Camera tracking and the construction of a robust and accurate map in unknown environments are still challenging tasks in computer vision and robotic applications. Visual Simultaneous Localization and Mapping (SLAM) along with Augmented Reality (AR) are two important applications, and their performance is entirely dependent on the accuracy of the camera tracking routine. This paper presents a novel feature-based approach for the monocular SLAM problem using a hand-held camera in room-sized workspaces with a maximum scene depth of 4–5 m. In the core of the proposed method, there is a Particle Filter (PF) responsible for the estimation of extrinsic parameters of the camera. In addition, contrary to key-frame based methods, the proposed system tracks the camera frame by frame and constructs a robust and accurate map incrementally. Moreover, the proposed algorithm initially constructs a metric sparse map. To this end, a chessboard pattern with a known cell size has been placed in front of the camera for a few frames. This enables the algorithm to accurately compute the pose of the camera and therefore, the depth of the primary detected natural feature points are easily calculated. Afterwards, camera pose estimation for each new incoming frame is carried out in a framework that is merely working with a set of visible natural landmarks. Moreover, to recover the depth of the newly detected landmarks, a delayed approach based on linear triangulation is used. The proposed method is applied to a realworld VGA quality video (640 × 480 pixels) where the translation error of the camera pose is less than 2 cm on average and the orientation error is less than 3 degrees, which indicates the effectiveness and accuracy of the developed algorithm.

Artificial intelligence techniques for image pattern recognition and retrieval are pivotal in various applications, particularly in medical imaging. Despite numerous existing methods, the process remains complex and computationally intensive. This study introduces an innovative approach to content-based image retrieval (CBIR) by integrating Local Average Binary Patterns (LABP) and the joint probability distribution of color channels. LABP extends the traditional Local Binary Pattern (LBP) by considering multiple layers of neighboring pixels, enabling a more comprehensive texture representation. Additionally, we propose a novel color feature extraction method based on the discrete joint probability distribution of RGB color channels, providing a robust representation of color information. The effectiveness of the proposed method is validated on the Wang (Corel-1k) and Corel-10k datasets, demonstrating superior precision compared to other state-of-the-art techniques. This work contributes to enhancing CBIR performance by combining these novel features into a unified feature vector, improving efficiency and accuracy, especially in large datasets. The code and links to datasets are publicly available at https://github.com/BU-AILab/LABP.