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.

References in corpus (3)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Cited by in corpus (51)

• Deep Learning for Visual Tracking: A Comprehensive Survey
• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection
• RGB-D Salient Object Detection: A Survey
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Bifurcated backbone strategy for RGB-D salient object detection
• TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network
• CAGNet: Content-Aware Guidance for Salient Object Detection
• Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
• Dual Deep Network for Visual Tracking
• Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• Pyramid Feature Attention Network for Saliency detection
• Adaptive Siamese Tracking with a Compact Latent Network
• Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness
• DFNet: Discriminative feature extraction and integration network for salient object detection
• Parallel Tracking and Verifying
• Deformable Object Tracking with Gated Fusion
• Target-Aware Deep Tracking
• TRAT: Tracking by Attention Using Spatio-Temporal Features
• End-to-end Flow Correlation Tracking with Spatial-temporal Attention
• Selectivity or Invariance: Boundary-aware Salient Object Detection
• Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How
• 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
• Highly Efficient Salient Object Detection with 100K Parameters
• Siamese Keypoint Prediction Network for Visual Object Tracking
• Deep Convolutional Correlation Iterative Particle Filter for Visual 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
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres
• Centralized Information Interaction for Salient Object Detection
• A Structured Model For Action Detection
• OGNet: Salient Object Detection with Output-guided Attention Module
• Autonomous Social Distancing in Urban Environments using a Quadruped Robot
• Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation
• CLASS: Cross-Level Attention and Supervision for Salient Objects Detection
• Wide and Deep Graph Neural Networks with Distributed Online Learning
• Is Depth Really Necessary for Salient Object Detection?
• SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
• Distortion-adaptive Salient Object Detection in 360${}^{\circ }$ Omnidirectional Images
• Salient Object Detection with Purificatory Mechanism and Structural Similarity Loss
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
• Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
• Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
• Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network
• Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining