3D hand detection and tracking algorithms has increased research interests in computer vision, pattern recognition, and human-computer interfacing. It is greatly inspired by the emerging technologies like RGBD camera, depth sensors and processing architecture. Therefore, this paper presents a survey on recent works on 3D hand detection and tracking and their applications as a natural user interface to control the computer with hand movements and gestures. It examines the literature in terms of 1) 3D hand capturing techniques used like RGBD cameras, depth sensors, 2) processing with different image processing and computer vision algorithms and their hardware implementation 3) and applications in human computer interfacing for realization of the system. While the emphasis is on 3D mouse and keyboard, the related findings and future challenges are also discussed for practitioners. 

A Survey on 3D Hand Detection and Tracking Algorithms for Human Computer Interfacing

Virtual Reality (VR) is one of the pioneering technologies in the current decade. An increasing number of users are migrating to the virtual world as time progresses. This has led to users desiring more intuitive and natural control for their inputs in the digital world, surpassing the need for traditional input systems such as mouse and keyboard. VR based natural inputs systems are scarce, and the available ones are expensive. Again, very few of them translates the normal hand movements into the virtual control inputs. Therefore, the objective is to design and develop a wearable input system for controlling VR with enhanced usability and high accuracy. To attain this objective, user requirements were firstly elicited through semi-structured interviews. Then, a cost-effective and usable wearable system (VR Glove) was developed based on the revealed requirements for controlling VR. Finally, the system was evaluated with 20 test-participants (novice and expert); and it was found that the VR Glove was usable both to the novice and expert users, though the system was more usable to experts than the novice users. Participants were comfortable with the working mechanism of the proposed VR Glove system and also found the system very responsive.

VR Glove: A Virtual Input System for Controlling VR with Enhanced Usability and High Accuracy

Virtual Reality (VR) is one of the pioneering technologies in the current decade. An increasing number of users are migrating to the virtual world as time progresses. This has led to users desiring more intuitive and natural control for their inputs in the digital world, surpassing the need for traditional input systems such as mouse and keyboard. VR based natural inputs systems are scarce, and the available ones are expensive. Again, very few of them translates the normal hand movements into the virtual control inputs. Therefore, the objective is to design and develop a wearable input system for controlling VR with enhanced usability and high accuracy. To attain this objective, user requirements were firstly elicited through semi-structured interviews. Then, a cost-effective and usable wearable system (VR Glove) was developed based on the revealed requirements for controlling VR. Finally, the system was evaluated with 20 test-participants (novice and expert); and it was found that the VR Glove was usable both to the novice and expert users, though the system was more usable to experts than the novice users. Participants were comfortable with the working mechanism of the proposed VR Glove system and also found the system very responsive. 

Today, with this fast-changing world, portability is one of the critical factors for consumers when choosing a personal computer (PC). Still, the conventional hardware keyboard is a significant limitation in desktops and notebooks. Virtual keyboard prototype solves hardware limitations of the keyboard by presenting an easy and economical alternative using minimum external hardware. In this paper, we have tried to design a virtual keyboard model, which is based on image processing using an inbuilt camera. After that, the basic framework of this can be modified to serve various types of augmented reality (AR), paper, and air keyboard purposes.

Virtual Keyboard Using Image Processing and Computer Vision

An artificial intelligence (AI)-based smart Internet protocol (IP) camera system for examination monitoring has been designed, realized, and rigorously tested under realistic environment. The purpose of the proposed IP cameras is to carry out real-time remote surveillance of the examination hall as well as store corresponding videos recordings in cloud storage. Internet-of-things (IoT) technology is used to remote access of the IP cameras and real-time video streaming on web-browser of any computer/smart phone connected to either internal or external network; a dedicated cloud service (named “remoteit”) is used for this purpose. Practically, 640 × 480 sq. pixels with 30–35 frames per second (fps) video capturing are used for the online streaming. On the other hand, compressed video size of 320 × 240 sq. pixels with 30–35 fps is used for recording and storing in cloud. In addition, a custom TensorFlow lite model has been built for detecting undesirable chaos in the examination hall, and a bulk short messaging service (SMS) application programming interface (API) is used to send real-time alert to the competent authority in order to initiate necessary action. In future, the proposed system may be customized for various other sectors for security and alerting purposes. 

Rohan Karmakar

Papers

Virtual Keyboard Using Image Processing and Computer Vision

IoT-Based Smart Internet Protocol Camera for Examination Monitoring