Innovative Community Projects That Utilized Grove-Vision AI Module: 11 Inspiring Stories
Artificial intelligence (AI) has taken the world by storm, with its potential to transform the way we live and work. It’s no wonder that many industries are eager to adopt this technology to solve complex real-world problems. Last year, Seeed Studio released the Grove-Vision AI Module, a state-of-the-art camera that harnesses the power of Edge Machine Learning algorithms and computational photography to perform real-time object detection. Designed to be used with the XIAO ecosystem and Arduino, the Grove-Vision AI Module is the perfect tool for creating AI-powered camera projects.
The Grove-Vision AI Module is a compact board that utilizes the advanced Himax HX6537-A processor and is equipped with an AI-driven OV2640 camera sensor. This sensor offers exceptional image quality, thanks to its auto-exposure and auto-white balance capabilities. The device’s built-in Edge Machine Learning algorithm uses computational photography to conduct real-time, improved object detection. The module also comes with pre-loaded models for human face detection and can support up to three customized models for import.
Upgrade to Industrial Solutions
If you’re looking to undertake industrial-level projects, we recommend checking out our SenseCAP A1101 – LoRaWAN Vision AI Sensor. This top-of-the-line industrial sensor is enclosed in an IP66 grade industry-level enclosure with an embedded Wio-E5 LoRaWAN module and MCU, making it perfect for outdoor use. Using the SenseCAP Mate App and Dashboard, it’s effortless to add and deploy the application once the model training is finished.
SenseCAP A1101 – LoRaWAN Vision AI Sensor, Open the Door to the TinyML world
The SenseCAP A1101 is a cutting-edge LoRaWAN Vision AI Sensor that harnesses the power of TinyML AI technology and long-range LoRaWAN transmission, making it an excellent device solution for both indoor and outdoor environments. It’s equipped with a highly efficient AI vision solution from Himax, ensuring energy-efficient operations. This sensor also supports training using various TinyML AI platforms like Google TensorFlow Lite and Edge Impulse, providing its users with ease of use and flexibility. Furthermore, SenseCAP A1101 supports customization for different AI applications, fill up the form here if you would like to customize your special Vision AI Sensor.
Edge Impulse’s Official Support for Grove-Vision AI Module & SenseCAP A1101 – LoRaWAN Vision AI Sensor
Edge Impulse is an advanced AI modeling platform designed to assist enterprise teams in constructing and optimizing AI models that can be easily installed on any edge device. As Seeed Studio’s software partner, Edge Impulse offers assistance to our edge devices by creating guides for developing machine learning models, training them, and deploying them onto the devices.
Over the last few months, Edge Impulse has made consecutive announcements regarding their official support for the Grove-Vision AI Module and SenseCAP A1101 LoRaWAN Vision AI Sensor. This means that you can now collect raw data from these devices, build models, and deploy the trained machine learning models directly onto the devices through the studio, without needing any programming skills.
Check out the following guides with Edge Impulse:
- Grove-Vision AI Module: Click here
- SenseCAP A1101-LoRaWAN Vision AI Sensor: Click here
In this blog, we are excited to showcase 11 community projects that have utilized the Grove-Vision AI Module and SenseCAP A1101 LoRaWAN Vision AI Sensor to create inspiring real-world applications. We hope to inspire you to think outside the box and explore the innovative ways in which AI can be leveraged to drive positive change. From improving healthcare to enhancing agriculture, these projects demonstrate the endless possibilities of AI technology.
Join us as we explore these amazing projects and discover how AI is being used to create a better world. Let’s dive in!
1. Detect the Drain Blockage with Tiny ML + LoRa
The office belonging to Shuyang boasts of a beautiful balcony. Upon stepping into the area, one would feel as though they have entered a peaceful garden. The vibrant colors from blooming flowers and plants during spring and summer bring about a truly delightful atmosphere. However, this beauty also brings along fallen petals and leaves, which could get swept away by strong winds or rain and quickly clog up the balcony drain. Shuyang is determined to find a solution to detect any debris accumulation in the balcony drain and send alerts for timely action.
Shuyang faced a challenge when attempting to install sensors on her balcony due to the difficulty of wiring and her limited knowledge of coding and TinyML. To overcome these obstacles, she discovered a no-code solution that involved utilizing an outdoor smart image sensor capable of performing local inference and transmitting the results with LoRa. She also relied on Edge Impulse for assistance with model training.
Seeed’s products used in this project
Software
- Edge Impulse
>>Read the full project on Hackster
2. Penguin Counting and Monitoring
Over the past few years, ocean species have been adversely affected by marine pollution and marine heatwaves, leading to starvation and mass deaths. The little blue penguin, also known as “Kororā,” is particularly vulnerable to these conditions, with New Zealand’s Department of Conservation (DOC) categorizing them as “declining/at risk.”
To address this critical issue, Richard Wright has developed a system using the Grove-Vision AI Module to detect, monitor and protect penguins when they come ashore and send the notification via LoRa. However, this task is quite challenging as penguins typically come ashore at dusk when it is too dark to capture them, but Richard Wright believes that it is a crucial and ongoing endeavor that people must undertake.
Seeed’s products used in this project
- SenseCAP K1100 – The Sensor Prototype Kit with LoRa® and AI
- Wio Terminal Chassis
- Wio Terminal Chassis – Battery
Software
- Microsoft Visual Studio Code Extension for Arduino
>>Read the full project on Hackster
3. Early Flash Flood Warn System
Floods are a type of natural disaster that can be both common and costly. They are often caused by hurricanes, melting snow, or prolonged periods of rain. Flash floods can occur suddenly when water rapidly rises along a stream or low – lying area.
Jhonattan Fredy Moreno Bernal has created a project to tackle this problem by developing a low-cost system for generating early warnings. By deploying a network of nodes, the system is able to monitor water flows and gather more information to build predictive flood models. The system utilizes a trained model to detect sudden floods and sends an alarm through the Blynk platform via email when a defined detection threshold is exceeded. This helps provide timely alerts for taking preventive measures against floods.
Seeed’s products used in this project
Software
- Roboflow
- Blynk
>>Read the full project on Hackster
4. Vision based Sand Depletion Prevention Kit (VSDP)
Sand mining from riverbeds is a major environmental issue, leading to various negative impacts on rivers, including social, environmental, geomorphic, and disastrous impacts. Unchecked sand consumption could increase by 45% in four decades, leading to environmental damage and urban expansion material shortages.
To address this issue, Rahul Khanna D has designed a system that uses Grove sensors to process sensor data, such as VOC, eCO2, soil moisture, temperature, and humidity. This device monitors trespassing humans in the sand depletion region and notifies the server via the gate way. Additionally, the Edge AI model monitors illegal sand mining using the Grove-Vision AI Module. Multiple AI nodes are deployed and connected to the LoRaWAN gateway, which connects to the Helium Server.
Seeed’s products used in this project
Software
- Arduino IDE
- Helium Console
>>Read the full project on Hackster
5. IoT AI-driven Tree Disease Identifier w/ Edge Impulse & MMS
As a result of environmental changes and extensive deforestation, trees and plants are becoming increasingly vulnerable to contagious illnesses. This is particularly concerning since trees play a critical role in pollination, and the spread of tree diseases can lead to significant crop yield losses, animal fatalities, widespread infectious epidemics, and even land degradation caused by soil erosion.
To address this issue, Kutluhan Aktar has developed a project called “IoT AI-Driven Tree Disease Identifier w/ Edge Impulse & MMS.” This innovative approach employs Grove-Vision AI to gather images of infected trees, thereby creating a comprehensive dataset. Using Edge Impulse, the models are trained and deployed to identify tree diseases at an early stage. The results are then communicated via MMS, enabling swift action to prevent further spread and harm to forests, farms, and arable lands.
Seeed’s products used in this project
- SenseCAP K1100 – The Sensor Prototype Kit with LoRa® and AI
- Grove – CO2 & Temperature & Humidity Sensor (SCD30)
Software
- Edge Impulse Studio
- Arduino IDE
- Thonny
- Autodesk Fusion 360
- Ultimaker Cura
>>Read the full project on Hackster
6. Wildlife Sanctuary Monitor
Indonesia’s tropical forests, the third-largest in the world, are home to diverse wildlife, including endangered species. However, conservation efforts face challenges such as illegal hunting and deforestation. The Javan Rhinoceros and orangutan are among those species at risk, with a lack of resources and staff further hindering conservation efforts.
Hendra Kusumah has created a conservation tool that monitors the state of forests and identifies endangered animals as part of efforts to protect them. This project centers on utilizing audio classification to assess the vitality of endangered wildlife, with Grove-Vision AI employed to detect their movements. The device can immediately alert authorities of illegal poaching activities and issue early warnings in the event of wildfire outbreaks to prevent their spread. Moreover, the system can transmit data results wirelessly over long distances and display them on computer dashboards and smartphones.
Seeed’s products used in this project
Software
- Edge Impulse Studio
- Arduino IDE
>>Read the full project on Hackster
7. Plastic Bottle Detector For Lake
There is a misconception among many people that plastic bottles/containers are biodegradable and can be disposed of in the environment, leading to their inappropriate disposal in rivers, drains, lakes, and oceans. This misconception has resulted in severe environmental pollution and poses a threat to the health and well-being of humans and other living organisms.
JuanYi has developed a device that utilizes vision to identify plastic bottles floating on a lake and sends the collected data to the cloud to minimize the negative impact of trash on the environment. To train the convolutional neural network (CNN), a dataset of plastic bottles is required. Therefore, JuanYi employed the Grove-Vision AI to gather data regularly over several weeks from a nearby park lake.
Seeed’s products used in this project
Software
- Arduino IDE
- Roboflow
>>Read the full project on Hackster
8. DeViridi: IoT Food Spoilage Sensor and Monitoring Dashboard
The Rockefeller Foundation found that smallholder farmers and supply chain actors in developing countries lose 15% of income due to food spoilage, potentially feeding an extra billion people by 2050. Farmers worldwide struggle with food storage and detection of spoiled foods, leading to high costs for them and processing companies. Agriculture waste contributes to greenhouse gases, with Kenya alone wasting 50% of post-harvest crops, resulting in edible food loss and 25 times more heat-trapping methane gas than carbon dioxide.
Ashwin Sridhar developed a smart IoT device that uses AI-based image detection to monitor food storage conditions and detect spoilage early. In addtion, by detecting the gas emitted by different types of food, such as ammonia and hydrogen sulfide from rotting meats and ethylene from fruits and vegetables, the device can determine the progress and extent of food spoilage, allowing farmers, suppliers, supermarkets, and households to accurately assess food edibility.
Seeed’s products used in this project
Software
- Autodesk Fusion 360
- Arduino IDE
- TensorFlow
>>Read the full project on Hackster
9. Endangered Animal Detector
In recent times, Australian wildlife has suffered significantly from the devastating effects of fire and flood. This has had a particularly dire impact on the country’s unique and endangered species, some of which are exclusive to Australia. One such species is the Gang-gang cockatoo, which serves as the emblem of the Australian Capital Territory. Unfortunately, this bird is now facing the designation of a threatened species as a result of a sharp decline in its population, attributed to both the climate crisis and the bushfire disaster.
The objective of the project is to deploy a grid of inconspicuous image classification sensors across a nature reserve, in order to track the movement and population of native animals. Pbrown has utilized Grove-Vision AI modules to accurately detect the Gang-gang and other indigenous bird species. Additionally, the system incorporates environmental sensors such as humidity and temperature sensors to monitor various environmental conditions. This will enable the collection of valuable data on the number and species of animals, as well as their directional movement, and specific environmental factors within the reserve.
Seeed’s products used in this project
Software
- Arduino IDE
>>Read the full project on Hackster
10. Gate Keeper – An IoT Based Elephant Detection System
Located in southern India, Ooty is a picturesque hill known for its scenic beauty. However, the frequent entry of elephants into the area often causes panic among the residents. While the sounds of these giant mammals sometimes alert the locals, they usually remain silent, posing a significant risk of human-elephant conflict.
To mitigate this issue, Pradeep Thiruna and his team developed an IoT-based Elephant Detection System using the SenseCAP K1100 – The Sensor Prototype Kit with LoRa® and AI. They integrated the Grove-Vision AI Module to detect and monitor elephant activities and promptly alert the residents via SMS or email.
Seeed’s products used in this project
Software
- Arduino IDE
- Qubitro
- Blues Wireless Notehub.io
>>Read the full project on Hackster
11. NMCS: No More Coffee Spills!
Sashrika Das, one of the winners of the “IoT in the Wild Contest 2022” by Seeed Studio, has recently developed a new device. The device, named “NMCS” (No More Coffee Spills), was inspired by her dad’s experience of spilling coffee while brewing it. NMCS aims to prevent such mishaps by checking for the presence of a cup before starting the brewing process.
To achieve this, the device uses a microphone module from the Wio Terminal to detect brewing sounds from the coffee machine. Once brewing is detected, the device uses the Grove-Vision AI Module to check if a cup is present in the machine. If not, the Wio Terminal’s built-in buzzer will beep, alerting the user to place a cup before it is too late.
Seeed’s products used in this project
Software
- Arduino IDE
- Edge Impulse Studio
- Roboflow
>>Read the full project on Hackster
We encourage you to read more about these projects. While some of these ideas may be challenging to execute, they illustrate the powerful impact of AI on our lives and the world. This has inspired us to delve deeper into this technology.
These community projects are just a glimpse of the endless possibilities that AI technology can bring to various industries. As we continue to explore and innovate with AI, it is important to keep in mind its potential to drive positive change in the world. Whether it’s improving healthcare, enhancing agriculture, or even creating art, AI has the potential to transform the way we live and work. We hope these projects have inspired you to think outside the box and explore the innovative ways in which AI can be leveraged to make a difference. Let’s continue to push the boundaries of what’s possible with AI and create a better world together.
About Author
The inspiring stories help me to improve the motivation. In addition, we can see the benefits of innovative community projects. So, I appreciate you when you launching this article.