In modern agricultural and forestry research and production management, the efficiency and accuracy of plant phenotypic data acquisition have become critical bottlenecks constraining research progress. With the deepening development of precision agriculture and smart forestry, researchers' requirements for data collection have evolved beyond simple numerical recording toward multi-dimensional, dynamic, and traceable data. Against this backdrop, the technological evolution of leaf area meters—fundamental tools in plant eco-physiology research—reflects the industry's shift from offline data collection to cloud-based visualization.
As a dedicated player in this field, Shandong Laiyin Optoelectronics Technology Co., Ltd. (hereinafter referred to as "Laiyin Technology") has long been committed to advancing agricultural information technology in China. As a high-tech enterprise integrating R&D, manufacturing, sales, implementation, and service, Laiyin Technology deeply embeds cutting-edge technologies—such as the Internet of Things (IoT) and cloud computing—into the agricultural sector. It has established an advanced product portfolio covering agriculture, forestry, meteorology, soil testing, and plant physiology. Guided by a corporate mission that prioritizes quality, customers, innovation, and sincere service, the company offers systematic solutions ranging from basic measurement to cloud-based management.
Faced with the demand for collecting massive amounts of phenotypic data, traditional offline operational modes struggle to meet requirements for research efficiency and data traceability, making technological upgrades imperative.
I. Non-destructive, in vivo measurement is becoming the mainstream trend in field phenotyping.
In traditional plant physiology research, measuring leaf area often relied on methods such as grid counting, gravimetric analysis, or photoelectric scanning—techniques that typically required detaching leaves from the plant. Research in plant phenomics indicates that destructive sampling results in the loss of approximately 30% of longitudinal growth data, severely compromising the continuity of full-lifecycle monitoring. As research scopes expand, scientists are increasingly focused on the dynamic changes plants undergo throughout their entire growth cycle; the destructive nature of detached-leaf measurements clearly fails to meet the needs of full-lifecycle monitoring. Consequently, portable, non-destructive, in vivo measurement devices have increasingly become the preferred choice for field phenotyping.
Advanced equipment currently on the market has successfully addressed many of the pain points associated with field operations. Take the YMJ series portable leaf area meter as an example; its integrated design—combining the main unit and the probe—greatly simplifies field operations. Regarding technical specifications, these devices typically feature a wide measurement range, capable of measuring leaves up to 2000 × 155 mm² in a single pass. This allows for precise measurements of large-leaved crops—such as corn and bananas—without the need for destructive sampling. Furthermore, to address the challenge of power supply in the field, the inclusion of high-performance, high-capacity lithium batteries enables continuous operation without an external power source, effectively ensuring the continuity of data collection. This non-destructive measurement method preserves the leaf's physiological functions and facilitates longitudinal tracking studies, thereby guaranteeing the integrity and continuity of monitoring data.
II. Image Recognition Technology Solves the Challenge of Quantifying Irregular Samples
If portable devices solved the question of "where to measure," then image recognition technology has solved the challenge of "how to measure accurately." In plant pathology research, leaves often lack intact morphology; pest damage and lesions can cause holes or notches. Experimental data indicates that when traditional photoelectric scanning instruments process leaves with holes, the error in projected area calculation can exceed 15%. These instruments struggle to accurately exclude the area of pest-induced holes, leading to systematic data bias.
With the widespread adoption of computer vision technology, camera-based leaf area meters have emerged. Compared to traditional photoelectric devices, imaging equipment integrated with deep learning algorithms can precisely identify and calculate the number and area of pest holes using techniques such as leaf contour feature extraction and edge detection. The YMJ-P series of camera-based instruments from Laiyin Technology combines high-resolution image capture hardware with professional analysis software to precisely measure over a dozen parameters—including leaf area, perimeter, maximum length and width, and shape factor—with an accuracy of up to 0.001 cm². For large leaves exceeding the standard measurement range, the system employs segmented measurement and automatic stitching technologies to reconstruct the full leaf image. This technological advancement is particularly crucial for plant pathology research; by accurately quantifying the proportion of lesions and the area of pest holes, researchers can more objectively assess crop stress resistance. Meanwhile, open-architecture leaf image analyzers (such as the YMJ-S model) allow users to manually correct analysis results. This "algorithm-assisted plus manual verification" approach combines the efficiency of machine vision with the flexibility of human judgment, significantly enhancing data reliability when dealing with complex sample environments.
III. IoT-Enabled End-to-End Closed-Loop Data Acquisition
As Internet of Things (IoT) technology permeates the agricultural sector, isolated data silos can no longer meet the demands of smart agriculture. Traditional measuring instruments often require data to be exported via USB after an experiment concludes; this delayed data workflow is not only inefficient but also prone to discrepancies between recorded data and actual field conditions. Today, smart leaf area meters integrating GPS positioning and wireless transmission technologies are redefining data acquisition standards.
The latest high-end models (such as the YMJ-G) feature integrated high-speed GPS positioning modules and 4G wireless transmission systems. At the moment of measurement, the device records not only leaf length, width, and area but also captures time and geographic coordinates, thereby assigning spatiotemporal tags to the data. Once measured, data is uploaded to a cloud platform in real-time, allowing researchers to view key metrics—such as measurement time and leaf area—and generate line or bar charts for intuitive analysis. This "edge-to-cloud" collaborative architecture resolves the industry-wide pain point of disconnected spatiotemporal data. For researchers, real-time data uploading enables remote monitoring of fieldwork progress; furthermore, the cloud platform supports data export to Excel and online printing, greatly simplifying post-processing workflows. This end-to-end closed-loop process—spanning from field acquisition to cloud-based visualization—marks the entry of plant phenotyping equipment into the IoT era.
