• Teacher-Student model to minimize the different modality gap. Joint cycle-consistency GAN generate corresponding image pairs. Only use main backbone in test stage for efficiency. Numerous experiments conducted have proven effectiveness of proposed model. RGB-Infrared (RGB-IR) person re-identification (ReID) is a technology where system can automatically identify same appearing at parts video ...

Plant diseases have become an important issue because they cause important reduction in each quality and amount of agricultural products. Automatic detection of plant diseases is an important analysis topic because it could significantly help in observation giant fields, and enable automatic detection the symptoms of diseases as soon as they appear on the plant leaves. In this paper an algorith...

In this study, a novel single-image based dehazing framework is proposed to remove haze artifacts from images through local atmospheric light estimation. We use a novel strategy based on a physical model where the extreme intensity of each RGB pixel is used to define an initial atmospheric veil (local atmospheric light veil). Across bilateral filter is applied to each veil to achieve both local...

Color-depth cameras (RGB-D cameras) have become the primary sensors in most robotics systems, from service robotics to industrial robotics applications. Typical consumergrade RGB-D cameras are provided with a coarse intrinsic and extrinsic calibration that generally does not meet the accuracy requirements needed by many robotics applications (e.g., high accuracy 3D environment reconstruction an...

The recent availability of low-cost RGB-D sensors and the maturity of machine vision algorithms makes shape-based parametric modeling of 3D objects in natural environments more practical than ever before. In this paper, we investigate the use of RGB-D based modeling of natural objects using RGB-D sensors and a combination of volumetric 3D reconstruction and parametric shape modeling. We apply t...

Recent works on interactive video object cutout mainly focus on designing dynamic foreground-background (FB) classifiers for segmentation propagation. However, the research on optimally removing errors from the FB classification is sparse, and the errors often accumulate rapidly, causing significant errors in the propagated frames. In this work, we take the initial steps to addressing this prob...

In the study of SLAM problem using an RGB-D camera, depth information and visual information as two types of primary measurement data are rarely tightly coupled during refinement of camera pose estimation. In this paper, a new method of RGB-D camera SLAM is proposed based on extended bundle adjustment with integrated 2D and 3D information on the basis of a new projection model. First, the geome...

The human hand moves in complex and highdimensional ways, making estimation of 3D hand pose configurations from images alone a challenging task. In this work we propose a method to learn a statistical hand model represented by a cross-modal trained latent space via a generative deep neural network. We derive an objective function from the variational lower bound of the VAE framework and jointly...

3D model of indoor environments provide rich information that can facilitate the disambiguation of different places and increases the familiarization process to any indoor environment for the remote users. In this research work, we describe a system for visual odometry and 3D modeling using information from RGB-D sensor (Camera). The visual odometry method estimates the relative pose of the con...

While recent deep neural networks have achieved promising results for 3D reconstruction from a single-view image, these rely on the availability of RGB textures in images and extra information as supervision. In this work, we propose novel stacked hierarchical networks and an end to end training strategy to tackle a more challenging task for the first time, 3D reconstruction from a single-view ...