This paper presents an approach towards the autonomous collaboration between unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV) for weed classification and detection. The paper outlines the development of an infrastructure for continued work towards a sustainable solution. RGB and multispectral data of a strawberry crop field infested with weeds were collected from UAVs. Fully convolutional neural network (U-Net v2) was employed in an effort to create a real-time capable onsite segmentation engine.
Using a combination of images collected from UAVs and highly accurate location information, target species were identified and isolated to efficiently generate a large dataset of images, which were then used to train a robust and state-of- the-art classifier. A highly sanitized dataset was used to effectively extract and augment a large amount of data without the need for manually labeling or outsourcing. The trained bounding box classifier were hosted onsite for real-time inferencing capabilities. In the proposed solution, a UAV surveys the areas of interest and transmits the images to the computing unit to detect and determine the presence of invasive weeds using the trained classifier. Positively identified locations by the UAV is stored for further investigation by the UGV. The UGV is equipped with high a precision IMU/GPS for the autonomous routing to the target location. After arriving at the target location, the UGV utilizes the onboard camera to confirm the presence of the invasive weed species. The UGV is equipped with a highly maneuverable robotic manipulator.
ACCESS THE FULL ARTICLE
No SPIE Account? Create one

refine by

SEARCH WITHIN
PRESENTATIONS
YEAR -
Range
Single Year
CONFERENCE NAME -
TECHNOLOGY -
KEYWORDS -
ACCESS -
CONTENT TYPE -

View Details
Just Watched
17:19
18 December 2024
Exploring non-linear absorptance in Ta2O5, HfO2, and SiO2 oxcide coatings: a comparative analysis
Vladimir Pervak, et al.

View Details
Just Watched
29:19
18 December 2024
Vectorial control of ultrafast pulses using dielectric metasurfaces
Amit Agrawal, et al.

View Details
Just Watched
18:22
18 December 2024
Investigating the lifetime of dielectric coatings: the role of absorption
Erikas Atkočaitis, et al.

View Details
Just Watched
28:39
18 December 2024
Ultrafast laser-irradiated silica: from excited-state dynamics to nanostructuring
Jean-Philippe Colombier, et al.

View Details
Just Watched
15:19
18 December 2024
Synthesis, characterization, and blade-coating of amorphous silica nanotubes for bottom-up assembly of mesomorphic ceramic waveplates
Mitchell Anthamatten, et al.

View Details
Just Watched
14:52
18 December 2024
Damage growth prediction study with multi-modal characterization
Jae Hyuck Yoo, et al.

View Details
Just Watched
20:11
18 December 2024
Development of waveplates with spatially controlled birefringence based on glancing-angle deposition coatings
Marcela Mireles Ramirez, et al.

View Details
Just Watched
24:52
18 December 2024
Polarization beam shaping by ultrafast laser nanostructuring of glass for high power laser applications
Peter Kazansky, et al.

View Details
Just Watched
47:45
20 November 2024
Tracking Earth’s ice from space
Andrew Shepherd, et al.

View Details
Just Watched
38:40
16 November 2024
Sensing in the second quantum revolution
Francesco Saverio Cataliotti, et al.

View Details
Just Watched
27:05
16 November 2024
Imaging and sensing that delivers operational advantage
Jason Field, et al.

View Details
Just Watched
34:55
13 November 2024
Addressing Moore's law challenges to unleash AI opportunities
Christophe Fouquet, et al.

View Details
Just Watched
39:49
13 November 2024
From system on a chip to system of chips: hyperconvergence in design and manufacturing
Srinivas Raghvendra, et al.

View Details
Just Watched
35:44
13 November 2024
Effects of hyperbolic metamaterials on the photophysics of organic semiconductors (Conference Presentation)
Jean Charles Ribierre, et al.

View Details
Just Watched
31:06
13 November 2024
Exposure tool and ecosystem status for 0.55NA EUV lithography
Mark Phillips, et al.

View Details
Just Watched
12 November 2024
EUV mask technologies: evolution and ecosystem for devices
Jin Choi, et al.
Sort By
Display

Loading...
Please refine your search query.