S. S. Mehta
YOU?
Author Swipe
Deep Orange: Mask R-CNN based Orange Detection and Segmentation Open
The objective of this work is to detect individual fruits and obtain pixel-wise mask for each detected fruit in an image. To this end, we presents a deep learning approach, named Deep Orange, to detection and pixel-wise segmentation of fru…
On Achieving Bounded Harvest Times in Robotic Fruit Harvesting: A Finite-Time Visual Servo Control Approach Open
To improve commercial feasibility of robotic harvesters, it is utmost important to reduce and be able to guarantee harvesting times. A significant portion of this responsibility is on the control system. Current visual servo control method…
Risk-averse Optimization for Improving Harvesting Efficiency of Autonomous Systems through Human Collaboration Open
Autonomous systems operating in unstructured and complex agricultural environments are susceptible to errors leading to uncertain losses in the efficiency of the system. In robotic harvesting, these losses would translate into lower harves…
Adaptive Visual Servo Control of Robotic Harvesting Systems Open
Harvesting efficiency is a critical factor in determining whether robotic harvesting can be economically superior to hand picking. One practical challenge in robotic harvesting is to grasp a moving fruit, where unsuccessful pick cycles may…
Multi-camera Fruit Localization in Robotic Harvesting Open
Motivated by an effort to study layered vision systems for robotic harvesting, this paper investigates the problem of fruit localization using multiple cameras in the fruit detection layer of the vision system. A pseudo stereo-vision appro…