scholarly journals Object tracking framework with Siamese network and re-detection mechanism

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Daqun Li ◽  
Yi Yu ◽  
Xiaolin Chen
Keyword(s):  
Object Tracking ◽  
Objective Evaluation ◽  
Tracking Accuracy ◽  
Detection Mechanism ◽  
Siamese Network ◽  
Tracking Ability ◽  
Background Clutter ◽  
Instance Search ◽  
Template Updating ◽  
Siamese Networks

AbstractTo improve the deficient tracking ability of fully-convolutional Siamese networks (SiamFC) in complex scenes, an object tracking framework with Siamese network and re-detection mechanism (Siam-RM) is proposed. The mechanism adopts the Siamese instance search tracker (SINT) as the re-detection network. When multiple peaks appear on the response map of SiamFC, a more accurate re-detection network can re-determine the location of the object. Meanwhile, for the sake of adapting to various changes in appearance of the object, this paper employs a generative model to construct the templates of SiamFC. Furthermore, a method of template updating with high confidence is also used to prevent the template from being contaminated. Objective evaluation on the popular online tracking benchmark (OTB) shows that the tracking accuracy and the success rate of the proposed framework can reach 79.8% and 63.8%, respectively. Compared to SiamFC, the results of several representative video sequences demonstrate that our framework has higher accuracy and robustness in scenes with fast motion, occlusion, background clutter, and illumination variations.

scholarly journals A Learning Frequency-Aware Feature Siamese Network for Real-Time Visual Tracking

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 854
Author(s):  
Yuxiang Yang ◽  
Weiwei Xing ◽  
Shunli Zhang ◽  
Qi Yu ◽  
Xiaoyu Guo ◽  
...  
Keyword(s):  
Object Tracking ◽  
Low Frequency ◽  
Linear Representation ◽  
Visual Object ◽  
Tracking Accuracy ◽  
Discriminative Ability ◽  
Visual Object Tracking ◽  
Training Samples ◽  
Complex Scenes ◽  
Siamese Networks

Visual object tracking by Siamese networks has achieved favorable performance in accuracy and speed. However, the features used in Siamese networks have spatially redundant information, which increases computation and limits the discriminative ability of Siamese networks. Addressing this issue, we present a novel frequency-aware feature (FAF) method for robust visual object tracking in complex scenes. Unlike previous works, which select features from different channels or layers, the proposed method factorizes the feature map into multi-frequency and reduces the low-frequency information that is spatially redundant. By reducing the low-frequency map’s resolution, the computation is saved and the receptive field of the layer is also increased to obtain more discriminative information. To further improve the performance of the FAF, we design an innovative data-independent augmentation for object tracking to improve the discriminative ability of tracker, which enhanced linear representation among training samples by convex combinations of the images and tags. Finally, a joint judgment strategy is proposed to adjust the bounding box result that combines intersection-over-union (IoU) and classification scores to improve tracking accuracy. Extensive experiments on 5 challenging benchmarks demonstrate that our FAF method performs favorably against SOTA tracking methods while running around 45 frames per second.

scholarly journals Object Tracking in Hyperspectral-Oriented Video with Fast Spatial-Spectral Features

2021 ◽  
Vol 13 (10) ◽  
pp. 1922
Author(s):  
Lulu Chen ◽  
Yongqiang Zhao ◽  
Jiaxin Yao ◽  
Jiaxin Chen ◽  
Ning Li ◽  
...  
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Spatial Information ◽  
Video Tracking ◽  
Spectral Features ◽  
Surveillance Video ◽  
Tracking Accuracy ◽  
Low Resolution ◽  
Background Clutter ◽  
Appearance Changes

This paper presents a correlation filter object tracker based on fast spatial-spectral features (FSSF) to realize robust, real-time object tracking in hyperspectral surveillance video. Traditional object tracking in surveillance video based only on appearance information often fails in the presence of background clutter, low resolution, and appearance changes. Hyperspectral imaging uses unique spectral properties as well as spatial information to improve tracking accuracy in such challenging environments. However, the high-dimensionality of hyperspectral images causes high computational costs and difficulties for discriminative feature extraction. In FSSF, the real-time spatial-spectral convolution (RSSC) kernel is updated in real time in the Fourier transform domain without offline training to quickly extract discriminative spatial-spectral features. The spatial-spectral features are integrated into correlation filters to complete the hyperspectral tracking. To validate the proposed scheme, we collected a hyperspectral surveillance video (HSSV) dataset consisting of 70 sequences in 25 bands. Extensive experiments confirm the advantages and the efficiency of the proposed FSSF for object tracking in hyperspectral video tracking in challenging conditions of background clutter, low resolution, and appearance changes.

scholarly journals SNS-CF: Siamese Network with Spatially Semantic Correlation Features for Object Tracking

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4881
Author(s):  
Thierry Ntwari ◽  
Hasil Park ◽  
Joongchol Shin ◽  
Joonki Paik
Keyword(s):  
Object Tracking ◽  
State Of The Art ◽  
Input Image ◽  
Frame Rate ◽  
Correlation Filter ◽  
Correlation Filters ◽  
Semantic Correlation ◽  
Siamese Network ◽  
Feature Extractor ◽  
Siamese Networks

Recent advances in object tracking based on deep Siamese networks shifted the attention away from correlation filters. However, the Siamese network alone does not have as high accuracy as state-of-the-art correlation filter-based trackers, whereas correlation filter-based trackers alone have a frame update problem. In this paper, we present a Siamese network with spatially semantic correlation features (SNS-CF) for accurate, robust object tracking. To deal with various types of features spread in many regions of the input image frame, the proposed SNS-CF consists of—(1) a Siamese feature extractor, (2) a spatially semantic feature extractor, and (3) an adaptive correlation filter. To the best of authors knowledge, the proposed SNS-CF is the first attempt to fuse the Siamese network and the correlation filter to provide high frame rate, real-time visual tracking with a favorable tracking performance to the state-of-the-art methods in multiple benchmarks.

scholarly journals A Deep Hyper Siamese Network for Real-Time Object Tracking

2020 ◽  
Vol 8 (1) ◽  
pp. 35-46
Author(s):  
Yongpeng Zhao ◽  
Lasheng Yu ◽  
Xiaopeng Zheng
Keyword(s):  
Object Tracking ◽  
Target Object ◽  
Visual Object ◽  
Feature Maps ◽  
Deep Convolutional Neural Networks ◽  
Backbone Networks ◽  
Feature Representations ◽  
Siamese Network ◽  
Benchmark Datasets ◽  
Siamese Networks

Siamese networks have drawn increasing interest in the field of visual object tracking due to their balance of precision and efficiency. However, Siamese trackers use relatively shallow backbone networks, such as AlexNet, and therefore do not take full advantage of the capabilities of modern deep convolutional neural networks (CNNs). Moreover, the feature representations of the target object in a Siamese tracker are extracted through the last layer of CNNs and mainly capture semantic information, which causes the tracker's precision to be relatively low and to drift easily in the presence of similar distractors. In this paper, a new nonpadding residual unit (NPRU) is designed and used to stack a 22-layer deep ResNet, referred as ResNet22. After utilizing ResNet22 as the backbone network, we can build a deep Siamese network, which can greatly enhance the tracking performance. Considering that the different levels of the feature maps of the CNN represent different aspects of the target object, we aggregated different deep convolutional layers to make use of ResNet22's multilevel feature maps, which can form hyperfeature representations of targets. The designed deep hyper Siamese network is named DHSiam. Experimental results show that DHSiam has achieved significant improvement on multiple benchmark datasets.

scholarly journals Attention Modulated Multiple Object Tracking with Motion Enhancement and Dual Correlation

Symmetry ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 266 ◽  
Author(s):  
Yifeng Wang ◽  
Zhijiang Zhang ◽  
Ning Zhang ◽  
Dan Zeng
Keyword(s):  
Object Tracking ◽  
Multiple Object Tracking ◽  
Tracking Accuracy ◽  
Feature Maps ◽  
Backbone Networks ◽  
Multiple Object ◽  
The Arts ◽  
Training Stage ◽  
The One ◽  
Baseline State

The one-shot multiple object tracking (MOT) framework has drawn more and more attention in the MOT research community due to its advantage in inference speed. However, the tracking accuracy of current one-shot approaches could lead to an inferior performance compared with their two-stage counterparts. The reasons are two-fold: one is that motion information is often neglected due to the single-image input. The other is that detection and re-identification (ReID) are two different tasks with different focuses. Joining detection and re-identification at the training stage could lead to a suboptimal performance. To alleviate the above limitations, we propose a one-shot network named Motion and Correlation-Multiple Object Tracking (MAC-MOT). MAC-MOT introduces a motion enhance attention module (MEA) and a dual correlation attention module (DCA). MEA performs differences on adjacent feature maps which enhances the motion-related features while suppressing irrelevant information. The DCA module focuses on decoupling the detection task and re-identification task to strike a balance and reduce the competition between these two tasks. Moreover, symmetry is a core design idea in our proposed framework which is reflected in Siamese-based deep learning backbone networks, the input of dual stream images, as well as a dual correlation attention module. Our proposed approach is evaluated on the popular multiple object tracking benchmarks MOT16 and MOT17. We demonstrate that the proposed MAC-MOT can achieve a better performance than the baseline state of the arts (SOTAs).

scholarly journals A Two-Stage Data Association Approach for 3D Multi-Object Tracking

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2894
Author(s):  
Minh-Quan Dao ◽  
Vincent Frémont
Keyword(s):  
Object Detection ◽  
Object Tracking ◽  
Moving Objects ◽  
Data Association ◽  
Autonomous Driving ◽  
Tracking Accuracy ◽  
Two Stage ◽  
Bipartite Matching ◽  
3D Object ◽  
3D Object Detection

Multi-Object Tracking (MOT) is an integral part of any autonomous driving pipelines because it produces trajectories of other moving objects in the scene and predicts their future motion. Thanks to the recent advances in 3D object detection enabled by deep learning, track-by-detection has become the dominant paradigm in 3D MOT. In this paradigm, a MOT system is essentially made of an object detector and a data association algorithm which establishes track-to-detection correspondence. While 3D object detection has been actively researched, association algorithms for 3D MOT has settled at bipartite matching formulated as a Linear Assignment Problem (LAP) and solved by the Hungarian algorithm. In this paper, we adapt a two-stage data association method which was successfully applied to image-based tracking to the 3D setting, thus providing an alternative for data association for 3D MOT. Our method outperforms the baseline using one-stage bipartite matching for data association by achieving 0.587 Average Multi-Object Tracking Accuracy (AMOTA) in NuScenes validation set and 0.365 AMOTA (at level 2) in Waymo test set.

scholarly journals An Anchor-Free Siamese Network with Multi-Template Update for Object Tracking

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1067
Author(s):  
Tongtong Yuan ◽  
Wenzhu Yang ◽  
Qian Li ◽  
Yuxia Wang
Keyword(s):  
Object Tracking ◽  
Correlation Energy ◽  
Feature Maps ◽  
Siamese Network ◽  
Template Update ◽  
Free Network ◽  
Multiple Prediction ◽  
Bounding Boxes ◽  
High Level ◽  
Speed And Accuracy

Siamese trackers are widely used in various fields for their advantages of balancing speed and accuracy. Compared with the anchor-based method, the anchor-free-based approach can reach faster speeds without any drop in precision. Inspired by the Siamese network and anchor-free idea, an anchor-free Siamese network (AFSN) with multi-template updates for object tracking is proposed. To improve tracking performance, a dual-fusion method is adopted in which the multi-layer features and multiple prediction results are combined respectively. The low-level feature maps are concatenated with the high-level feature maps to make full use of both spatial and semantic information. To make the results as stable as possible, the final results are obtained by combining multiple prediction results. Aiming at the template update, a high-confidence multi-template update mechanism is used. The average peak to correlation energy is used to determine whether the template should be updated. We use the anchor-free network to implement object tracking in a per-pixel manner, which computes the object category and bounding boxes directly. Experimental results indicate that the average overlap and success rate of the proposed algorithm increase by about 5% and 10%, respectively, compared to the SiamRPN++ algorithm when running on the dataset of GOT-10k (Generic Object Tracking Benchmark).

Sign in / Sign up

Export Citation Format

Share Document