Search

The concept of augmented reality markerless tracking is introduced. This concept provides a flexible and practical framework and is especially relevant for video game augmented reality applications. Markerless AR has been comprised of the universal communal. Markerless augmented reality is the encounter proficiency that’s now prepared for the primary time. The perception of this report is that the handler’s aspect at the live appearance of the camera of their portable phone in three dimensional and the passage that they see that is the certainty is developed by assimilated three- dimensional virtual objects. Augmented reality games have the authority to outspread virtual gaming into real-world circumstances with real people, while improving the senses of the user. This paper designates the AR-zombie game established with the purpose of detected and unindustrialized mobile augmented reality submissions, precisely for gaming, using ground plane detection collaboration techniques. The objective of the AR zombie player is to kill zombies that are identified through the demonstration of the device. Instead of using indicators as a mean of tracking zombies, this game integrates a ground plane detection system, which will augment the user experience by improving the interface of performers with the real world. As the player travels around the environment, the game will show virtual zombies on the display if the detected ground plane is predictable as belonging to the class of the zombies. AR zombie was tested with users to evaluate the interaction with the real world and its types of tracks were evaluated concerning the presentation to confirm a better gaming familiarity.

Different objects have unique attributes, visual appearances and physical properties which help human visual system to recognize them better. But can object attributes help improve the object detection performance in computer vision? To answer this very question, we carry out extensive experimentation in this research work and claim that, indeed, object attributes improve the object detection performance significantly. We train feature pyramid networks to learn deep convolutional features for objects and their attributes. When used in combination with each other to infer bounding boxes and class scores for objects, these convolutional features show that object detection boosts significantly. We present a new method to boost the performance of object detection using object attributes in Detect-and-Describe (DaD) framework. We explain multiple approaches for boosting of object detection using their attributes. In these approaches, the convolutional features of attributes are merged with convolutional features of bounding box and class labels using different feature merging techniques to boost object detection. To report the performance of object detection boosting using DaD framework, we train our experimental models on aPascal train split and report performance on aPascal test split. Our results show that object attributes can help boost mean average precision (mAP) of object detection as significant as 2.68%

In this paper, we proposed a tunable frequency selective surface (FSS) which is electronically switchable using a microcontroller. The unit cell of the FSS has the shape of a square loop aperture, each aperture includes a pin diode at 90degree interval. This active FSS design has two features, it can transmit at 2.45 GHz with an ON and OFF switch. Also, the measurement shows that the frequency response of the proposed design is not affected with changes to the angle of incidence up to $\pm ~45$ degree from normal. The integration of the microcontroller makes the ability of the switching property easier, which has the potential of developing smart applications.