Farm and environment information bidirectional acquisition system with individual tree identification using smartphones for orchard precision management
Introduction
China is a country with a large fruit production in the world. For apples, the production in 2010 exceeded 30 million tons (Qian et al., 2013). However, the fruit quality and yield has undergone large fluctuations from year to year because of extensive issues in management (Qi et al., 2011).
Precision agriculture has the characteristic of high technology content, advanced production means and strong technology integration (Zhang et al., 2002). Flexible management is the key idea of precision agriculture. The idea can be used in orchard management. A different method at a different time is performed in the orchard according to the individual and population diversity, which has been an efficient way to improve extensive management (Cunha et al., 2010). In orchard precision management, a single orchard tree or an orchard tree microcommunity is the basic unit, and information collection and management is the important content. The information includes two parts, one of which is the plant environment information, such as the temperature and humidity, and another is the farming operation information, such as irrigation and insecticides (Jiang et al., 2008).
A WSN (Wireless Sensor Network) provides effective support for environmental information quick acquisition and real-time monitoring (Wang et al., 2006, Fernandes et al., 2013). A WSN consists of non-intrusive communication devices of small size, to which one or more precision sensors for data collection are adapted. Sensors usually measure parameters such as the soil-moisture, salinity or pH, among other factors (Garcia-Sanchez et al., 2011). Regional and on-farm sensor networks were developed and implemented in two agricultural applications in Washington State, an agricultural weather network and an on-farm frost monitoring network (Pierce and Elliott, 2008). López Riquelmea et al. successfully implemented a WSN on a crop of ecological cabbage (Brassica oleracea), and the result was a low-cost, highly reliable and simple infrastructure for the collection of agronomical data over a distributed area in horticultural environments (López Riquelmea et al., 2009).
With the development of mobile communication technology, the information collecting and uploading time using portable devices (mobile phone, PDA, tablet PC) has become an effective means for farming operation information collection (Tseng et al., 2006, Qian et al., 2012, So-In et al., 2014). Steinberger et al. (2009) developed mobile farming information collection equipment that transmitted the information to the server through the internet. Amiama et al. (2008) developed an automatic acquisition system that collects information that concerns herbage reaping. This system transmits the information that is collected through an SMS module and fixes the reaper’s position using GPS. Finally, the relationship between the output and plot area was found. Fang and He (2008) developed a real-time field information collection and processing system in the Pocket PC, which realizes data acquisition and a dynamic display function using GPS and GIS. Li et al. (2010) developed farming information acquisition and a decision support system (PRDS) in a PDA for cucumber traceability, which was applied in two production companies in Beijing and proved to improve the production efficiency.
Combining environment information and farming operation information, the establishment of a decision support system is an effective way to improve the management and decision level in orchard precision performance. However, the existing studies and applications with WSNs and mobile devices cannot integrate the two types of information. The limitations in single tree precision orchard management are obvious in three respects: (1) the environment information is collected and transmitted to the monitor and cannot been searched or inspected in the orchard scene; (2) the most similar environment information cannot been searched based on the identified tree; (3) the farm operation information cannot been corresponded with the environment information in the mobile device. To overcome these shortcomings, a bidirectional information acquisition system with single-tree identification was developed on the smart phone platform. The system framework was designed, and the system functions were implemented with key technologies. The two important indexes of the 2d-barcode decoding and system were tested. The system was proved to be an effective method for orchard precision management.
Section snippets
Single-tree identification
Every fruit tree was identified by an RFID card with a two-dimensional barcode, as shown in Fig. 1. The card adopts the Web™ UHF chip produced by UPM. The frequency range of the chip is between 860 and 960 MHz. The chip supports the protocol of ISO 18000-6C and EPC Class 1 Gen 2 and has a TID memory of 64 bits. The reading and writing radius ranges from 4 m to 6 m (The bio Company UPM, 2011). Visible information, including the tree number, manager, species and two-dimensional barcode, was printed
System framework
The bidirectional acquisition system for orchard production included farming information that was collected in the forward direction and environmental information acquisition that moved in the backward direction. As shown in Fig. 2, three parts were included. The QR code on the tree card was the basis for the single orchard tree identification. The bidirectional information acquisition system in the smart phone was the key for scanning the barcode, information collection and data access from
Basic flow
Unlike RFID identification with a special instrument, taking a QR photo and extracting the code to identify a single tree with a smart phone is a simple and low cost method. Referring to the QR code extracting steps in the literature (Zhao et al., 2012), the farming information collection flow can be divided into four steps, as shown in Fig. 3.
- (1)
QR code image acquisition: control the camera in the phone to capture the QR code on the tree label card.
- (2)
Image preprocessing: For the reason of
Basic flow
The environment information was collected with the sensors and stored in the remote server described in the literature (Yang et al., 2013). To obtain the environment information every time in the orchard, the processing in the smart phone needed to exchange the data with the server. The basic flow of the environment information acquisition was described as in Fig. 7.
- (1)
Taking the QR code image and extracting the tree position: The QR code on the tree label card was captured with a smart phone.
System implementation
The system was developed on an Android platform with the Java language. The following functionalities were realized in the system.
- (1)
QR decoding: The camera in the phone focused on the QR code on the tree label. Then, the fruit tree number was extracted through decoding the QR image. To increase the success rate, a series of standard operations, such as binarization and transformation, was performed.
- (2)
Farm records information collection: This function was activated after successful decoding. This
Application test
The developed system was applied in an orchard. This orchard is located in Feicheng city in Shandong Province, China. A total of 144 apple trees were planted in the orchard, which was 0.24 hm2. The main apple cultivars (84) are Fuji and Gala. The application scene is described in Fig. 10. Eight environment sensors with a WSN (Wireless Sensors Network) were deployed in the orchard. The sensors collected the data, such as the air temperature, air humidity, soil humidity, and soil temperature every
Conclusions
An orchard precision management system is an effective way for implementing management level. The widely application of mobile phones provides a convenience for real-time and on the field management. In this paper, a bidirectional acquisition system was designed with smart phones. The system included farming information collection for the forward direction and environmental information acquisition for the backward direction.
In the farming information collection part, information collection flow
Acknowledgments
The authors would like to thank the referees for their suggestions, which improved the content and presentation of this paper. This work was funded by the National Key Technology R&D Program of China (No. 2013BAD19B04).
References (21)
- et al.
Design and field test of an automatic data acquisition system in a self-propelled forage harvester
Comput. Electron. Agric.
(2008) - et al.
The use of mobile devices with multi-tag technologies for an overall contextualized vineyard management
Comput. Electron. Agric.
(2010) - et al.
A pocket PC based field information fast collection system
Comput. Electron. Agric.
(2008) - et al.
A framework for wireless sensor networks management for precision viticulture and agriculture based on IEEE 1451 standard
Comput. Electron. Agric.
(2013) - et al.
Wireless sensor network deployment for integrating video-surveillance and data-monitoring in precision agriculture over distributed crops
Comput. Electron. Agric.
(2011) - et al.
A GSM-based remote wireless automatic monitoring system for field information: a case study for ecological monitoring of the oriental fruit fly, Bactrocera dorsalis (Hendel)
Comput. Electron. Agric.
(2008) - et al.
A PDA-based record-keeping and decision-support system for traceability in cucumber production
Comput. Electron. Agric.
(2010) - et al.
Regional and on-farm wireless sensor networks for agricultural systems in Eastern Washington
Comput. Electron. Agric.
(2008) - et al.
A traceability system incorporating 2D barcode and RFID technology for wheat flour mills
Comput. Electron. Agric.
(2012) - et al.
A hybrid mobile environmental and population density management system for smart poultry farms
Comput. Electron. Agric.
(2014)
Cited by (22)
Estimating canopy-scale chlorophyll content in apple orchards using a 3D radiative transfer model and UAV multispectral imagery
2022, Computers and Electronics in AgricultureCitation Excerpt :Image spectroscopy is a low-cost, highly flexible tool widely used in terrestrial ecosystem monitoring (Berger et al. 2020; Xie et al. 2019; Zhang et al. 2021). High-resolution images hold great potential for monitoring the health status and estimating biophysical parameters of individual tree crowns (ITCs) (Ali and Imran 2020; Ferreira et al. 2018; Johansen et al. 2020), which is an important aspect of orchard precision management (Qian et al. 2015). Image spectroscopy data acquired in open-canopy plantations can be subject to high variability caused by various factors, such as branching patterns, biophysical properties, soil, weeds, illumination, and geometry of acquisition.
Using information from images for plantation monitoring: A review of solutions for smallholders
2020, Information Processing in AgricultureCitation Excerpt :Therefore, positioning sensors are not required in every farm activity. The use of QR technology is promising in offering high accuracy and consistency in recording and minimizing human error in plantation management [51]. Different nutrient needs, yield, pests and disease occurrence, and other plant health indicators in each plant are the main reasons for improving plantation management systems.
Image enhancement for crop trait information acquisition system
2018, Information Processing in AgricultureCitation Excerpt :The progress and application of information technology in agriculture have led to increased attention being paid to precision breeding worldwide [1–4].
Development of a visual monitoring system for water balance estimation of horticultural crops using low cost cameras
2017, Computers and Electronics in AgricultureCitation Excerpt :It has been shown that, with suitable photogrammetric systems, it is possible to optimize the use of water in irrigation management in agriculture (Lou et al., 2016; Escarabajal-Henarejos et al., 2015a). Moreover, computer vision techniques can be helpful in many other tasks, such as crop monitoring (Brillante et al., 2016; Lin et al., 2013), controlling the quality of vegetables and fruits (Donis-Gonzalez et al., 2016; Kodagali and Balaji, 2012), weed control (Arroyo et al., 2016; Slaughter et al., 2008), and reading QR codes in the field (Qian et al., 2015), among others. Many advances have been developed by means of remote sensing, where satellite imagery is used to cover large areas all over the world (Ramírez-Cuesta et al., 2017; Odi-Lara et al., 2016; Sicre et al., 2014; Xu et al., 2010).
Optimization of QR code readability in movement state using response surface methodology for implementing continuous chain traceability
2017, Computers and Electronics in Agriculture