Lightweight Deep Learning based Intelligent Mobile Augmented Reality

Object Tracking in Augmented Reality: Enhancement Using Convolutional Neural Networks

“…The use of DL in AR is still relatively new. Several previous studies have proposed the use of AR, such as [8], [10] (DNN), [11] (LSTM), and [12][13][14][15] (CNN). One study [16] used a deep neural network (DNN) for an intelligent municipality AR service system in the fields of information dissemination and tourism.…”

“…This study compared LSTM and CNN methods to improve the performance of AR in maintenance in a manufacturing environment. In addition, [12] proposed lightweight DL on mobile-based using CNN. Source [12] is an initial study that has just been published, so the results are not yet satisfactory.…”

“…In addition, [12] proposed lightweight DL on mobile-based using CNN. Source [12] is an initial study that has just been published, so the results are not yet satisfactory. The use of CNN methods has also been proposed by several previous studies [15][16][17] to improve the performance of AR for system maintenance.…”

“…Therefore, in this study, we propose the use of CNN to aid in the detection process and object segmentation in lab maintenance (Arduino). The contribution of this study is to improve the performance of the CNN method previously proposed in [12]. Study [12] only shows the initial state of the research, so there is a need for further research using CNN in the AR field for detection and segmentation.…”

“…The contribution of this study is to improve the performance of the CNN method previously proposed in [12]. Study [12] only shows the initial state of the research, so there is a need for further research using CNN in the AR field for detection and segmentation. Therefore, this research proposes a CNN method to improve the performance of AR object detection and segmentation with different light intensities.…”