Deep Reinforcement Learning for Visual Object Tracking in Videos

Abstract

In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame. An important insight is that the tracking problem can be considered as a sequential decision-making process and historical semantics encode highly relevant information for future decisions. Based on this intuition, we formulate our model as a recurrent convolutional neural network agent that interacts with a video overtime, and our model can be trained with reinforcement learning (RL) algorithms to learn good tracking policies that pay attention to continuous, inter-frame correlation and maximize tracking performance in the long run. The proposed tracking algorithm achieves state-of-the-art performance in an existing tracking benchmark and operates at frame-rates faster than real-time. To the best of our knowledge, our tracker is the first neural-network tracker that combines convolutional and recurrent networks with RL algorithms.

References in corpus (18)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Playing Atari with Deep Reinforcement Learning
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• Recurrent Models of Visual Attention
• Fully Convolutional Networks for Semantic Segmentation
• Multiple Object Recognition with Visual Attention
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Transferring Rich Feature Hierarchies for Robust Visual Tracking
• Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
• Understanding and Diagnosing Visual Tracking Systems
• First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks
• On Learning Where To Look
• Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
• Robust Visual Tracking via Convolutional Networks

Cited by in corpus (18)

• Deep Learning for Visual Tracking: A Comprehensive Survey
• Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
• Learning Policies for Adaptive Tracking with Deep Feature Cascades
• S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
• Natural Environment Benchmarks for Reinforcement Learning
• Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
• iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Learning to Track Dynamic Targets in Partially Known Environments
• DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking
• Robust and customized methods for real-time hand gesture recognition under object-occlusion
• Deep Reinforcement Learning for Active Human Pose Estimation
• Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications
• Long and Short Memory Balancing in Visual Co-Tracking using Q-Learning
• Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
• Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning
• Real-time tracker with fast recovery from target loss
• Hide and Seek tracker: Real-time recovery from target loss