Apple crop-load estimation with over-the-row machine vision system

Gongal, Aleana; Silwal, Abhisesh; Amatya, Suraj; Karkee, Manoj; Zhang, Q.; Lewis, K.M.

doi:10.1016/j.compag.2015.10.022

Cited by 123 publications

(97 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the accuracy of fruit detection is substantially limited by the occlusion of fruit in canopy images by leaves, branches, and other fruit (Gongal et al, 2015). A number of research projects have been carried out in the past to accurately detect fruit in similar outdoor environments.…”

Section: Sensors and Systems For Fruit Detectionmentioning

confidence: 99%

“…Application of TOF camera in agricultural automation has been investigated for 3D reconstruction of apple trees , determination of interplant spacing (Nakarmi and Tang, 2012) as well as for localization of fruit in trees (Gongal et al, 2015). Gongal et al (2015) used a TOF camera to determine 3D coordinates of fruit in apple trees trained to a narrow fruiting wall in Washington State. The 3D coordinate information was used to identify repeated apples that were visible in images captured from two opposite sides of the tree canopy.…”

Section: Time-of-flight (Tof) Of Light-based 3d Camerasmentioning

confidence: 99%

See 1 more Smart Citation

Sensors and systems for fruit detection and localization: A review

Gongal

Amatya

Karkee

et al. 2015

Computers and Electronics in Agriculture

Self Cite

447

244

View full text Add to dashboard Cite

Section: Sensors and Systems For Fruit Detectionmentioning

confidence: 99%

Section: Time-of-flight (Tof) Of Light-based 3d Camerasmentioning

confidence: 99%

Sensors and systems for fruit detection and localization: A review

Gongal

Amatya

Karkee

et al. 2015

Computers and Electronics in Agriculture

Self Cite

447

244

View full text Add to dashboard Cite

“…An end‐to‐end solution to this problem involves solving multiple subproblems such as fruit detection, counting, tracking fruits across multiple views, and merging fruit counts from both sides of a row. Many approaches strive to solve this problem—Some rely on specialized sensors and hardwares (Das et al, ; Gongal et al, ), and some correlate fruit counts from a single side to ground truth (Stein et al, ). In contrast to these works, we follow the approach proposed by Dong, Roy, and Isler () and Roy, Dong, et al ().…”

Section: Problem Formulation and Overview Of The Entire Systemmentioning

confidence: 99%

A comparative study of fruit detection and counting methods for yield mapping in apple orchards

Häni

Roy

Isler

2019

Journal of Field Robotics

119

View full text Add to dashboard Cite

We present a modular end‐to‐end system for yield estimation in apple orchards. Our goal is to identify fruit detection and counting methods with the best performance for this task. We propose a novel semantic segmentation‐based approach for fruit detection and counting and perform extensive comparative analysis against other state‐of‐the‐art techniques. This is the first work comparing multiple fruit detection and counting methods head‐to‐head on the same data sets. Fruit detection results indicate that the semisupervised method, based on Gaussian Mixture Models, outperforms the deep learning‐based methods in the majority of the data sets. For fruit counting though, the deep learning‐based approach performs better for all of the data sets. Combining these two methods, we achieve yield estimation accuracies ranging from 95.56% to 97.83%.

show abstract

“…The calibration algorithm provided the intrinsic camera parameters including focal length (F), principal point (C) and distortion coefficient (k) (skew coefficient for radial and tangential distortions). Using these intrinsic parameters, a stereo calibration was performed to determine extrinsic camera parameters, which included rotation (R) and translation (T) vectors of the 3D camera with respect to the RGB camera [24,25]. For more details on co-registration process used in this work, please refer to [25].…”

Section: Co-registration Of Depth and Rgb Imagesmentioning

confidence: 99%

“…Using these intrinsic parameters, a stereo calibration was performed to determine extrinsic camera parameters, which included rotation (R) and translation (T) vectors of the 3D camera with respect to the RGB camera [24,25]. For more details on co-registration process used in this work, please refer to [25].…”

Section: Co-registration Of Depth and Rgb Imagesmentioning

confidence: 99%

Automated Detection of Branch Shaking Locations for Robotic Cherry Harvesting Using Machine Vision

et al. 2017

View full text Add to dashboard Cite

Automation in cherry harvesting is essential to reduce the demand for seasonal labor for cherry picking and reduce the cost of production. The mechanical shaking of tree branches is one of the widely studied and used techniques for harvesting small tree fruit crops like cherries. To automate the branch shaking operation, different methods of detecting branches and cherries in full foliage canopies of the cherry tree have been developed previously. The next step in this process is the localization of shaking positions in the detected tree branches for mechanical shaking. In this study, a method of locating shaking positions for automated cherry harvesting was developed based on branch and cherry pixel locations determined using RGB images and 3D camera images. First, branch and cherry regions were located in 2D RGB images. Depth information provided by a 3D camera was then mapped on to the RGB images using a standard stereo calibration method. The overall root mean square error in estimating the distance to desired shaking points was 0.064 m. Cherry trees trained in two different canopy architectures, Y-trellis and vertical trellis systems, were used in this study. Harvesting testing was carried out by shaking tree branches at the locations selected by the algorithm. For the Y-trellis system, the maximum fruit removal efficiency of 92.9% was achieved using up to five shaking events per branch. However, maximum fruit removal efficiency for the vertical trellis system was 86.6% with up to four shakings per branch. However, it was found that only three shakings per branch would achieve a fruit removal percentage of 92.3% and 86.4% in Y and vertical trellis systems respectively.

show abstract

Apple crop-load estimation with over-the-row machine vision system

Cited by 123 publications

References 11 publications

Sensors and systems for fruit detection and localization: A review

Sensors and systems for fruit detection and localization: A review

A comparative study of fruit detection and counting methods for yield mapping in apple orchards

Automated Detection of Branch Shaking Locations for Robotic Cherry Harvesting Using Machine Vision

Contact Info

Product

Resources

About