Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network

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.

Cited by in corpus (24)

• Pyramid Feature Attention Network for Saliency detection
• DFNet: Discriminative feature extraction and integration network for salient object detection
• Target-Aware Deep Tracking
• Accurate RGB-D Salient Object Detection via Collaborative Learning
• Global Context-Aware Progressive Aggregation Network for Salient Object Detection
• Deep Reasoning with Multi-Scale Context for Salient Object Detection
• Siamese Keypoint Prediction Network for Visual Object Tracking
• A Review of Visual Trackers and Analysis of its Application to Mobile Robot
• Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters
• Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
• Centralized Information Interaction for Salient Object Detection
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• Autonomous Social Distancing in Urban Environments using a Quadruped Robot
• OGNet: Salient Object Detection with Output-guided Attention Module
• CLASS: Cross-Level Attention and Supervision for Salient Objects Detection
• Is Depth Really Necessary for Salient Object Detection?
• Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network
• Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
• Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining
• Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach