Level 6: Object Detection by an AI-assisted Edge Device
Train & implement AI-assisted device for object detection
- Use ESP32-CAM for image recognition.
- Training AI models with Edge Impulse
- Cup or vegetable detection using ESP32-CAM, deploying machine learning models on ESP32-CAM
- Edge computing with ESP32-CAM and Edge Impulse.
Grow visibility, open a Shopify shop Start promoting your AI-assisted device.
This level covers data acquisition, model training, deployment and AI-assisted edge computing using Edge Impulse for object detection. Students will learn to describe, promote and optionally market their AI-assisted device on a sharing platform.
Summary for this Level
In the final level of the challenge, students will work on computer vision, using the ESP32-CAM module to develop an image recognition system for object detection. They will train AI models using Edge Impulse for tasks such as detecting a cup or vegetables. These models will be deployed on the ESP32-CAM, and students will describe and promote their AI-assisted device. This level provides a understanding of image processing, AI model training, and edge computing. By the end of this level, students will have the skills to create sophisticated image recognition systems and understand the basics of deploying AI models on edge devices.
Reward: CAM Dual-Adapter for 0.66-OLED / or Hero-Website with own device (H-A result), free shop stocking of 5 own devices, incl. fulfillment, getting 100% sales profit.
| Level of Difficulty: advanced / AI related | Tutor: Melina |
Tutorial for this level
Motivational or Reference Video
Gained Tech Competences
Remembering: Level 6 is the culmination of the challenge, where students will build an image recognition system using the ESP32-CAM module to identify vegetables like tomatoes, potatoes, and onions. Understanding: They will train and deploy machine learning models on the ESP32-CAM to validate them and to identify objects such as vegetables. They will also learn the basics of edge computing, data acquisition, model training, and deployment. Applying: This level covers edge computing concepts, data acquisition, model training, and deployment using Edge Impulse. Students can refer to a blog post of the experts to create their own object detection system. Analyzing: Students analyze and refine their device's description on Solution Builder. Evaluating: Completing this level provides students with free stocking and sales of five devices, including fulfillment and 100% sales profit. The results of their work are displayed on an OLED screen for easy viewing. Creating: Using the Edge Impulse platform, they train and deploy a machine learning model to run directly on the ESP32-CAM, with AI-assisted object detection displayed on an OLED screen for validation.
Gained Soft Skills
Remembering: Level 6 focuses on advanced problem-solving and critical thinking as students build image recognition systems. Understanding: They will enhance their communication skills by describing and promoting their AI-assisted devices. Applying: Leadership and initiative are demonstrated by managing their developments and marketing efforts. Analyzing: Time management is crucial for balancing model training, deployment, and promotion tasks. Evaluating: Adaptability is required to learn and use edge computing concepts, and attention to detail ensures accurate image recognition. Creating: Resilience is built as they overcome challenges in deploying high accuracy to their device.
Summary for this Level
In the final level of the challenge, students will work on computer vision, using the ESP32-CAM module to develop an image recognition system for object detection. They will train AI models using Edge Impulse for tasks such as detecting a cup or vegetables. These models will be deployed on the ESP32-CAM, and students will describe and promote their AI-assisted device. This level provides a understanding of image processing, AI model training, and edge computing. By the end of this level, students will have the skills to create sophisticated image recognition systems and understand the basics of deploying AI models on edge devices.
