Vision-based hand gesture recognition is an area of active current research in computer vision and machine learning. Being a natural way of human interaction, it is an area where many researchers are working on, with the goal of making human computer interaction (HCI) easier and natural, without the need for any extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them, for example, to convey information. For that, visionbased hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. Hand gestures are a powerful human communication modality with lots of potential applications and in this context we have sign language recognition, the communication method of deaf people. Sign languages are not standard and universal and the grammars differ from country to country. In this paper, a real-time system able to interpret the Portuguese Sign Language is presented and described. Experiments showed that the system was able to reliably recognize the vowels in real-time, with an accuracy of 99.4% with one dataset of features and an accuracy of 99.6% with a second dataset of features. Although the implemented solution was only trained to recognize the vowels, it is easily extended to recognize the rest of the alphabet, being a solid foundation for the development of any vision-based sign language recognition user interface system.

This paper presents a road surface scanning system that operates with a trichromatic line scan camera with light emitting diode (LED) lighting achieving road surface resolution under a millimeter. It was part of a project named Roadkills—Intelligent systems for surveying mortality of amphibians in Portuguese roads, sponsored by the Portuguese Science and Technology Foundation. A trailer was developed in order to accommodate the complete system with standalone power generation, computer image capture and recording, controlled lighting to operate day or night without disturbance, incremental encoder with 5000 pulses per revolution attached to one of the trailer wheels, under a meter Global Positioning System (GPS) localization, easy to utilize with any vehicle with a trailer towing system and focused on a complete low cost solution. The paper describes the system architecture of the developed prototype, its calibration procedure, the performed experimentation and some obtained results, along with a discussion and comparison with existing systems. Sustained operating trailer speeds of up to 30 km/h are achievable without loss of quality at 4096 pixels’ image width (1 m width of road surface) with 250 µm/pixel resolution. Higher scanning speeds can be achieved by lowering the image resolution (120 km/h with 1 mm/pixel). Computer vision algorithms are under development to operate on the captured images in order to automatically detect road-kills of amphibians.

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for humancomputer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of vision-based interaction systems can be the same for all applications and thus facilitate the implementation. In order to test the proposed solutions, three prototypes were implemented. For hand posture recognition, a SVM model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications.

Hand gesture recognition is a natural way of human computer interaction and an area of very active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research applied to Human-Computer Interaction (HCI) is to create systems, which can identify specific human gestures and use them to convey information or controlling devices. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. This paper presents a solution, generic enough, with the help of machine learning algorithms, allowing its application in a wide range of human-computer interfaces, for real-time gesture recognition. Experiments carried out showed that the system was able to achieve an accuracy of 99.4 % in terms of hand posture recognition and an average accuracy of 93.72 % in terms of dynamic gesture recognition. To validate the proposed framework, two applications were implemented. The first one is a real-time system able to help a robotic soccer referee judge a game in real time. The prototype combines a vision-based hand gesture P. Trigueiros ( ) Insituto Politécnico do Porto, IPP,

In RoboCup Middle Size league (MSL) the main referee uses assisting technology, controlled by a second referee, to support him, in particular for conveying referee decisions for robot players with the help of a wireless communication system. In this paper a vision-based system is introduced, able to interpret dynamic and static gestures of the referee, thus eliminating the need for a second one. The referee's gestures are interpreted by the system and sent directly to the Referee Box, which sends the proper commands to the robots. The system is divided into four modules: a real time hand tracking and feature extraction, a SVM (Support Vector Machine) for static hand posture identification, an HMM (Hidden Markov Model) for dynamic unistroke hand gesture recognition, and a FSM (Finite State Machine) to control the various system states transitions. The experimental results showed that the system works very reliably, being able to recognize the combination of gestures and hand postures in real-time. For the hand posture recognition, with the SVM model trained with the selected features, an accuracy of 98,2% was achieved. Also, the system has many advantages over the current implemented one, like avoiding the necessity of a second referee, working on noisy environments, working on wireless jammed situations. This system is easy to implement and train and may be an inexpensive solution.

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for human-computer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of visionbased interaction systems could be the same for all applications and thus facilitate the implementation. For hand posture recognition, a SVM (Support Vector Machine) model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM (Hidden Markov Model) model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications. To validate the proposed framework two applications were implemented. The first one is a real-time system able to interpret the Portuguese Sign Language. The second one is an online system able to help a robotic soccer game referee judge a game in real time.

One of the most important tasks on robot soccer is localization. The team robots should self-localize on the 18 x 12 meters soccer field. Since a few years ago the soccer field has increased and the corner posts were removed and that increased the localization task complexity. One important aspect to take care for a proper localization is to find out the robot orientation. This paper proposes a new technique to calculate the robot orientation. The proposed method consists of using a histogram of white-green transitions (to detect the lines on the field) to know the robot orientation. This technique does not take much computational time and proves to be very reliable.

No abstract