Agriculture sector is an important pillar of the global economy. The cotton crop is considered one of the prominent agricultural resources. It is widely cultivated in India, China, Pakistan, USA, Brazil, and other countries of the world. The worldwide cotton crop production is severely affected by numerous diseases such as cotton leaf curl virus (CLCV/CLCuV), bacterial blight, and ball rot. Image processing techniques together with machine learning algorithms are successfully employed in numerous fields and have also used for crop disease detection. In this study, we present a deep learning-based method for classifying diseases of the cotton crop, including bacterial blight and cotton leaf curl virus (CLCV). The dataset of cotton leaves showing disease symptoms is collected from various locations in Sindh, Pakistan. We employ the Inception v4 architecture as a convolutional neural network to identify diseased plant leaves in particular bacterial blight and CLCV. The accuracy of the designed model is 98.26% which shows prominent improvement compared to the existing models and systems.

Head-mounted displays and augmented reality headsets are emerging as the future of human-computer interaction. Such devices can display high resolution 3D images and use on-board cameras to capture the surroundings of the user. However, capturing the user who is wearing the device to facilitate 3D telepresence is not possible with such headsets. Here we propose and demonstrate a new integrated platform to provide mobile 3D telepresence experience using a head-worn device and a dual-purpose passive screen. At the core of this telepresence architecture, we use a portable multi-layered passive screen which facilitates the stereoscopic 3D display using a pair of head-worn projectors and at the same time, captures the multi-perspective views of the user on a head-worn camera through reflections of the screen. The screen contains retroreflective material for stereo image display and an array of convex mirrors for 3D capture. The 3D telepresence is demonstrated using an experimental setup where a local-user wearing the developed head-worn device perceives the 3D images on the dual-purpose screen, while the captured perspective views of user-1 are rendered as stereo viewpoints and showed to the user-2 on a virtual reality headset.

The Head Mounted Projection Display (HMPD) is a growing interest area in HCI. Although various aspects of HMPDs have been investigated, there is not enough information regarding the effect of HMPDs (i.e., head referenced static and dynamic displays while a user is in motion and standing) on visual attentional performance. For this purpose, we conducted a user study (N=18) with three experimental conditions (control, standing, walking) and two visual perceptual tasks (with dynamic and static displays). Significant differences between conditions were only found for the task with dynamic display; accuracy was lower in walking condition compared to the other two conditions. Our work contributes an empirical investigation of the effect of HMPDs on visual attentional performance by providing data-driven benchmarks for developing graphical user interface design guidelines for HMPDs.