Automatic model based dataset generation for fast and accurate crop and weeds detection

@article{Cicco2017AutomaticMB,
  title={Automatic model based dataset generation for fast and accurate crop and weeds detection},
  author={Maurilio Di Cicco and Ciro Potena and Giorgio Grisetti and Alberto Pretto},
  journal={2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2017},
  pages={5188-5195}
}
  • M. D. Cicco, Ciro Potena, +1 author A. Pretto
  • Published 9 December 2016
  • Computer Science
  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Selective weeding is one of the key challenges in the field of agriculture robotics. To accomplish this task, a farm robot should be able to accurately detect plants and to distinguish them between crop and weeds. Most of the promising state-of-the-art approaches make use of appearance-based models trained on large annotated datasets. Unfortunately, creating large agricultural datasets with pixel-level annotations is an extremely time consuming task, actually penalizing the usage of data-driven… Expand
Data Augmentation Using GANs for Crop/Weed Segmentation in Precision Farming
TLDR
This work tackles the crop/weed segmentation problem by using a synthetic image generation method to augment the training dataset without the need of manually labelling the images, and shows that the method well generalizes across multiple architectures. Expand
Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images
TLDR
This paper proposes a novel fully automatic learning method using convolutional neuronal networks (CNNs) with an unsupervised training dataset collection for weed detection from UAV images that is comparable to traditional supervised training data labeling. Expand
Real-Time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNs
TLDR
This paper addresses the problem of CNN-based semantic segmentation of crop fields separating sugar beet plants, weeds, and background solely based on RGB data and proposes a CNN that exploits existing vegetation indexes and provides a classification in real time. Expand
Fully Convolutional Networks With Sequential Information for Robust Crop and Weed Detection in Precision Farming
TLDR
A novel crop-weed classification system that relies on a fully convolutional network with an encoder-decoder structure and incorporates spatial information by considering image sequences is proposed, which shows that the system generalizes well to previously unseen fields under varying environmental conditions. Expand
Deep Learning with unsupervised data labeling for weeds detection on UAV images
TLDR
A novel fully automatic learning method using Convolutional Neuronal Networks (CNNs) with unsupervised training dataset collection for weeds detection from UAV images, which is comparable to the traditional supervised training data labeling. Expand
Real-Time Crop Recognition in Transplanted Fields With Prominent Weed Growth: A Visual-Attention-Based Approach
TLDR
The results indicate that the proposed method has the potential to provide an efficient solution for recognizing crop plants, even in the presence of severe weed growth. Expand
Semi-supervised online visual crop and weed classification in precision farming exploiting plant arrangement
TLDR
This paper exploits the fact that most crops are planted in rows with a similar spacing along the row, which can be used to initialize a vision-based classifier requiring only a minimal amount of training data through a semi-supervised approach to solve the problem of separating crops from weeds reliably. Expand
weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming
TLDR
An approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV) using the recently developed encoder–decoder cascaded convolutional neural network, SegNet, that infers dense semantic classes while allowing any number of input image channels and class balancing with sugar beet and weed datasets. Expand
Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming
TLDR
Quantitative experiments show that the proposed conditional GAN model is capable of generating realistic multi-spectral images of plants and improves the segmentation performance of state-of-the-art semantic segmentation Convolutional Networks. Expand
Crop and Weed Classication Using Pixel-wise Segmentation on Ground and Aerial Images
Articial Intelligence (AI) is a key tool in agriculture for implementing sus- tainable strategies for weed control. In traditional weed control, the agro-chemical inputs are uniformly applied to theExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Fast and Accurate Crop and Weed Identification with Summarized Train Sets for Precision Agriculture
TLDR
A novel unsupervised dataset summarization algorithm that automatically selects from a large dataset the most informative subsets that better describe the original one enables to streamline and speed-up the manual dataset labeling process, otherwise extremely time consuming, while preserving good classification performance. Expand
Plant classification system for crop /weed discrimination without segmentation
TLDR
A machine vision approach for plant classification without segmentation that uses a Random Forest classifier to estimate crop/weed certainty at sparse pixel positions based on features extracted from a large overlapping neighborhood. Expand
Weed and crop discrimination using image analysis and artificial intelligence methods
TLDR
Two methods were applied to recognise carrot seedlings from those of ryegrass and Fat Hen using digital imaging, showing that a neural network-based methodology exists which allows the system to learn and discriminate between species to an accuracy exceeding 75% without predefined plant descriptions being necessary. Expand
An effective classification system for separating sugar beets and weeds for precision farming applications
TLDR
This paper proposes a system that performs vegetation detection, feature extraction, random forest classification, and smoothing through a Markov random field to obtain an accurate estimate of the crops and weeds. Expand
A vision-based method for weeds identification through the Bayesian decision theory
TLDR
An automatic computer vision-based approach for the detection and differential spraying of weeds in corn crops where weeds and corn plants display similar spectral signatures and the weeds appear irregularly distributed within the crop's field is outlined. Expand
Cats and dogs
TLDR
These models are very good: they beat all previously published results on the challenging ASIRRA test (cat vs dog discrimination) when applied to the task of discriminating the 37 different breeds of pets, and obtain an average accuracy of about 59%, a very encouraging result considering the difficulty of the problem. Expand
Fast robust monocular depth estimation for Obstacle Detection with fully convolutional networks
TLDR
This work proposes a novel appearance-based Object Detection system that is able to detect obstacles at very long range and at a very high speed (~ 300Hz), without making assumptions on the type of motion. Expand
Combining randomization and discrimination for fine-grained image categorization
TLDR
Results show that the proposed random forest with discriminative decision trees algorithm identifies semantically meaningful visual information and outperforms state-of-the-art algorithms on various datasets. Expand
Playing for Data: Ground Truth from Computer Games
TLDR
It is shown that associations between image patches can be reconstructed from the communication between the game and the graphics hardware, which enables rapid propagation of semantic labels within and across images synthesized by the game, with no access to the source code or the content. Expand
Learning scene-specific pedestrian detectors without real data
TLDR
An efficient discriminative learning method is proposed that generates a spatially-varying pedestrian appearance model that takes into the account the perspective geometry of the scene and is able to learn a unique pedestrian classifier customized for every possible location in the scene. Expand
...
1
2
3
...