[Technical Information] Recognizing the target object from the entire camera image (AI)

Added to bookmarks
Bookmarks list

Bookmark has been removed
Bookmarks list

You can't add any more bookmarks

By registering as a member, you can increase the number of bookmarks you can save and organize them with labels.
Free membership registration

DOBOT Magician

last updated：Jan 09, 2025

Official site

Sample program available ■ Introducing a method for object recognition that uses "a single image as training data without cropping the object from the camera image"!

Here is a case article introducing the tabletop-sized small robot arm, DOBOT Magician. ■ Article link: https://qiita.com/shimamotosan/items/d3a06e834d332b914973 ■ Content When distinguishing objects, we use OpenCV to take the extracted objects from camera images as training data or input them into a trained model for classification. Therefore, fine-tuning is necessary to effectively recognize and extract objects from camera images. This time, we will modify the program to classify objects using a single image as training data without extracting objects from the camera image. Keywords: Python, OpenCV, AI, image recognition, dobot ■ About DOBOT Magician DOBOT Magician is a robot arm equipped with a 4-axis arm, priced around 150,000 yen. The device does not require prior safety training, making it suitable for various locations and applicable in a wide range of scenarios. * DOBOT Magician product introduction page https://afrel.co.jp/product/dobot

Related Link - https://afrel.co.jp/product/dobot

Inquire About This Product

basic information

■DOBOT Magician * Main unit: Weight 3.4kg * 4-axis arm * Position repeatability: 0.2mm * Dedicated software (DobotStudio): Free to use * Tool head (included as standard) - Suction cup kit - Pneumatic gripper (can lift objects up to approximately 500g) - Lighting & drawing kit (includes a dedicated pen) - 3D printing kit * Functions - Gripping - Teach & playback (records multiple XYZ coordinates to form a sequence. Can reproduce actions.) * Features - Graphical programming (programming by simply arranging blocks) - Expanded I/O (can expand functionality by connecting external devices such as sensors using 13 expansion ports) - Connect a webcam for image recognition/processing and robot arm control * Optional products - Conveyor belt Includes photoelectric switches, color sensors, and wooden blocks, allowing for learning and experimentation that simulates a production line - Slider rail kit Uses slider rails over 1m long, enabling work while moving horizontally

Price information

DOBOT Magician Educational Version: 226,000 yen excluding tax DOBOT Magician Standard Version: 180,000 yen excluding tax

Price range

Delivery Time

Please contact us for details

※The delivery date may vary depending on the quantity, so please contact us.

Applications/Examples of results

- Examination and demonstration aimed at streamlining and automating production lines in the manufacturing industry Movement of parts (workpieces) Sorting of parts using image recognition and processing - Control learning of robotic arms - Utilization in production management and product development departments * Typical implementation patterns are introduced in the explanatory article. https://learninglab.afrel.co.jp/1145/

Line up（4）

Model number	overview
AFD-ED21: DOBOT Magician Educational Version	This set includes peripheral parts such as a Bluetooth module, Wi-Fi module, and joystick control kit in addition to the Standard Version.
AFD-ST38: DOBOT Magician Standard Version	This set includes the robot arm itself, a suction cup kit, a gripper, a writing and drawing kit, and a 3D printing kit.
AFD-CV8: Conveyor Belt	This set includes the main body, a photoelectric switch, a color sensor, and wooden blocks.
AFD-SLRK: Slider Rail Kit	This set includes a slider rail body with a length of over 1 meter, a wire set, and a tool kit.