Gesture controlled robot hand

Sammanfattning: This project was chosen by the students themselves. The idea behind the proposed system was tooffer an alternative method to control robotics in remote places and harsh environments using avision-based approach. The purpose of the project is to introduce a more natural way of humanto-computer interaction and also to make humans working in hazardous environments still performtheir duties remotely.The components used in the project are a mechanic hand, a Raspberry Pi, a Raspberry Pi cameramodule v2, servos, a servo driver, and a Raspberry Pi display. The code is written in C++, and thelibraries used were OpenCV for the computer vision part and wiringPi for the servo control. Theimage processing is divided into four parts, finding the region of interest, which is responsible forsegmenting the hand region, locating fingertips and the palm center, calculating the distances inorder to detect movements of the user’s hand, and finally a part responsible for the servo control.With respect to the specification and the goals of the projects, the project resulted in a successfulworking system, with some limitations. However, the system proposed relies on the binary maskcreated in one of the first steps in the image processing part. Results show that the creation of thebinary mask is heavily dependent on good lighting conditions of the scene. There is still room formore improvements regarding image processing and alternative methods in order to achieve betterresults.