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.

Martian terrain segmentation plays a crucial role in autonomous navigation and safe driving of Mars rovers as well as global analysis of Martian geological landforms. However, most deep learning-based segmentation models cannot effectively handle the challenges of highly unstructured and unbalanced terrain distribution on the Martian surface, thus leading to inadequate adaptability and generalization ability. In this paper, we propose a novel multi-view Martian Terrain Segmentation framework (MTSNet) by developing an efficient Martian Terrain text-Guided Segment Anything Model (MTG-SAM) and combining it with a tailored Local Terrain Feature Enhancement Network (LTEN) to capture intricate terrain details. Specifically, the proposed MTG-SAM is equipped with a Terrain Context attention Adapter Module (TCAM) to efficiently and effectively unleashing the model adaptability and transferability on Mars-specific terrain distribution. Then, a Local Terrain Feature Enhancement Network (LTEN) is designated to compensate for the limitations of MTG-SAM in capturing the fine-grained local terrain features of Mars surface. Afterwards, a simple yet efficient Gated Fusion Module (GFM) is introduced to dynamically merge the global contextual features from MTG-SAM encoder and the local refined features from LTEN module for comprehensive terrain feature learning. Moreover, the proposed MTSNet enables terrain-specific text as prompts resolving the efficiency issue of existing methods that require costly annotation of bounding boxes or foreground points. Experimental results on AI4Mars and ConeQuest datasets demonstrate that our proposed MTSNet can effectively learns the unique Martian terrain feature distribution and achieves state-of-the-art performance on multi-view terrain segmentation from both the perspectives of the Mars rover and the satellite remote sensing. Code is available at https://github.com/raoxuefeng/mtsnet.

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.

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.

Blind image deblurring (BID) is an ill-posed inverse problem and becomes challengingwhen blurry observations are contaminated by severe outliers. Conventional maximuma posteriori (MAP) formulations typically rely on residual-minimizing data-fidelityterms, whose estimates can be biased by corrupted measurements. To address this limitation,we propose a unified plug-and-play Maximum-Consensus MAP (MC-MAP)framework that rethinks data fidelity by seeking the image–kernel pair supported bythe largest subset of measurements satisfying a prescribed residual tolerance. Unlikeconventional residual minimization, MC distinguishes inliers from outliers accordingto a prescribed residual tolerance and minimizes the number of measurements violatingthis bound, thereby reducing the influence of severe outliers and mitigating theresulting masking and swamping effects. Importantly, the proposed MC mechanism isprior-independent and can be combined with domain-appropriate priors within a unifiedformulation. For face and general natural images, MC is integrated with diffusionpriors through reverse posterior sampling, whereas for text images it is combined withsparsity priors. A unified optimization framework based on the Alternating DirectionMethod of Multipliers (ADMM) and Half-Quadratic Splitting (HQS) decomposes theresulting discontinuous and nonconvex MC-MAP problem into shared MC auxiliaryvariableupdates and prior-specific image and kernel updates. Experiments on textimages, FFHQ, AFHQ, and ImageNet under Gaussian and motion blur with outliercontamination demonstrate consistent improvements in both latent-image restoration and blur-kernel estimation over representative BID methods. These results establishMC as a flexible and robust data-fitting principle that accommodates heterogeneouspriors across diverse image domains.