Regional deep learning model for visual tracking

Wu, Guoxing; Lu, Wenjie; Gao, Guangwei; Zhao, Chenglin; Liu, Jiayin

doi:10.1016/j.neucom.2015.10.064

Cited by 64 publications

(24 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the recent years, CNN-based feature extraction has made tracking alghorithms achieve significant improvements [22]. LeCun et al [23] proposed CNN, which is a model of neural networks, the aim of which is to learn features from image pixels directly.…”

Section: Cnnmentioning

confidence: 99%

Convolutional Gating Network for Object Tracking

Feizi

2019

IJE

View full text Add to dashboard Cite

A B S T R A C TObject tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. T his paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. T he weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the p article filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.

show abstract

Section: Cnnmentioning

confidence: 99%

Convolutional Gating Network for Object Tracking

Feizi

2019

IJE

View full text Add to dashboard Cite

show abstract

“…Furthermore, this method is susceptible to occlusion. Wu et al [21] proposed a regional deep learning tracker that observes the object by multiple subregions and each region is observed by a deep learning model. However, with the increase of tracked objects, it can cause a huge deep network; thus it is difficult to achieve efficient tracking.…”

Section: Previous Workmentioning

confidence: 99%

Tracking Algorithm of Multiple Pedestrians Based on Particle Filters in Video Sequences

Liu

Wang

et al. 2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Pedestrian tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in pedestrian tracking for nonlinear and non-Gaussian estimation problems. However, pedestrian tracking in complex environment is still facing many problems due to changes of pedestrian postures and scale, moving background, mutual occlusion, and presence of pedestrian. To surmount these difficulties, this paper presents tracking algorithm of multiple pedestrians based on particle filters in video sequences. The algorithm acquires confidence value of the object and the background through extracting a priori knowledge thus to achieve multipedestrian detection; it adopts color and texture features into particle filter to get better observation results and then automatically adjusts weight value of each feature according to current tracking environment. During the process of tracking, the algorithm processes severe occlusion condition to prevent drift and loss phenomena caused by object occlusion and associates detection results with particle state to propose discriminated method for object disappearance and emergence thus to achieve robust tracking of multiple pedestrians. Experimental verification and analysis in video sequences demonstrate that proposed algorithm improves the tracking performance and has better tracking results.

show abstract

“…Deep neural networks (DNNs) have progressed rapidly in recent years and have been applied successfully to many computational tasks, including speech recognition, natural language processing (NLP), information retrieval, computer vision, and image analysis [1][2][3][4][5][6][7]. In the fields of computer vision, the most relevant procedures of the winners follow three main avenues: extending the training data, building ensembles of learning machines, and constructing DNNs.…”

Section: Introductionmentioning

confidence: 99%

Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data

2019

KSII TIIS

View full text Add to dashboard Cite

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods. Hu et al.: Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data

show abstract

Regional deep learning model for visual tracking

Cited by 64 publications

References 28 publications

Convolutional Gating Network for Object Tracking

Convolutional Gating Network for Object Tracking

Tracking Algorithm of Multiple Pedestrians Based on Particle Filters in Video Sequences

Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data

Contact Info

Product

Resources

About