
     
         16 . The method of  claim 13 , further comprising determining a velocity and acceleration of a vehicle supporting the one or more image sensors within a geographic boundary of the real-world agricultural scene. 
     
     
         17 . The method of  claim 15 , wherein the vehicle is moving and the one or more agricultural objects of the real-world agricultural scene are moving targets relative to the vehicle. 
     
     
         18 . The method of  claim 1 , further comprising receiving a set of mapped image data depicting one or more localized agricultural objects. 
     
     
         19 . The method of  claim 18 , further comprising comparing a portion of the first image with a portion of the mapped image data depicting the one or more localized agricultural objects. 
     
     
         20 . The method of  claim 19 , wherein the one or more localized agricultural objects is selected based on comparing the localization of the agricultural objects of the mapped image data and the real-world location of the first agricultural object.