Tracking Failure Research Articles

SiLK-SLAM: accurate, robust and versatile visual SLAM with simple learned keypoints

PurposeWeak repeatability is observed in handcrafted keypoints, leading to tracking failures in visual simultaneous localization and mapping (SLAM) systems under challenging scenarios such as illumination change, rapid rotation and large angle of view variation. In contrast, learning-based keypoints exhibit higher repetition but entail considerable computational costs. This paper proposes an innovative algorithm for keypoint extraction, aiming to strike an equilibrium between precision and efficiency. This paper aims to attain accurate, robust and versatile visual localization in scenes of formidable complexity.Design/methodology/approachSiLK-SLAM initially refines the cutting-edge learning-based extractor, SiLK, and introduces an innovative postprocessing algorithm for keypoint homogenization and operational efficiency. Furthermore, SiLK-SLAM devises a reliable relocalization strategy called PCPnP, leveraging progressive and consistent sampling, thereby bolstering its robustness.FindingsEmpirical evaluations conducted on TUM, KITTI and EuRoC data sets substantiate SiLK-SLAM’s superior localization accuracy compared to ORB-SLAM3 and other methods. Compared to ORB-SLAM3, SiLK-SLAM demonstrates an enhancement in localization accuracy even by 70.99%, 87.20% and 85.27% across the three data sets. The relocalization experiments demonstrate SiLK-SLAM’s capability in producing precise and repeatable keypoints, showcasing its robustness in challenging environments.Originality/valueThe SiLK-SLAM achieves exceedingly elevated localization accuracy and resilience in formidable scenarios, holding paramount importance in enhancing the autonomy of robots navigating intricate environments. Code is available at https://github.com/Pepper-FlavoredChewingGum/SiLK-SLAM.

Probabilistic 3D motion model for object tracking in aerial applications

AbstractVisual object tracking, crucial in aerial applications such as surveillance, cinematography, and chasing, faces challenges despite AI advancements. Current solutions lack full reliability, leading to common tracking failures in the presence of fast motions or long‐term occlusions of the subject. To tackle this issue, a 3D motion model is proposed that employs camera/vehicle states to locate a subject in the inertial coordinates. Next, a probability distribution is generated over future trajectories and they are sampled using a Monte Carlo technique to provide search regions that are fed into an online appearance learning process. This 3D motion model incorporates machine‐learning approaches for direct range estimation from monocular images. The model adapts computationally by adjusting search areas based on tracking confidence. It is integrated into DiMP, an online and deep learning‐based appearance model. The resulting tracker is evaluated on the VIOT dataset with sequences of both images and camera states, achieving a 68.9% tracking precision compared to DiMP's 49.7%. This approach demonstrates increased tracking duration, improved recovery after occlusions, and faster motions. Additionally, this strategy outperforms random searches by about 3.0%.

Deep-feature-based asymmetrical background-aware correlation filter for object tracking

Correlation filter-based video object-tracking algorithms have gained widespread attention due to their efficiency and excellent tracking performance. However, traditional correlation filtering tracking algorithms possess several limitations. (1) They extract image features only by using rule sampling, which ignores the shape information of the target, resulting in insufficient discriminative power of the features. (2) They focus only on the difference between the background and the object, ignoring the effects of more challenging intra-class interference. (3) They do not further evaluate the reliability of the optimal candidate samples, resulting in easy failure in occlusion scenarios. This paper proposes an asymmetric background-aware correlation filter method for object tracking with deep features to solve the above limitations. First, an asymmetrical background-aware sampling method based on the shape information of the object is proposed. This sampling method significantly differs from the symmetrical sampling method in the traditional correlation filter framework. By exploring the shape information of the object, improving the otherness between the background and object samples is easy, thus suppressing the intra-class interferences. Second, deep neural networks are introduced in the correlation filter framework to extract the deep object features and a spatio-temporal regularization factor is adaptively assigned to suppress the boundary effects, intra-class distractors and aberrance between frames. Finally, a multi-modal object pool is constructed to evaluate the optimal candidate sample in each frame. This template pool fully exploits object diversity and solves the tracking drift and failure caused by invalid appearance changes in scenes such as occlusion and vigorous motion scenarios. To validate the effectiveness of the proposed method, it was compared with the state-of-the-art methods on public datasets. The experimental results show that the tracking performance of the proposed method is competitive.

AODiMP‐TIR: Anti‐occlusion thermal infrared targets tracker based on SuperDiMP

AbstractTo address the issue of tracking drift and failures in thermal infrared (TIR) tracking tasks caused by target occlusion, this study proposes an anti‐occlusion TIR target tracker named AODiMP‐TIR. This approach involves an anti‐occlusion strategy that relies on target occlusion status determination and trajectory prediction. This enables the prediction of the target's current position when it is identified as occluded, ensuring swift recapture upon reappearance. A criterion is introduced for occlusion status determination based on the classification response map of SuperDiMP. Additionally, a trajectory mapping module designed to decouple target motion from camera motion is presented, enhancing the precision of trajectory prediction. Comparative experiments with other state‐of‐the‐art trackers are conducted on the large‐scale high‐diversity thermal infrared object tracking benchmark (LSOTB‐TIR), LSOTB‐TIR100, and thermal infrared pedestrian tracking benchmark (PTB‐TIR) datasets. The results indicate that the AODiMP‐TIR performs well across all three datasets, particularly exhibiting outstanding performance in occlusion sequences. Furthermore, ablation study experiments confirm the effectiveness of the anti‐occlusion strategy, occlusion determination criterion and trajectory mapping module.

One step back, two steps forward: learning moves to recover from SLAM tracking failures

Tracking failure in state-of-the-art visual SLAM has been reported to be frequent and hampers real-world deployment of SLAM solutions. Very recently, efforts have been made to avoid tracking failure using various methods (e.g. using deep reinforcement learning to plan a path where the risk of tracking failure is minimal). The results of those approaches are encouraging but are far from producing a failure-free visual system. Failure is inevitable in vision-based systems. Therefore, developing recovery (post-failure) solutions might be a better approach in developing more reliable systems. To this end, we propose a novel, easily trainable, deep recovery maneuver algorithm. Instead of predicting tracking failures, our algorithm predicts the back stepping move, post failure, which helps regain tracking. With our proposed simple approach, state-of-the-art SLAM manages to complete 13 out of 50 navigation episodes (13x improvement over the baseline). Furthermore, even for cases where our algorithm fails to complete the route, it traverses 2x longer distances as compared to baseline methods.

A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking

Performance of modern trackers degrades substantially on transparent objects compared to opaque objects. This is largely due to two distinct reasons. Transparent objects are unique in that their appearance is directly affected by the background. Furthermore, transparent object scenes often contain many visually similar objects (distractors), which often lead to tracking failure. However, development of modern tracking architectures requires large training sets, which do not exist in transparent object tracking. We present two contributions addressing the aforementioned issues. We propose the first transparent object tracking training dataset Trans2k that consists of over 2k sequences with 104,343 images overall, annotated by bounding boxes and segmentation masks. Standard trackers trained on this dataset consistently improve by up to 16%. Our second contribution is a new distractor-aware transparent object tracker (DiTra) that treats localization accuracy and target identification as separate tasks and implements them by a novel architecture. DiTra sets a new state-of-the-art in transparent object tracking and generalizes well to opaque objects.

Research on Inter-Frame Feature Mismatch Removal Method of VSLAM in Dynamic Scenes

Visual Simultaneous Localization and Mapping (VSLAM) estimates the robot’s pose in three-dimensional space by analyzing the depth variations of inter-frame feature points. Inter-frame feature point mismatches can lead to tracking failure, impacting the accuracy of the mobile robot’s self-localization and mapping. This paper proposes a method for removing mismatches of image features in dynamic scenes in visual SLAM. First, the Grid-based Motion Statistics (GMS) method was introduced for fast coarse screening of mismatched image features. Second, an Adaptive Error Threshold RANSAC (ATRANSAC) method, determined by the internal matching rate, was proposed to improve the accuracy of removing mismatched image features in dynamic and static scenes. Third, the GMS-ATRANSAC method was tested for removing mismatched image features, and experimental results showed that GMS-ATRANSAC can remove mismatches of image features on moving objects. It achieved an average error reduction of 29.4% and 32.9% compared to RANSAC and GMS-RANSAC, with a corresponding reduction in error variance of 63.9% and 58.0%, respectively. The processing time was reduced by 78.3% and 38%, respectively. Finally, the effectiveness of inter-frame feature mismatch removal in the initialization thread of ORB-SLAM2 and the tracking thread of ORB-SLAM3 was verified for the proposed algorithm.

Globalization’s Cultural Odyssey: Navigating Multicultural Waters in Business

Globalization has ushered in a transformative era in business, eradicating borders and fostering cross-border commerce. This phenomenon has led to an influx of multinational corporations (MNCs) venturing into developing nations. Consequently, MNCs are now prevalent in various countries, with diverse cultural landscapes. The essence of managing across cultures has emerged as a direct outcome of globalization, necessitating that expatriates, hailing from foreign cultures, adapt to and lead individuals from disparate cultural backgrounds in unfamiliar settings. This challenge has yielded a mixed track record, with both successes and failures. Managing across cultures demands the intricate balance of assimilating into, and yet retaining, one’s own culture while comprehending and respecting the cultures, customs, management practices, and preferences of others. It is a dynamic process of adjusting to a multitude of sometimes conflicting cultures while preserving one’s own cultural identity

Online Learning Samples and Adaptive Recovery for Robust RGB-T Tracking

With the increasing diversity of visual tracking tasks, object tracking in RGB and thermal (RGB-T) modalities has received widespread interest. Most of the existing RGB-T tracking methods mainly improve tracking performance by integrating hierarchically complementary information from RGB and thermal modalities, however, they are insufficient in handling tracking failures due to the lack of re-detection capability. To address these issues, we propose a new RGB-T tracking method with online learning samples and adaptive object recovery. First, the features of RGB and thermal modalities are concatenated for robust appearance modeling. Second, a multimodal fusion strategy is designed to stably integrate reliable information of modalities and propose to use similarity to measure tracking confidence. Finally, a detector with online learning of positive and negative samples and adaptive recovery is developed to correct unreliable tracking results. Numerical results on five recent large-scale benchmark datasets demonstrate that the proposed tracker achieves competitive performance compared to other state-of-the-art methods.

The parameter identification of metro rail corrugation based on effective signal extraction and inertial reference method

Rail corrugation is a severe track damage and failure problem in metro lines. So, the accurate assessment of rail corrugation is significant for the safety and comfort of vehicles. It is an efficient means to detect rail corrugation through the acceleration signal. However, the acceleration signal contains the mixed signal caused by vehicle component noise and wheel polygonal wear, resulting in poor rail corrugation detection accuracy. Therefore, a new method is presented to extract the effective signal components and accurately identify the rail corrugation. Firstly, the Cubic mapping, modified sine algorithm, and Lévy flight are introduced into the dung beetle optimizer algorithm. A new improved dung beetle optimizer (IDBO) algorithm is presented to optimize the hyperparameters of the VMD algorithm, which can increase the signal decomposition performance of the VMD. Secondly, the fast independent component analysis method separates the independent components (ICs) from the VMD modes and original acceleration signal. Based on the selection criteria of ICs, the dominant signal components related to rail corrugation are determined. The rail corrugation amplitude can be obtained through the inertial reference method. The experimental results demonstrate that the presented method has better rail corrugation recognition accuracy, the root mean square error is smaller than the comparison method, and the corrugation wavelength of the straight track is larger than the curve track.

A comparative study on the influence of typical track failures on high-speed pantograph-catenary interaction dynamics

Different track failures are proven to have different influences on train-track interactions, but their influence on pantograph-catenary interactions has not been investigated thus far. In this work, the influences of typical track failures on pantograph-catenary interaction dynamics are first investigated. A reduced train-track-pantograph-catenary interaction model is developed to study these effects. In this model, the long catenary is reduced to a small moving area around the moving pantograph, and this area is considered and modelled as the reduced catenary model based on the arbitrary Lagrangian–Eulerian method. The reduced catenary model and moving pantograph are formulated as the reduced pantograph-catenary interaction model, and it is further unidirectionally connected with the existing reduced train-track interaction model to formulate the reduced train-track-pantograph-catenary interaction model. The present reduced pantograph-catenary model is first validated by the EN50318-2018 standard, and the influences of track irregularity, track buckling, fastening failure, and track settlement on pantograph-catenary interaction dynamics are studied. The investigation results first show that the track settlement with a long wavelength has a significant influence on the pantograph-catenary interaction dynamics and can even cause contact loss with a good train-track interaction behaviour. Thus, it should be further mentioned in the maintenance of the track structure.

Duality-Gated Mutual Condition Network for RGBT Tracking.

Low-quality modalities contain not only a lot of noisy information but also some discriminative features in RGB-Thermal (RGBT) tracking. However, the potentials of low-quality modalities are not well explored in existing RGBT tracking algorithms. In this work, we propose a novel duality-gated mutual condition network to fully exploit the discriminative information of all modalities while suppressing the effects of data noise. In specific, we design a mutual condition module, which takes the discriminative information of a modality as the condition to guide feature learning of target appearance in another modality. Such a module can effectively enhance target representations of all modalities even in the presence of low-quality modalities. To improve the quality of conditions and further reduce data noise, we propose a duality-gated mechanism and integrate it into the mutual condition module. To deal with the tracking failure caused by sudden camera motion, which often occurs in RGBT tracking, we design a resampling strategy based on optical flow. It does not increase much computational cost since we perform optical flow calculation only when the model prediction is unreliable and then execute resampling when the sudden camera motion is detected. Extensive experiments on four RGBT tracking benchmark datasets show that our method performs favorably against the state-of-the-art tracking algorithms.

SiamEFT: adaptive-time feature extraction hybrid network for RGBE multi-domain object tracking.

Integrating RGB and Event (RGBE) multi-domain information obtained by high-dynamic-range and temporal-resolution event cameras has been considered an effective scheme for robust object tracking. However, existing RGBE tracking methods have overlooked the unique spatio-temporal features over different domains, leading to object tracking failure and inefficiency, especally for objects against complex backgrounds. To address this problem, we propose a novel tracker based on adaptive-time feature extraction hybrid networks, namely Siamese Event Frame Tracker (SiamEFT), which focuses on the effective representation and utilization of the diverse spatio-temporal features of RGBE. We first design an adaptive-time attention module to aggregate event data into frames based on adaptive-time weights to enhance information representation. Subsequently, the SiamEF module and cross-network fusion module combining artificial neural networks and spiking neural networks hybrid network are designed to effectively extract and fuse the spatio-temporal features of RGBE. Extensive experiments on two RGBE datasets (VisEvent and COESOT) show that the SiamEFT achieves a success rate of 0.456 and 0.574, outperforming the state-of-the-art competing methods and exhibiting a 2.3-fold enhancement in efficiency. These results validate the superior accuracy and efficiency of SiamEFT in diverse and challenging scenes.

FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching

HighlightsExisting tracking methods face challenges in accuracy and robustness.FishMOT (Multiple Object Tracking for Fish) is a novel fish-tracking approach combining object detection and IoU matching.FishMOT outperforms state-of-the-art multi-target trackers and specialized fish-tracking tools on several metrics.The simplified workflow and strong performance make FishMOT a highly effective fish-tracking approach.Abstract. Fish tracking plays a vital role in understanding fish behavior and ecology. However, existing tracking methods face challenges in accuracy and robustness due to morphological changes in fish, occlusion, and complex environments. This article proposes FishMOT (Multiple Object Tracking for Fish), a novel fish tracking approach combining object detection and IoU (Intersection over Union) matching, including a basic module, an interaction module, and a refind module. Wherein, a basic module performs target association based on the IoU of detection boxes between successive frames to deal with the morphological change of fish; an interaction module combines the IoU of detection boxes and the IoU of fish entities to handle occlusions; and a refind module uses spatio-temporal information to overcome the tracking failure resulting from the missed detection by the detector in a complex environment. FishMOT reduces the computational complexity and memory consumption since it does not require complex feature extraction or identity assignment per fish and does not need a Kalman filter to predict the detection boxes of successive frames. Experimental results demonstrate FishMOT outperforms state-of-the-art multi-object trackers and specialized fish tracking tools in terms of MOTA (Multiple Object Tracking Accuracy), accuracy, computation time, memory consumption, etc. Furthermore, the method exhibits excellent robustness and generalizability for varying environments and fish numbers. The simplified workflow and strong performance make FishMOT a highly effective fish-tracking approach. The source codes and pre-trained models are available at: https://github.com/gakkistar/FishMOT. Keywords: Behavior analysis, Fish behavior, Fish tracking, Multiple object tracking, Object detection.

Applicability of J-CTO channel score to predict microcatheter tracking during retrograde percutaneous coronary intervention of chronic total occlusions: Insights from the SURFING MICRO registry.

The J-chronic total occlusion(CTO) channel score can predict guidewire tracking of the collateral channels(CCs), but its efficacy in predicting microcatheter tracking has never been tested in the setting of retrograde CTO-percutaneous coronary intervention(PCI). Predicting microcatheter collateral tracking during retrograde CTO-PCIs. A total of 189 patients undergoing retrograde CTO-PCI from April 2017 to August 2021 were screened. The primary outcome of interest was a correlation between J-CTO channel score and microcatheter tracking failure (MTF) after successful CC tracking by the guidewire. The independent association between anatomical features of the J-CTO channel score and the primary outcome of interest was explored. After adjustment, only small size (adjusted OR: 12.70, 95% confidence interval [CI]: 1.79-89.82; p = 0.01) and continuous bends (adjusted OR: 14.15, 95% CI: 2.77-72.34; p < 0.001) remained significantly associated with an increased risk of MTF for septal collaterals. The small size was the only predictor of the MTF for epicardial collaterals (OR: 6.39, 95% CI: 1.13-35.96; p = 0.020) at univariate analysis. Patients in the MTF group had a lower incidence of procedural success compared with patients in the microcatheter tracking success (MTS) group (40.0% vs. 93.9%, p < 0.001) and had a higher incidence of collateral perforations (20.0% vs. 3.0%, p < 0.001). Small and tortuous septal collaterals, identified by a score ≥3, are associated with an increased risk of MTF, lower incidence of procedural success, and higher risk of procedural complications driven by collateral perforations.

Visual Localization and Mapping in Dynamic and Changing Environments

The real-world deployment of fully autonomous mobile robots depends on a robust simultaneous localization and mapping (SLAM) system, capable of handling dynamic environments, where objects are moving in front of the robot, and changing environments, where objects are moved or replaced after the robot has already mapped the scene. This paper proposes Changing-SLAM, a method for robust Visual SLAM in both dynamic and changing environments. This is achieved by using a Bayesian filter combined with a long-term data association algorithm. Also, it employs an efficient algorithm for dynamic keypoints filtering based on object detection that correctly identifies features inside the bounding box that are not dynamic, preventing a depletion of features that could cause lost tracks. Furthermore, a new dataset was developed with RGB-D data specially designed for the evaluation of changing environments on an object level, called PUC-USP dataset. Six sequences were created using a mobile robot, an RGB-D camera and a motion capture system. The sequences were designed to capture different scenarios that could lead to a tracking failure or map corruption. Changing-SLAM does not assume a given camera pose or a known map, being also able to operate in real time. The proposed method was evaluated using benchmark datasets and compared with other state-of-the-art methods, proving to be highly accurate.

Moving Target Tracking Method Based on Improved Camshift

&lt;p&gt;Aiming at the problem that target occlusion and other disturbances in complex background will reduce the tracking accuracy of moving target, and even lead to tracking failure, this paper proposes a moving target tracking algorithm based on the improved Camshift algorithm. Firstly, Gaussian background is used to model the foreground image to improve the backprojection image, and then the interference of backprojection is removed to improve the tracking effect in complex background conditions. Secondly, Kalman filtering is utilized to predict the trajectory, which further improves the tracking accuracy of Camshift algorithm in occlusion condition. A lot of experiments are processed, and the results show that the proposed algorithm could effectively improve the tracking accuracy and meet the real-time requirements.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Joint spatio-temporal modeling for visual tracking

Similarity-based approaches have made significant progress in visual object tracking (VOT). Although these methods work well in simple scenes, they ignore the continuous spatio-temporal connection of the object in the video sequence. For this reason, tracking by spatial matching solely can lead to tracking failures because of distractors and occlusion. In this paper, we propose a spatio-temporal joint-modeling tracker named STTrack which implicitly builds continuous connections between the temporal and spatial aspects of the sequence. Specifically, we first design a time-sequence iteration strategy (TSIS) to concentrate on the temporal connection of the object in the video sequence. Then, we propose a novel spatial temporal interaction Transformer network (STIN) to capture the spatio-temporal correlation of the object between frames. The proposed STIN module is robust in object occlusion because it explores the dynamic state change dependencies of the object. Finally, we introduce a spatio-temporal query to suppress distractors by iteratively propagating the target prior. Extensive experiments on six tracking benchmark datasets demonstrate that the proposed STTrack achieves excellent performance while operating in real-time. The code is publicly available at https://github.com/nubsym/STTrack.

Multi-Pedestrian Tracking Based on KC-YOLO Detection and Identity Validity Discrimination Module

Multiple-object tracking (MOT) is a fundamental task in computer vision and is widely applied across various domains. However, its algorithms remain somewhat immature in practical applications. To address the challenges presented by complex scenarios featuring instances of missed detections, false alarms, and frequent target switching leading to tracking failures, we propose an approach to multi-object tracking utilizing KC-YOLO detection and an identity validity discrimination module. We have constructed the KC-YOLO detection model as the detector for the tracking task, optimized the selection of detection frames, and implemented adaptive feature refinement to effectively address issues such as incomplete pedestrian features caused by occlusion. Furthermore, we have introduced an identity validity discrimination module in the data association component of the tracker. This module leverages the occlusion ratio coefficient, denoted by “k”, to assess the validity of pedestrian identities in low-scoring detection frames following cascade matching. This approach not only enhances pedestrian tracking accuracy but also ensures the integrity of pedestrian identities. In experiments on the MOT16, MOT17, and MOT20 datasets, MOTA reached 75.9%, 78.5%, and 70.1%, and IDF1 reached 74.8%, 77.8%, and 72.4%. The experimental results demonstrate the superiority of the methodology. This research outcome has potential applications in security monitoring, including public safety and fire prevention, for tracking critical targets.

Fall risk management in interventional prenatal diagnosis perioperative pregnant women based on tracking methodology and failure mode and effect analysis application.

The aim was to explore the effectiveness of a tracing methodology combined with failure mode and effect analysis (FMEA) for managing falls in pregnant women during the perioperative period of interventional prenatal diagnosis. Using the tracing methodology, the process was evaluated and analyzed using FMEA after reviewing data, on-site interview, case tracking and on-site inspection, and improvement measures were proposed for the existing risk factors, and the fall-related quality indicators, satisfaction with fall-related health education, and risk priority number were compared before and after implementation. Effectiveness analysis for interventional prenatal diagnosis of perioperative maternal falls risk management resulted in a significant decrease in risk priority number (P < .01), a significant increase in the rate of correct fall risk identification and assessment, correct handover rate of pregnant women at risk of falls, correct intervention rate of pregnant women at high risk of falls, and effective coverage of falls-related health education (P < .01), a significant increase in satisfaction with falls-related health education (P < .001), and the incidence of falls among pregnant women decreased from 0.12% to 0%. The use of tracking methodology combined with FMEA can reduce the risk of perioperative maternal falls in interventional prenatal diagnosis and improve the safety of maternal visits.