Accurate 6DoF (degrees of freedom) pose and focal length estimation are important in extended reality (XR) applications, enabling precise object alignment and projection scaling, thereby enhancing user experiences. This study focuses on improving 6DoF pose estimation using single RGB images of unknown camera metadata. Estimating the 6DoF pose and focal length from an uncontrolled RGB image, obtained from the internet, is challenging because it often lacks crucial metadata. Existing methods such as FocalPose and Focalpose++ have made progress in this domain but still face challenges due to the projection scale ambiguity between the translation of an object along the z-axis ($t_z$) and the camera’s focal length. To overcome this, we propose a two-stage strategy that decouples the projection scaling ambiguity in the estimation of z-axis translation and focal length. In the first stage, $t_z$ is set arbitrarily, and we predict all the other pose parameters and focal length relative to the fixed $t_z$. In the second stage, we predict the true value of $t_z$ while scaling the focal length based on the $t_z$ update. The proposed two-stage method reduces projection scale ambiguity in RGB images and improves pose estimation accuracy. The iterative update rules constrained to the first stage and tailored loss functions including Huber loss in the second stage enhance the accuracy in both 6DoF pose and focal length estimation. Experimental results using benchmark datasets show significant improvements in terms of median rotation and translation errors, as well as better projection accuracy compared to the existing state-of-the-art methods. In an evaluation across the Pix3D datasets (chair, sofa, table, and bed), the proposed two-stage method improves projection accuracy by approximately 7.19%. Additionally, the incorporation of Huber loss resulted in a significant reduction in translation and focal length errors by 20.27% and 6.65%, respectively, in comparison to the Focalpose++ method.

This study presents six degrees of freedom (6-DoF) pose estimation of an object from a single RGB image and retrieval of the matching CAD model by measuring the similarity between RGB and CAD rendering images. The 6-DoF pose estimation of an RGB object is one of the important techniques in 3D computer vision. However, in addition to 6-DoF pose estimation, retrieval and alignment of the matching CAD model with the RGB object should be performed for various industrial applications such as eXtended Reality (XR), Augmented Reality (AR), robot’s pick and place, and so on. This paper addresses 6-DoF pose estimation and CAD model retrieval problems simultaneously and quantitatively analyzes how much the 6-DoF pose estimation affects the CAD model retrieval performance. This study consists of two main steps. The first step is 6-DoF pose estimation based on the PoseContrast network. We enhance the structure of PoseConstrast by adding variance uncertainty weight and feature attention modules. The second step is the retrieval of the matching CAD model by an image similarity measurement between the CAD rendering and the RGB object. In our experiments, we used 2000 RGB images collected from Google and Bing search engines and 100 CAD models from ShapeNetCore. The Pascal3D+ dataset is used to train the pose estimation network and DELF features are used for the similarity measurement. Comprehensive ablation studies about the proposed network show the quantitative performance analysis with respect to the baseline model. Experimental results show that the pose estimation performance has a positive correlation with the CAD retrieval performance.

Traffic accidents have emerged as a serious global concern, resulting in daily casualties and prompting authorities to prioritize accident prevention measures. This study presents an accident prediction system that alerts drivers of potential accidents by analyzing multiple attributes which are the potential courses of accidents. While previous studies have predominantly focused on analyzing geographical factors, predicting accident frequencies, and assessing accident risks, this study aims to develop two systems—an advanced route recommendation system and a real-time accident prediction system—to enhance road safety. Moreover, existing systems often predict post hoc accident occurrences or have limited geographical coverage. The advanced route recommendation system is designed to assist users in planning their journeys by providing them with the safest routes in advance. Through a website interface, users can log in and receive personalized recommendations on the accident prone areas on their path, based on factors such as historical accident data, road conditions, traffic patterns and weather conditions. This system aims to empower individuals to make informed decisions and reduce the likelihood of accidents during their trips in advance. The real-time accident prediction system aims to provide drivers with up-to-date information on potential accidents along their routes. By utilizing GPS coordinates and retrieving live data, including weather conditions and real-time accident reports, the system predicts accident-prone areas in real-time. Drivers receive these predictions through a mobile application as an audio message, enabling them to make timely adjustments to their routes and avoid hazardous situations. Additionally, static predictions are displayed on a website, featuring markers indicating accident-prone areas. The research utilizes an extensive dataset of "US Accident Dataset" spanning across all 49 states of the USA. Results demonstrate that the Random Forest classifier achieves an impressive 91.5% accuracy in predicting accident severity, surpassing previous studies. Furthermore, this paper conducts Exploratory Data Analysis, unveiling intriguing patterns in the dataset regarding accident occurrences.

This study addresses the challenge of accurate 6D pose estimation in Augmented Reality (AR), a critical component for seamlessly integrating virtual objects into real-world environments. Our research primarily addresses the difficulty of estimating 6D poses from uncontrolled RGB images, a common scenario in AR applications, which lacks metadata such as focal length. We propose a novel approach that strategically decomposes the estimation of z-axis translation and focal length, leveraging the neural-render and compare strategy inherent in the FocalPose architecture. This methodology not only streamlines the 6D pose estimation process but also significantly enhances the accuracy of 3D object overlaying in AR settings. Our experimental results demonstrate a marked improvement in 6D pose estimation accuracy, with promising applications in manufacturing and robotics. Here, the precise overlay of AR visualizations and the advancement of robotic vision systems stand to benefit substantially from our findings.