Automatic Model Based Dataset Generation for Fast and Accurate Crop and Weeds Detection

Abstract

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 techniques. In this paper, we face this problem by proposing a novel and effective approach that aims to dramatically minimize the human intervention needed to train the detection and classification algorithms. The idea is to procedurally generate large synthetic training datasets randomizing the key features of the target environment (i.e., crop and weed species, type of soil, light conditions). More specifically, by tuning these model parameters, and exploiting a few real-world textures, it is possible to render a large amount of realistic views of an artificial agricultural scenario with no effort. The generated data can be directly used to train the model or to supplement real-world images. We validate the proposed methodology by using as testbed a modern deep learning based image segmentation architecture. We compare the classification results obtained using both real and synthetic images as training data. The reported results confirm the effectiveness and the potentiality of our approach.

To appear in IEEE/RSJ IROS 2017

References in corpus (2)

• How transferable are features in deep neural networks?
• Playing for Data: Ground Truth from Computer Games

Cited by in corpus (14)

• Fully Convolutional Networks with Sequential Information for Robust Crop and Weed Detection in Precision Farming
• Building an Aerial-Ground Robotics System for Precision Farming: An Adaptable Solution
• Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming
• Segmentation of structural parts of rosebush plants with 3D point-based deep learning methods
• Tomato Maturity Recognition with Convolutional Transformers
• Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming
• Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks
• RoSmEEry: Robotic Simulated Environment for Evaluation and Benchmarking of Semantic Mapping Algorithms
• Towards Precise Pruning Points Detection using Semantic-Instance-Aware Plant Models for Grapevine Winter Pruning Automation
• Grapevine Winter Pruning Automation: On Potential Pruning Points Detection through 2D Plant Modeling using Grapevine Segmentation
• SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment
• WeedMap: A large-scale semantic weed mapping framework using aerial multispectral imaging and deep neural network for precision farming
• The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environments
• deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques