Learning Policies for Adaptive Tracking with Deep Feature Cascades

08/09/2017
by   Chen Huang, et al.
0

Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a high-end GPU. In this paper, we learn to improve the speed of deep trackers without losing accuracy. Our fundamental insight is to take an adaptive approach, where easy frames are processed with cheap features (such as pixel values), while challenging frames are processed with invariant but expensive deep features. We formulate the adaptive tracking problem as a decision-making process, and learn an agent to decide whether to locate objects with high confidence on an early layer, or continue processing subsequent layers of a network. This significantly reduces the feed-forward cost for easy frames with distinct or slow-moving objects. We train the agent offline in a reinforcement learning fashion, and further demonstrate that learning all deep layers (so as to provide good features for adaptive tracking) can lead to near real-time average tracking speed of 23 fps on a single CPU while achieving state-of-the-art performance. Perhaps most tellingly, our approach provides a 100X speedup for almost 50 approach.

READ FULL TEXT
research
01/03/2017

Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation

Visual tracking is a fundamental problem in computer vision. Recently, s...
research
07/17/2017

Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning

We formulate tracking as an online decision-making process, where a trac...
research
02/02/2019

Confidence Trigger Detection: An Approach to Build Real-time Tracking-by-detection System

With deep learning based image analysis getting popular in recent years,...
research
04/09/2018

Markerless tracking of user-defined features with deep learning

Quantifying behavior is crucial for many applications in neuroscience. V...
research
01/31/2017

Deep Reinforcement Learning for Visual Object Tracking in Videos

In this paper we introduce a fully end-to-end approach for visual tracki...
research
03/14/2017

Learning Background-Aware Correlation Filters for Visual Tracking

Correlation Filters (CFs) have recently demonstrated excellent performan...
research
08/07/2022

Robust Multi-Object Tracking by Marginal Inference

Multi-object tracking in videos requires to solve a fundamental problem ...

Please sign up or login with your details

Forgot password? Click here to reset