Proceedings ArticleDOI
Deep GoogLeNet Features for Visual Object Tracking
P. Aswathy,Siddhartha,Deepak Mishra +2 more
- pp 60-66
Reads0
Chats0
TLDR
This study demonstrates for the first time, the viability of features extracted from deep layers of GoogLeNet CNN architecture for the purpose of object tracking, and integrated Goog LeNet features in a discriminative correlation filter based tracking framework.Abstract:
Convolutional Neural Network (CNN) has recently become very popular in visual object tracking due to their strong feature representation capabilities. Almost all of the CNN based trackers currently use the features extracted from shallow convolutional layers of VGGNet architecture. This paper presents an investigation of the impact of deep convolutional layer features in an object tracking framework. In this study, we demonstrate for the first time, the viability of features extracted from deep layers of GoogLeNet CNN architecture for the purpose of object tracking. We integrated GoogLeNet features in a discriminative correlation filter based tracking framework. Our experimental results show that the GoogLeNet features provides significant computational advantages over the conventionally used VGGNet features, without much compromise on the tracking performance. It was observed that features obtained from inception modules of GoogLeNet have high depths. Further, Principal Component Analysis (PCA) was employed to reduce the dimensionality of the extracted features. This greatly reduces the computational cost and thus improve the speed of the tracking process. Extensive evaluation have been performed on three benchmark datasets: OTB, ALOV300++ and VOT2016 datasets and its performances are measured in terms of metrics like F-score, One Pass Evaluation, robustness and accuracy.read more
Citations
More filters
Proceedings ArticleDOI
Epithelial Tissue Classification using Pre-Trained Deep Convolutional Neural Networks
Aman Jain,R. Tiwari +1 more
TL;DR: In this article , the authors used transfer learning to categorize several Epithelial tissues (e.g., nervous tissues, blood, etc.), each of which is made up of cells that have a common ancestry, a comparable cellular structure, and a shared function.
Driving Behavior Recognition using Multiple Deep Learning Models
Muhammad Hafizin Zarif Mohd Fodli,Fadhlan Hafizhelmi Kamaru Zaman,N. K. Mun,Lucyantie Mazalan +3 more
TL;DR: The results of this investigation show that MobileNetV2 outperforms other models, presenting a good balance between accuracy and processing runtime for real-world deployment.
Journal ArticleDOI
Multi-class Classification Approach for Retinal Diseases
TL;DR: In this paper , a CNN with different architectures (Scratch model, GoogleNet, VGG, ResNet, MobileNet and DenseNet) was created to make a comparison between them and find the one with the best percentage of accuracy and less loss to generate the model for better automatic classification of images using a MURED database containing retinal images already labeled previously with their respective disease.
Proceedings ArticleDOI
Epithelial Tissue Classification using Pre-Trained Deep Convolutional Neural Networks
TL;DR: In this article , the authors used transfer learning to categorize several Epithelial tissues (e.g., nervous tissues, blood, etc.), each of which is made up of cells that have a common ancestry, a comparable cellular structure, and a shared function.
Journal ArticleDOI
Brain Tumor Classification Using Hybrid Single Image Super-Resolution Technique With ResNext101_32× 8d and VGG19 Pre-Trained Models
TL;DR: In this paper , two pre-trained deep learning models, ResNext101_ and VGG19, were proposed to classify two types of brain tumor: pituitary and glioma.
References
More filters
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Journal ArticleDOI
Object tracking: A survey
TL;DR: The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends to discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
Journal ArticleDOI
High-Speed Tracking with Kernelized Correlation Filters
TL;DR: A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.