Robust visual tracking with correlation filters and metric learning

SiamDF: Tracking training data-free siamese tracker

Much progress has been made in siamese tracking, primarily benefiting from increasing huge training data. However, very little attention has been really paid to the role of huge training data in learning an effective siamese tracker. In this study, we undertake an in-depth analysis of this issue from a novel optimization perspective, and observe that training data is particularly adept at background suppression, thereby refining target representation. Inspired by this insight, we present a data-free siamese tracking algorithm named SiamDF, which requires only a pre-trained backbone and no further fine-tuning on additional training data. Particularly, to suppress background distractors, we separately improve two branches of siamese tracking by retaining the pure target region as target input with the removal of template background, and by exploring an efficient inverse transformation to maintain the constant aspect ratio of target state in search region. Besides, we further promote the center displacement prediction of the entire backbone by eliminating its spatial stride deviations caused by convolution-like quantification operations. Our experimental results on several popular benchmarks demonstrate that SiamDF, free from both offline fine-tuning and online update, achieves impressive performance compared to well-established unsupervised and supervised tracking methods.

An adaptive spatiotemporal correlation filtering visual tracking method

Discriminative correlation filter (DCF) tracking algorithms are commonly used for visual tracking. However, we observed that different spatio-temporal targets exhibit varied visual appearances, and most DCF-based trackers neglect to exploit this spatio-temporal information during the tracking process. To address the above-mentioned issues, we propose a three-way adaptive spatio-temporal correlation filtering tracker, named ASCF, that makes fuller use of the spatio-temporal information during tracking. To be specific, we extract rich local and global visual features based on the Conformer network, establish three correlation filters at different spatio-temporal locations during the tracking process, and the three correlation filters independently track the target. Then, to adaptively select the correlation filter to achieve target tracking, we employ the average peak-to-correlation energy (APCE) and the peak-to-sidelobe ratio (PSR) to measure the reliability of the tracking results. In addition, we propose an adaptive model update strategy that adjusts the update frequency of the three correlation filters in different ways to avoid model drift due to the introduction of similar objects or background noise. Extensive experimental results on five benchmarks demonstrate that our algorithm achieves excellent performance compared to state-of-the-art trackers.

Robust thermal infrared tracking via an adaptively multi-feature fusion model

When dealing with complex thermal infrared (TIR) tracking scenarios, the single category feature is not sufficient to portray the appearance of the target, which drastically affects the accuracy of the TIR target tracking method. In order to address these problems, we propose an adaptively multi-feature fusion model (AMFT) for the TIR tracking task. Specifically, our AMFT tracking method adaptively integrates hand-crafted features and deep convolutional neural network (CNN) features. In order to accurately locate the target position, it takes advantage of the complementarity between different features. Additionally, the model is updated using a simple but effective model update strategy to adapt to changes in the target during tracking. In addition, a simple but effective model update strategy is adopted to adapt the model to the changes of the target during the tracking process. We have shown through ablation studies that the adaptively multi-feature fusion model in our AMFT tracking method is very effective. Our AMFT tracker performs favorably on PTB-TIR and LSOTB-TIR benchmarks compared with state-of-the-art trackers.

SiamATL: Online Update of Siamese Tracking Network via Attentional Transfer Learning

Visual object tracking with semantic deep features has recently attracted much attention in computer vision. Especially, Siamese trackers, which aim to learn a decision making-based similarity evaluation, are widely utilized in the tracking community. However, the online updating of the Siamese fashion is still a tricky issue due to the limitation, which is a tradeoff between model adaption and degradation. To address such an issue, in this article, we propose a novel attentional transfer learning-based Siamese network (SiamATL), which fully exploits the previous knowledge to inspire the current tracker learning in the decision-making module. First, we explicitly model the template and surroundings by using an attentional online update strategy to avoid template pollution. Then, we introduce an instance-transfer discriminative correlation filter (ITDCF) to enhance the distinguishing ability of the tracker. Finally, we suggest a mutual compensation mechanism that integrates cross-correlation matching and ITDCF detection into the decision-making subnetwork to achieve online tracking. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art tracking algorithms on multiple large-scale tracking datasets.

Lightweight Target-Aware Attention Learning Network-Based Target Tracking Method

Siamese network trackers based on pre-trained depth features have achieved good performance in recent years. However, the pre-trained depth features are trained in advance on large-scale datasets, which contain feature information of a large number of objects. There may be a pair of interference and redundant information for a single tracking target. To learn a more accurate target feature information, this paper proposes a lightweight target-aware attention learning network to learn the most effective channel features of the target online. The lightweight network uses a designed attention learning loss function to learn a series of channel features with weights online with no complex parameters. Compared with the pre-trained features, the channel features with weights can represent the target more accurately. Finally, the lightweight target-aware attention learning network is unified into a Siamese tracking network framework to implement target tracking effectively. Experiments on several datasets demonstrate that the tracker proposed in this paper has good performance.

Multiple Traffic Target Tracking with Spatial-Temporal Affinity Network

Traffic target tracking is a core task in intelligent transportation system because it is useful for scene understanding and vehicle autonomous driving. Most state-of-the-art (SOTA) multiple object tracking (MOT) methods adopt a two-step procedure: object detection followed by data association. The object detection has made great progress with the development of deep learning. However, the data association still heavily depends on hand crafted constraints, such as appearance, shape, and motion, which need to be elaborately trained for a special object. In this study, a spatial-temporal encoder-decoder affinity network is proposed for multiple traffic targets tracking, aiming to utilize the power of deep learning to learn a robust spatial-temporal affinity feature of the detections and tracklets for data association. The proposed spatial-temporal affinity network contains a two-stage transformer encoder module to encode the features of the detections and the tracked targets at the image level and the tracklet level, aiming to capture the spatial correlation and temporal history information. Then, a spatial transformer decoder module is designed to compute the association affinity, where the results from the two-stage transformer encoder module are fed back to fully capture and encode the spatial and temporal information from the detections and the tracklets of the tracked targets. Thus, efficient affinity computation can be applied to perform data association in online tracking. To validate the effectiveness of the proposed method, three popular multiple traffic target tracking datasets, KITTI, UA-DETRAC, and VisDrone, are used for evaluation. On the KITTI dataset, the proposed method is compared with 15 SOTA methods and achieves 86.9% multiple object tracking accuracy (MOTA) and 85.71% multiple object tracking precision (MOTP). On the UA-DETRAC dataset, 12 SOTA methods are used to compare with the proposed method, and the proposed method achieves 20.82% MOTA and 35.65% MOTP, respectively. On the VisDrone dataset, the proposed method is compared with 10 SOTA trackers and achieves 40.5% MOTA and 74.1% MOTP, respectively. All those experimental results show that the proposed method is competitive to the state-of-the-art methods by obtaining superior tracking performance.

Technical Diagnosis on Elite Female Discus Athletes Based on Grey Relational Analysis

The personalized training of elite athletes is the key to the breakthrough of Chinese track and field events in the Tokyo Olympic Games. The brilliance of Chinese women's throwing benefits from the closed-loop personalized training system. Training starts from the construction of accurate personalized technology and physical fitness model. This paper introduces the concept of champion model and puts forward a targeted technical training system based on the differentiation research of champion model. This paper mainly studies and analyzes some important technical parameters and achievements of elite female discus athletes aged 2018∼2021 by using the methods of Pearson, partial correlation and grey correlation analysis. We select from several technical parameters with significant differences, choose from several technical parameters that have significant difference, and calculate the correlation parameters and results. The results show that the influence degree of these technical parameters is as follows: torso angle of right foot touching the ground, discus release angle, discus release speed, shoulder and arm passing angle of left foot off the ground, discus moving distance of double support, center of mass moving distance of double support, and time of the second single support stage. This is different from our view that the hand speed is the most important, so the training of elite athletes should be more refined and specialized to promote the improvement of their performance. Through the application of technical diagnosis model in Chen Yang in a period of time, Chen Yang got her best result (65.14 m) in Chongqing Athletics Championship, which verified the success of the technical diagnosis model and application in this study.

Fast Tracking Algorithm Based on Spatial Regularization Correlation Filter

To solve the problem of the redundant number of training samples in a correlation filter-based tracking algorithm, the training samples were implicitly extended by circular shifts of the given target patches, and all the extended samples were used as negative samples for the fast online learning of the filter. Since all these shifted patches were not true negative samples of the target, the tracking process suffered from boundary effects, especially in challenging situations such as occlusion and background clutter, which can significantly impair the tracking performance of the tracker. Spatial regularization in the SRDCF tracking algorithm is an effective way to mitigate boundary effects, but it comes at the cost of highly increased time complexity, resulting in a very slow tracking speed of the SRDCF algorithm that cannot achieve a real-time tracking effect. To address this issue, we proposed a fast-tracking algorithm based on spatially regularized correlation filters that efficiently optimized the solved filters by replacing the Gauss–Seidel method in the SRDCF algorithm with the alternating direction multiplier method. The problem of slow speed in the SRDCF tracking algorithm improved, and the improved FSRCF algorithm achieved real-time tracking. An adaptive update mechanism was proposed by using the feedback from the high confidence tracking results to avoid model corruption. That is, a robust confidence evaluation criterion was introduced in the model update phase, which combined the maximum response criterion and the average peak correlation energy APCE criterion to determine whether to update the filter, thereby avoiding filter model drift and improving the target tracking accuracy and speed. We conducted extensive experiments on datasets OTB-2015, OTB-2013, UAV123, and TC128, and the experimental results show that the proposed algorithm exhibits a more stable and accurate tracking performance in the presence of occlusion and background clutter during tracking.

Real-Time Ship Tracking under Challenges of Scale Variation and Different Visibility Weather Conditions

Visual ship tracking provides crucial kinematic traffic information to maritime traffic participants, which helps to accurately predict ship traveling behaviors in the near future. Traditional ship tracking models obtain a satisfactory performance by exploiting distinct features from maritime images, which may fail when the ship scale varies in image sequences. Moreover, previous frameworks have not paid much attention to weather condition interferences (e.g., visibility). To address this challenge, we propose a scale-adaptive ship tracking framework with the help of a kernelized correlation filter (KCF) and a log-polar transformation operation. First, the proposed ship tracker employs a conventional KCF model to obtain the raw ship position in the current maritime image. Second, both the previous step output and ship training sample are transformed into a log-polar coordinate system, which are further processed with the correlation filter to determine ship scale factor and to suppress the negative influence of the weather conditions. We verify the proposed ship tracker performance on three typical maritime scenarios under typical navigational weather conditions (i.e., sunny, fog). The findings of the study can help traffic participants efficiently obtain maritime situation awareness information from maritime videos, in real time, under different visibility weather conditions.