Farm and environment information bidirectional acquisition system with individual tree identification using smartphones for orchard precision management

作者：Qian, Jian-ping^*; Yang, Xin-ting; Wu, Xiao-ming; Xing, Bin; Wu, Bao-guo; Li, Ming

来源：Computers and Electronics in Agriculture, 2015, 116: 101-108.

DOI：10.1016/j.compag.2015.06.003

• Information acquisition
• Tree identification
• Orchard precision management
• QR decoding
• RFID
• Smart phone

An orchard precision management system plays an important role in improvement at the management level and the enhancement of decision abilities. A single orchard tree or an orchard tree microcommunity is the basic management unit, and bidirectional information on the environment and plants is the important content for precision management. A type of RFID label was applied with a UHF chip in the core and a QR code in the surface for single tree identification. A bidirectional acquisition system for orchard production, which included farming information collection for the forward direction and environmental information acquisition for the backward direction, was designed with smart phones. In the farming information collection part, information collection flow that included QR code image acquisition, image preprocessing, barcode decoding and farming information collection was established. An improved local threshold method was adopted to improve the QR code identification rate in the smart phone platform. In the environment information acquisition part, a sensor search rule on the single tree position and a multi-point environment value model were designed. The orchard information bidirectional acquisition system was developed on an Android platform with the Java language, which has the function of QR decoding, farm record information collection, environment information acquisition, data uploading and statistical analysis. The system was tested in an apple orchard. A total of 144 trees were chosen to decode the QR codes in the tree label. The success rate was approximately 96.52%. The identification time of 85% of the trees was less than 4 s for the 20 chosen trees. In taking the temperature, for example, the difference between the computed temperature value and the measured temperature value around each tree was small. The system could decrease the cost of the professional equipment, such as portable RFID readers and writers, which was a low-cost and high-efficiency solution for orchard production information collection.

• 出版日期2015-8
• 单位北京市农林科学院; 北京林业大学