跳至主要内容

How Google Coral help for agriculture

Local AI can increase crop yields, improve land management, and reduce food waste


Local AI provides high performance, offline analysis for agriculture challenges that can improve soil quality, plant health, and crop yield in order to produce more food, reduce environmental impact, and enable sustainable farming practices.

According to the UN Food and Agriculture Organization, nearly one third of the world’s food production was wasted or lost, while more than 820 million people went hungry in 2018.

To feed the world sustainably, producers will need to increase output while aiding in the reduction of negative environmental impacts, such as erosion, nutrient loss, and greenhouse gas emissions.

SOIL ANALYSIS: Imagine knowing the quality of your soil instantly.

Analyzing growing conditions traditionally takes a month or more. This delay can lead to the planting of unsuitable crops, improper application of amendments, or low yields. In subsistence communities it can also mean the difference between having food at harvest time or not.

Coral-enabled sensors with neural networks trained on soil data can offer near real-time analysis of soil conditions. This allows for faster corrective action and more appropriate planting.

FOOD SORTING: Imagine sorting food closer to the source.

For smallholder farms, the ability to sort product by grades leads to higher price per bushel and faster time to market. Traditionally done by hand, the process can be slow and consume resources that might be used for other work.

Coral boards running object classification models form the basis for cheaper modular sorters that can help farmers easily grade their products and get to market quick.

DISEASE IDENTIFICATION: Imagine being able to detect and prevent plant disease.

Accurate diagnosis of plant health, including disease, pests, and environmental stress, is the first step toward improving growing conditions.

Segmentation models can help to separate leaves and plant features from complex backgrounds. When combined with classification models and run on the Coral platform, farmers can create tools that allow for real time diagnosis of diseases in the field.

Aggregating this data over a growing season and across fields improves the models, which then improves future yields and lowers disease risk.

PRECISION AGRICULTURE: Imagine plants getting the right nutrients with less waste.

Precision agriculture requires that you know the position, condition, and progression of every plant to provide the right amendments at the right time. Whether on large or small farms, tracking this information can be difficult.

With condition monitoring tools built with Coral local AI and models for identification and classification, farmers can find plants and assess their condition to deliver the right amendments in a targeted way. The precise application of pesticides, fertilizers, and herbicides reduces runoff and adverse effects as well.

In vertical farms where density and safety concerns prevent the use of broadcast techniques, tray-management machines built using Coral can operate independently while sharing knowledge to improve overall plant health.

If you are interested in Google Coral products, and more details about large volume or bulk sales (Volume Discounts) at #Gravitylink online store, welcome to contact our sales team via email: sales@gravitylink.com or market@gravitylink.com, and we'll get back to you with our best quotation ASAP.

评论

此博客中的热门博文

10 questions you should know about Google Edge TPU

1. What is the Edge TPU? The Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing for low-power devices. For example, it can execute state-of-the-art mobile vision models such as MobileNet V2 at almost 400 FPS, in a power efficient manner. Google offers multiple products that include the Edge TPU built-in. Two Edge TPU chips on the head of a US penny 2. What machine learning frameworks does the Edge TPU support? TensorFlow Lite only. 3. What type of neural networks does the Edge TPU support? The first-generation Edge TPU is capable of executing deep feed-forward neural networks (DFF) such as convolutional neural networks (CNN), making it ideal for a variety of vision-based ML applications. 4. How do I create a TensorFlow Lite model for the Edge TPU? You need to convert your model to TensorFlow Lite and it must be quantized using either quantization-aware training (recommended) or full integer post-training quantization. (To create a compatible model...

How to Retrain an object detection model

This tutorial shows you how to retrain an object detection model to recognize a new set of classes. You'll use a technique called transfer learning to retrain an existing model and then compile it to run on an Edge TPU device—you can use the retrained model with either the Coral Dev Board or the Coral USB Accelerator. Specifically, this tutorial shows you how to retrain a MobileNet V1 SSD model (originally trained to detect 90 objects from the COCO dataset) so that it detects two pets: Abyssinian cats and American Bulldogs (from the Oxford-IIIT Pets Dataset). But you can reuse these procedures with your own image dataset, and with a different pre-trained model. The steps below show you how to perform transfer-learning using either last-layers-only or full-model retraining. Most of the steps are the same; just keep an eye out for the different commands depending on the technique you desire. Note: These instructions do not require deep experience with TensorFlow o...

Introducing Google Coral Dev Board

Introducing Google Coral Dev Board (Part 1) Introducing Google Coral Dev Board (Part 2) Introducing Google Coral Dev Board (Part 3) Introducing Google Coral Dev Board (Part 4)