scholarly journals Multi-Stream Deep Similarity Learning Networks for Visual Tracking

2017 ◽  
Author(s):  
Kunpeng Li ◽  
Yu Kong ◽  
Yun Fu
Keyword(s):  
Visual Tracking ◽  
Model Updating ◽  
Feature Space ◽  
Fine Tuning ◽  
Similarity Learning ◽  
Learning Networks ◽  
Target Template ◽  
Background Clutter ◽  
Cluttered Background ◽  
Background Context

Visual tracking has achieved remarkable success in recent decades, but it remains a challenging problem due to appearance variations over time and complex cluttered background. In this paper, we adopt a tracking-by-verification scheme to overcome these challenges by determining the patch in the subsequent frame that is most similar to the target template and distinctive to the background context. A multi-stream deep similarity learning network is proposed to learn the similarity comparison model. The loss function of our network encourages the distance between a positive patch in the search region and the target template to be smaller than that between positive patch and the background patches. Within the learned feature space, even if the distance between positive patches becomes large caused by the appearance change or interference of background clutter, our method can use the relative distance to distinguish the target robustly. Besides, the learned model is directly used for tracking with no need of model updating, parameter fine-tuning and can run at 45 fps on a single GPU. Our tracker achieves state-of-the-art performance on the visual tracking benchmark compared with other recent real-time-speed trackers, and shows better capability in handling background clutter, occlusion and appearance change.

Efficient joint model learning, segmentation and model updating for visual tracking

2022 ◽  
Author(s):  
Wei Han ◽  
Chamara Kasun Liyanaarachchi Lekamalage ◽  
Guang-Bin Huang
Keyword(s):  
Visual Tracking ◽  
Model Updating ◽  
Joint Model ◽  
Model Learning

DBN Models for Visual Tracking and Prediction

2007 ◽  
pp. 176-193
Author(s):  
Qian Diao ◽  
Jianye Lu ◽  
Wei Hu ◽  
Yimin Zhang ◽  
Gary Bradski
Keyword(s):  
Visual Tracking ◽  
General Framework ◽  
Broad Class ◽  
Probability Distributions ◽  
Prediction Method ◽  
Dynamic Bayesian Networks ◽  
Time Series Models ◽  
Complex Environments ◽  
Inference Algorithms ◽  
Background Clutter

In a visual tracking task, the object may exhibit rich dynamic behavior in complex environments that can corrupt target observations via background clutter and occlusion. Such dynamics and background induce nonlinear, nonGaussian and multimodal observation densities. These densities are difficult to model with traditional methods such as Kalman filter models (KFMs) due to their Gaussian assumptions. Dynamic Bayesian networks (DBNs) provide a more general framework in which to solve these problems. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. Under the DBN umbrella, a broad class of learning and inference algorithms for time-series models can be used in visual tracking. Furthermore, DBNs provide a natural way to combine multiple vision cues. In this chapter, we describe some DBN models for tracking in nonlinear, nonGaussian and multimodal situations, and present a prediction method to assist feature extraction part by making a hypothesis for the new observations.

Effective template update mechanism in visual tracking with background clutter

2020 ◽  
Author(s):  
Shuai Liu ◽  
Dongye Liu ◽  
Khan Muhammad ◽  
Weiping Ding
Keyword(s):  
Visual Tracking ◽  
Template Update ◽  
Background Clutter

scholarly journals Adaptive Context-Aware and Structural Correlation Filter for Visual Tracking

2019 ◽  
Vol 9 (7) ◽  
pp. 1338 ◽  
Author(s):  
Bin Zhou ◽  
Tuo Wang
Keyword(s):  
Visual Tracking ◽  
High Performance ◽  
State Of The Art ◽  
Correlation Filter ◽  
Context Aware ◽  
Partial Occlusion ◽  
Structural Correlation ◽  
Background Clutter ◽  
Overall Performance ◽  
Fast Motion

Accurate visual tracking is a challenging issue in computer vision. Correlation filter (CF) based methods are sought in visual tracking based on their efficiency and high performance. Nonetheless, traditional CF-based trackers have insufficient context information, and easily drift in scenes of fast motion or background clutter. Moreover, CF-based trackers are sensitive to partial occlusion, which may reduce their overall performance and even lead to failure in tracking challenge. In this paper, we presented an adaptive context-aware (CA) and structural correlation filter for tracking. Firstly, we propose a novel context selecting strategy to obtain negative samples. Secondly, to gain robustness against partial occlusion, we construct a structural correlation filter by learning both the holistic and local models. Finally, we introduce an adaptive updating scheme by using a fluctuation parameter. Extensive comprehensive experiments on object tracking benchmark (OTB)-100 datasets demonstrate that our proposed tracker performs favorably against several state-of-the-art trackers.

scholarly journals HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 2137 ◽  
Author(s):  
Chenpu Li ◽  
Qianjian Xing ◽  
Zhenguo Ma
Keyword(s):  
Kalman Filter ◽  
Visual Tracking ◽  
Prior Information ◽  
State Of The Art ◽  
The Other ◽  
Robust Tracking ◽  
Similarity Learning ◽  
Complex Environments ◽  
Color Information ◽  
Learning Problem

In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.

Visual tracking based on semantic and similarity learning

2019 ◽  
Vol 13 (7) ◽  
pp. 623-631
Author(s):  
Yufei Zha ◽  
Min Wu ◽  
Zhuling Qiu ◽  
Wangsheng Yu
Keyword(s):  
Visual Tracking ◽  
Similarity Learning

Robust Inland Waterway Ship Tracking via Hybrid TLD and Kalman Filter

2014 ◽  
Vol 1037 ◽  
pp. 373-377 ◽  
Author(s):  
Teng Fei ◽  
Liu Qing ◽  
Lin Zhu ◽  
Jing Li
Keyword(s):  
Kalman Filter ◽  
Visual Tracking ◽  
State Of The Art ◽  
Experimental Results ◽  
Closed Circuit ◽  
Video Sequences ◽  
Inland Waterway ◽  
Cluttered Background ◽  
Full Occlusion

In this paper, we mainly address the problem of tracking a single ship in inland waterway CCTV (Closed-Circuit Television) video sequences. Although state-of-the-art performance has been demonstrated in TLD (Tracking-Learning-Detection) visual tracking, it is still challenging to perform long-term robust ship tracking due to factors such as cluttered background, scale change, partial or full occlusion and so forth. In this work, we focus on tracking a single ship when it suffers occlusion. To accomplish this goal, an effective Kalman filter is adopted to construct a novel online model to adapt to the rapid ship appearance change caused by occlusion. Experimental results on numerous inland waterway CCTV video sequences demonstrate that the proposed algorithm outperforms the original one.

Robust visual tracking via self‐similarity learning

2017 ◽  
Vol 53 (1) ◽  
pp. 20-22 ◽  
Author(s):  
Huihui Song ◽  
Yuhui Zheng ◽  
Kaihua Zhang
Keyword(s):  
Visual Tracking ◽  
Similarity Learning ◽  
Self Similarity

scholarly journals Multiclass Incremental Learning for Fault Diagnosis in Induction Motors Using Fine-Tuning with a Memory of Exemplars and Nearest Centroid Classifier

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Magdiel Jiménez-Guarneros ◽  
Jonas Grande-Barreto ◽  
Jose de Jesus Rangel-Magdaleno
Keyword(s):  
Fault Detection ◽  
Incremental Learning ◽  
Induction Motors ◽  
Asynchronous Motor ◽  
Feature Space ◽  
Fine Tuning ◽  
Electromechanical Systems ◽  
Critical Data ◽  
Public Datasets ◽  
Centroid Classifier

Early detection of fault events through electromechanical systems operation is one of the most attractive and critical data challenges in modern industry. Although these electromechanical systems tend to experiment with typical faults, a common event is that unexpected and unknown faults can be presented during operation. However, current models for automatic detection can learn new faults at the cost of forgetting concepts previously learned. This article presents a multiclass incremental learning (MCIL) framework based on 1D convolutional neural network (CNN) for fault detection in induction motors. The presented framework tackles the forgetting problem by storing a representative exemplar set from past data (known faults) in memory. Then, the 1D CNN is fine-tuned over the selected exemplar set and data from new faults. Test samples are classified using nearest centroid classifier (NCC) in the feature space from 1D CNN. The proposed framework was evaluated and validated over two public datasets for fault detection in induction motors (IMs): asynchronous motor common fault (AMCF) and Case Western Reserve University (CWRU). Experimental results reveal the proposed framework as an effective solution to incorporate and detect new induction motor faults to already known, with a high accuracy performance across different incremental phases.

Sign in / Sign up

Export Citation Format

Share Document