Image-based particle filtering for navigation in a semi-structured agricultural environment

Hiremath, Santosh; Evert, F.K. van; Braak, Cajo J. F. ter; Stein, Alfred; Heijden, G.W.A.M. van der

doi:10.1016/j.biosystemseng.2014.02.010

Cited by 32 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…But this time may signify a collision considering an under canopy vehicle within a nominal 0.8 m width crop lane subject to: (a) unreliable GNSS information; (b) constant sensor occlusions due hanging leaves and weeds; (c) greater effect from soil unevenness; and (d) forward movement about 0.2 m/s. Also in maize field, Hiremath, van Evert, ter Braak, Stein, and van der Heijden () demonstrates an image‐based particle filtering for navigation with a robot that is slightly bigger than ours. But it required a downward‐looking camera at a height of 1.65 m, which limits the use of such method in later crop stages.…”

Section: Related Workmentioning

confidence: 59%

Under canopy light detection and ranging‐based autonomous navigation

Higuti

Velasquez

Magalhães

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

This paper describes a light detection and ranging (LiDAR)-based autonomous navigation system for an ultralightweight ground robot in agricultural fields. The system is designed for reliable navigation under cluttered canopies using only a 2D Hokuyo UTM-30LX LiDAR sensor as the single source for perception. Its purpose is to ensure that the robot can navigate through rows of crops without damaging the plants in narrow row-based and high-leaf-cover semistructured crop plantations, such as corn (Zea mays) and sorghum (Sorghum bicolor). The key contribution of our work is a LiDAR-based navigation algorithm capable of rejecting outlying measurements in the point cloud due to plants in adjacent rows, low-hanging leaf cover or weeds. The algorithm addresses this challenge using a set of heuristics that are designed to filter out outlying measurements in a computationally efficient manner, and linear least squares are applied to estimate within-row distance using the filtered data.Moreover, a crucial step is the estimate validation, which is achieved through a heuristic that grades and validates the fitted row-lines based on current and previous information. The proposed LiDAR-based perception subsystem has been extensively tested in production/breeding corn and sorghum fields. In such variety of highly cluttered real field environments, the robot logged more than 6 km of autonomous run in straight rows. These results demonstrate highly promising advances to LiDARbased navigation in realistic field environments for small under-canopy robots.

show abstract

Section: Related Workmentioning

confidence: 59%

Under canopy light detection and ranging‐based autonomous navigation

Higuti

Velasquez

Magalhães

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…The goal of [84] is to develop an algorithm to autonomously guide a small robotic ground vehicle platform along an orchard row, following the path of the row using an upward looking camera combined with a controller based on feature recognition from the contrast between the tree canopies and the sky. The method presented in [100] is based on a particle filter (PF) using a novel measurement model, where a model image is constructed from the particle and compared directly with the measurement image after elementary processing, such as downsampling, excessive-green filtering and thresholding. Machine vision and laser radar (ladar) are A color image of an orchard is classified into orchard elements by a multilayer feedforward neural network in [95].…”

Section: Vision-based Vehicle Guidance Systems For Agricultural Applimentioning

confidence: 99%

Machine Vision Systems in Precision Agriculture for Crop Farming

et al. 2019

View full text Add to dashboard Cite

Machine vision for precision agriculture has attracted considerable research interest in recent years. The aim of this paper is to review the most recent work in the application of machine vision to agriculture, mainly for crop farming. This study can serve as a research guide for the researcher and practitioner alike in applying cognitive technology to agriculture. Studies of different agricultural activities that support crop harvesting are reviewed, such as fruit grading, fruit counting, and yield estimation. Moreover, plant health monitoring approaches are addressed, including weed, insect, and disease detection. Finally, recent research efforts considering vehicle guidance systems and agricultural harvesting robots are also reviewed.

show abstract

“…For an automated field application using a mobile robot, the estimation of crop rows and out-of-row distance should be automated as well. Algorithms for crop row detection have been presented in several studies (Guerrero et al, 2013;Hiremath, Van Evert, Braak, Stein, & Van der Heijden, 2014;Kise, Zhang, Rovira Más, & Mas, 2005;Leemans & Destain, 2006;Romeo et al, 2012;Søgaard & Olsen, 2003), but these algorithms are likely to introduce noise. Thus, in the current approach, regional index (0.3, 0.6 and 0.9) was used instead of a precise number for the out-ofrow distance to compensate any potential noise.…”

Section: Out-of-row Regional Index (Orri)mentioning

confidence: 99%

Sugar beet and volunteer potato classification using Bag-of-Visual-Words model, Scale-Invariant Feature Transform, or Speeded Up Robust Feature descriptors and crop row information

Suh

Hofstee

IJsselmuiden

et al. 2018

Biosystems Engineering

View full text Add to dashboard Cite

One of the most important steps in vision-based weed detection systems is the classification of weeds growing amongst crops. In EU SmartBot project it was required to effectively control more than 95% of volunteer potatoes and ensure less than 5% of damage of sugar beet. Classification features such as colour, shape and texture have been used individually or in combination for classification studies but they have proved unable to reach the required classification accuracy under natural and varying daylight conditions. A classification algorithm was developed using a Bag-of-Visual-Words (BoVW) model based on Scale-Invariant Feature Transformation (SIFT) or Speeded Up Robust Feature (SURF) features with crop row information in the form of the Out-of-Row Regional Index (ORRI). The highest classification accuracy (96.5% with zero false-negatives) was obtained using SIFT and ORRI with Support Vector Machine (SVM) which is considerably better than previously reported research although its 7% false-positives deviated from the requirements. The average classification time of 0.10-0.11 s met the real-time requirements. The SIFT descriptor showed better classification accuracy than the SURF, but classification time did not vary significantly. Adding location information (ORRI) significantly improved overall classification accuracy. SVM showed better classification performance than random forest and neural network. The proposed approach proved its potential under varying natural light conditions, but implementing a practical system, including vegetation segmentation and weed removal may potentially reduce the overall performance and more research is needed.

show abstract

Image-based particle filtering for navigation in a semi-structured agricultural environment

Cited by 32 publications

References 21 publications

Under canopy light detection and ranging‐based autonomous navigation

Under canopy light detection and ranging‐based autonomous navigation

Machine Vision Systems in Precision Agriculture for Crop Farming

Sugar beet and volunteer potato classification using Bag-of-Visual-Words model, Scale-Invariant Feature Transform, or Speeded Up Robust Feature descriptors and crop row information

Contact Info

Product

Resources

About