In his search for a suitable camera, he came across IDS NXT - a complete system for the use of intelligent image processing. It fulfilled all requirements and, thanks to artificial intelligence, much more besides pure gesture recognition.

Robot plays "Rock, Paper, Scissors" - Part 1/3

Case Study from | IDS Imaging

Gesture recognition with intelligent camera

Sebastian Trella is passionate about technology and robotics. In his own blog, he is always taking on new tasks. But he has hardly ever worked with image processing. However, a colleague's LEGO® MINDSTORMS® robot, which uses several different sensors to detect the gestures of a hand, gave him an idea: "The robot should be able to "see”." Until now, the gesture had to be made at a specific point in front of the robot in order to be reliably recognized. Several sensors were needed for this, which made the system inflexible and dampened the joy of playing. Can image processing solve this task more "elegantly"?


From the idea to implementation

In his search for a suitable camera, he came across IDS NXT - a complete system for the use of  intelligent image processing. It fulfilled all requirements and, thanks to artificial intelligence, much more besides pure gesture recognition. Trella's interest was piqued. This is because the evaluation of the images and the communication of the results took place directly on or through the camera - without an additional PC. The IDS NXT Experience Kit also came with all the components to get started with the application right away - no prior AI knowledge required.

Trella took the idea further and began to develop a robot that would play the game "Rock, Paper, Scissors" in the future - with a process similar to the classical sense: The (human) player is asked to perform one of the familiar gestures (scissors, rock, paper) in front of the camera. The virtual opponent has already randomly determined his gesture at this point. The move is evaluated in real time and the winner is displayed.


The first step: Gesture recognition by means of image processing

But until then, some intermediate steps were necessary. Trella began implementing gesture recognition using image processing - new territory for the robotics fan. However, with the help of IDS lighthouse - a cloud-based AI vision studio - this was easier to realize than expected. Here, ideas evolve into complete applications. For this purpose, neural networks are trained by application images with the necessary product knowledge, such as in this case the individual gestures from different perspectives, and packaged into a suitable application workflow.

"The training process was super easy and I just used IDS Lighthouse's step-by-step wizard after taking several hundred pictures of my hands using rock, scissor, or paper gestures from different angles against different backgrounds. The first trained AI was able to reliably recognize the gestures directly," explains Sebastian Trella. This works for both left- and right-handed users with a recognition rate of about 95%. Probabilities are returned for the labels "Rock", "Paper", "Scissor" or "Nothing". A satisfactory result. But what happens now with the data obtained?


Further processing

The further processing of the recognized gestures could be carried out by means of a specially created vision app. For this, the captured image of the respective gesture - after evaluation by the AI - must be forwarded to the app. The latter "knows" the rules of the game and can thus decide which gesture beats another. It then determines the winner. In the first stage of development, the app will also simulate the opponent. All this is currently in the making and will be implemented in the next step to the "Rock, Paper, Scissors"-playing robot.


From play to everyday use

Initially, the project is more of a gimmick. But what could come out of it? A slot machine? Or maybe even an AI based sign language translator?


To be continued...  Read Part 2/3 here.


The content & opinions in this article are the author’s and do not necessarily represent the views of RoboticsTomorrow
IDS Imaging Development Systems Inc.

IDS Imaging Development Systems Inc.

IDS is a leading manufacturer of industrial cameras "Made in Germany" with USB or GigE interfaces. Equipped with state of the art CMOS sensors, the extensive camera portfolio ranges from low-cost project cameras, to small, powerful models with PoE functionality or robust cameras with housings that fulfill the prerequisites for protection code IP65/67. For quick, easy and precise 3D machine vision tasks IDS offers the Ensenso series. With the novel vision app-based sensors and cameras of IDS NXT the company opens up a new dimension in image processing. Whether in an industrial or non-industrial setting: IDS cameras and sensors assist companies worldwide in optimizing processes, ensuring quality, driving research, conserving raw materials, and serving people. They provide reliability, efficiency and flexibility for your application.

Other Articles

Trained quickly, inspected swiftly - Handling and defect inspection of indexable inserts
The German medium-sized company has developed a fully automated handling and inspection system in which the DENKnet solution for AI-based image evaluation plays a decisive role and sets new standards in terms of performance, zero-defect production and speed.
Robot plays "Rock, Paper, Scissors" - Part 2/3
The app forms the second phase of the project and - generally speaking - is intended to enable players to play against a simulated computer opponent. It builds on the trained AI and uses its results further.
3D Image Processing Solution With 2D Cameras, AI and Robotics Optimizes the Manufacturing Landscape
The easy-to-integrate system consists of a module for robot arms, a computing unit with pre-installed intelligent software and a camera module, each equipped in series with two uEye+ XCP cameras from IDS.
More about IDS Imaging Development Systems Inc.

Comments (0)

This post does not have any comments. Be the first to leave a comment below.

Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

PI USA - Improving Laser Drilling with Advanced Motion Control

PI USA - Improving Laser Drilling with Advanced Motion Control

Laser drilling precision and throughput are limited by a number of factors including optical distortion, tracking accuracy, acceleration limits of motion stages, and focus control performance. A new piezo-based control approach is designed to enhance the precision and accuracy of laser drilling for a wide range of target applications, including aerospace, medical, electronics, and automotive.