Multi-Object Tracking (MOT) involves the simultaneous tracking of multiple targets in a scene, demanding accurate discrimination of foreground and background, as well as precise identification of feature distinctions among diverse objects. Simple Online and Real-Time Tracking (SORT) is a widely adopted method in MOT, leveraging dual-phase Kalman Filter (KF) for object state estimation and ensuring consistent tracker association throughout a video sequence. Recent advancements in SORT-like algorithms aim to address nonlinear object motion and reduce reliance on detection for association in SORT. Despite these improvements, existing SORT-like methods often overlook camera motion, resulting in suboptimal motion prediction under dynamic camera conditions. In this paper, we introduce a novel SORT-like approach, termed Outlier Removal-based SORT (OR-SORT), which introduces a novel triple-phase Kalman Filter, encompassing prediction, re-prediction, and update phases. This framework dissects the object motion state transition model into distinct components—linear velocity self-motion and camera motion. Additionally, our method employs outlier removal based on Mixed Integer Linear Programming (MILP) to enhance camera motion estimation accuracy. Experimental evaluations on the MOTChallenge datasets, including the scenarios with both moving cameras and high object densities, demonstrate our method’s superior performance, particularly in scenarios with moving cameras. Our approach achieves a state-of-the-art MOTA of 80.7% and IDF1 of 79.6% on MOT17, and 77.9% and IDF1 of 76.4% on MOT20.

The blind text image deblurring problem presents a formidable challenge, requiring the recovery of a clean and sharp text image from a blurry version with an unknown blur kernel. Sparsity-based strategies have demonstrated their efficacy by emphasizing the sparse priors of the latent image and kernel. However, these existing strategies have largely neglected the influence of additional noise, imposing limitations on their performance. To overcome this limitation, we propose a novel framework designed to effectively mitigate the impact of extensive noise prevalent in blurred images. Our approach centers around a robust Maximum Consensus Framework, wherein we optimize the quantity of interest from the noisy blurry image based on the maximum consensus criterion. Furthermore, we propose the integration of the Alternating Direction Method of Multipliers (ADMM) and the Half-Quadratic Splitting (HQS) method to address the computationally intractable L0 norm problem. This innovative strategy enables improvements in the deblurring performance of blurry text images with the additional synthetic noise. Experimental evaluations conducted on various noisy blurry text images demonstrate the superiority of the proposed approach over existing methods.

The field of education is rapidly shifting toward digital platforms; however, aviation education continues to rely heavily on traditional paper-based manuals. This persistence is largely due to the inherent complexity, scale, and high costs associated with aviation equipment, making digital transformation particularly challenging. In this paper, we utilizing the analysis-by-synthesis method is presented for multi-view 3D reconstruction of solid objects, specifically focusing on aviation tools. To facilitate this research, a custom dataset was generated using Unity, enabling controlled experimentation and performance evaluation. Comparative analysis with existing benchmarks demonstrates that, despite the intricate nature of aviation tools compared to simpler objects, the proposed architecture effectively reconstructs detailed and accurate digital replicas. This advancement has the potential to enhance aviation education by providing immersive, interactive 3D content, thereby bridging the gap between traditional learning materials and modern digital education tools.

Robust geometric fitting is one of the crucial and fundamental problems in computer vision and pattern recognition. While random sampling and consensus maximization have been popular strategies for robust fitting, finding a balance between optimization quality and computational efficiency remains a persistent obstacle. In this paper, we adopt an optimization perspective and introduce a novel maximum consensus robust fitting algorithm that incorporates the maximum entropy framework into the consensus maximization problem. Specifically, we incorporate the probability distribution of inliers calculated using maximum entropy with consensus constraints. Furthermore, we introduce an improved relaxed and accelerated alternating direction method of multipliers (R-A-ADMMs) strategy tailored to our framework, facilitating an efficient solution to the optimization problem. Our proposed algorithm demonstrates superior performance compared to state-of-the-art methods on both synthetic and contaminated real datasets, particularly when dealing with contaminated datasets containing a high proportion of outliers.