Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network

TL;DR

This paper introduces an online visual tracking method that leverages CNN-derived features and saliency maps to improve target localization and segmentation, demonstrating superior performance on challenging benchmarks.

Contribution

The paper presents a novel online tracking algorithm that constructs target-specific saliency maps guided by CNN features and an online SVM, enhancing localization accuracy and segmentation.

Findings

Outperforms state-of-the-art tracking algorithms on benchmark datasets.

Enables pixel-level target segmentation through saliency map visualization.

Improves target localization accuracy in challenging scenarios.

Abstract

We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Given a CNN pre-trained on a large-scale image repository in offline, our algorithm takes outputs from hidden layers of the network as feature descriptors since they show excellent representation performance in various general visual recognition problems. The features are used to learn discriminative target appearance models using an online Support Vector Machine (SVM). In addition, we construct target-specific saliency map by backpropagating CNN features with guidance of the SVM, and obtain the final tracking result in each frame based on the appearance model generatively constructed with the saliency map. Since the saliency map visualizes spatial configuration of target effectively, it improves target localization accuracy and enable us to achieve pixel-level target segmentation. We verify the effectiveness of our tracking algorithm through extensive experiment on a challenging benchmark, where our method illustrates outstanding performance compared to the state-of-the-art tracking algorithms.