Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier

Touil, Djamel Eddine; Terki, Nadjiba; Medouakh, Saadia

doi:10.1007/s11760-018-1364-z

Cited by 12 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most well-known generative deep trackers are correlation filter (CF)-based networks and Siamese neural networks. In [14], the authors applied trained correlation filters in each convolutional layer in a CNN to encode the appearances of the tracked object. They then used the maximum response in each layer to locate an object.…”

Section: Deep Visual Trackingmentioning

confidence: 99%

Robust visual tracking using very deep generative model

AlBasiouny

Attia²,

Abdelmunim³

et al. 2023

J Big Data

View full text Add to dashboard Cite

Deep learning algorithms provide visual tracking robustness at an unprecedented level, but realizing an acceptable performance is still challenging because of the natural continuous changes in the features of foreground and background objects over videos. One of the factors that most affects the robustness of tracking algorithms is the choice of network architecture parameters, especially the depth. A robust visual tracking model using a very deep generator (RTDG) was proposed in this study. We constructed our model on an ordinary convolutional neural network (CNN), which consists of feature extraction and binary classifier networks. We integrated a generative adversarial network (GAN) into the CNN to enhance the tracking results through an adversarial learning process performed during the training phase. We used the discriminator as a classifier and the generator as a store that produces unlabeled feature-level data with different appearances by applying masks to the extracted features. In this study, we investigated the role of increasing the number of fully connected (FC) layers in adversarial generative networks and their impact on robustness. We used a very deep FC network with 22 layers as a high-performance generator for the first time. This generator is used via adversarial learning to augment the positive samples to reduce the gap between the hungry deep learning algorithm and the available training data to achieve robust visual tracking. The experiments showed that the proposed framework performed well against state-of-the-art trackers on OTB-100, VOT2019, LaSOT and UAVDT benchmark datasets.

show abstract

Section: Deep Visual Trackingmentioning

confidence: 99%

Robust visual tracking using very deep generative model

AlBasiouny

Attia²,

Abdelmunim³

et al. 2023

J Big Data

View full text Add to dashboard Cite

show abstract

“…From the traditional index analysis method, to the use of statistical methods for stock selection, and then to the current artificial intelligence method represented by machine learning, stock selection has undergone great changes. Machine learning is currently used in many fields, including computer vision [2,3], image processing [4], natural language processing [5][6][7], speech recognition [8,9], etc. In the field of stock selection, machine learning methods are used widely.…”

Section: Introductionmentioning

confidence: 99%

A Stock Selection Model of Image Classification Method Based on Convolutional Neural Network

Jin

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of artificial intelligence technology, an increasing number of researchers try to apply different machine learning and deep learning methods to quantitative trading fields to obtain more stable and efficient trading models. As a typical quantitative trading strategy, stock selection has also attracted a lot of attention. There are many studies and applications on stock selection. However, the existing research and application cannot meet the continuous expansion of the scale and dimension of stock selection data set and cannot meet the needs in terms of efficiency and accuracy of stock selection. A convolutional neural network has been applied to image classification and achieved better results than the traditional methods. In this study, we first constructed a multifactor stock selection data set based on China’s stock market. Then, we apply the convolutional neural network model to analyze stock selection data and select stocks. The main contribution of this study is that we build a stock multifactor data set, construct a “factor picture,” and classify them by convolutional neural network to select stocks. This study also makes comparative experiments on the decision tree, support vector machine, and feedforward neural network in stock selection on the same data set constructed in this study. The results show that the stock selection method based on the convolutional neural network outperforms other methods in terms of the annual return, sharp ratio, and max drawdown.

show abstract

“…Furthermore, it has been found that it cannot be effective for long time tracking and it cannot ensure the detection of the target position failures. In the same time, it has faced a major problem against changes of illumination within specific color sequences [13]. Authors in [14] proposed an efficient hybrid image fusion method based on the Integer Lifting Wavelet Transform (ILWT) and the Discrete Cosine Transform (DCT) to generate fused images with high visual quality which can be used to reduce some visual tracking problems.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Visual Object Tracking Approach based on Combined Features of Neural Networks, Wavelet Transforms, and Histogram of Oriented Gradients

Bourennane

Terki

Hamiane

et al. 2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

In this paper, a new Visual Object Tracking (VOT) approach is proposed to overcome the main problem the existing approaches encounter, i.e. the significant appearance changes which are mainly caused by heavy occlusion and illumination variation. The proposed approach is based on a combination of Deep Convolutional Neural Networks (DCNNs), Histogram of Oriented Gradient (HOG) features, and discrete wavelet packet transforms. The problem of illumination variation is solved by incorporating the coefficients of the image discrete wavelet packet transform instead of the image template to handle the case of images with high saturation in the input of the used CNN, whereas the inverse discrete wavelet packet transforms are used at the output for extracting the CNN features. By combining four learned correlation filters with the convolutional features, the target location is deduced using multichannel correlation maps at the CNN output. On the other side, the maximum value of the resulting maps from the correlation filters with convolutional features produced by the previously obtained HOG feature of the image template are calculated and are used as an updating parameter of the correlation filters extracted from CNN and from HOG. The major aim is to ensure long-term memory of the target appearance so that the target item may be recovered if tracking fails. In order to increase the performance of HOG, the coefficients of the discrete packet wavelet transform are employed instead of the image template. The obtained results demonstrate the superiority of the proposed approach.

show abstract

Hierarchical convolutional features for visual tracking via two combined color spaces with SVM classifier

Cited by 12 publications

References 41 publications

Robust visual tracking using very deep generative model

Robust visual tracking using very deep generative model

A Stock Selection Model of Image Classification Method Based on Convolutional Neural Network

An Enhanced Visual Object Tracking Approach based on Combined Features of Neural Networks, Wavelet Transforms, and Histogram of Oriented Gradients

Contact Info

Product

Resources

About