End-to-end Active Object Tracking via Reinforcement Learning
arXiv:1705.10561
Abstract
We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in realworld. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction prediction. We further propose an environment augmentation technique and a customized reward function, which are crucial for a successful training. The tracker trained in simulators (ViZDoom, Unreal Engine) shows good generalization in the case of unseen object moving path, unseen object appearance, unseen background, and distracting object. It can restore tracking when occasionally losing the target. With the experiments over the VOT dataset, we also find that the tracking ability, obtained solely from simulators, can potentially transfer to real-world scenarios.
To appear in ICML2018
Cited by in corpus (8)
- Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
- Perceptual Compressive Sensing
- C^3Net: End-to-End deep learning for efficient real-time visual active camera control
- Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
- Deep Attentive Tracking via Reciprocative Learning
- Imitation-Based Active Camera Control with Deep Convolutional Neural Network
- CRAVES: Controlling Robotic Arm with a Vision-based Economic System
- Pose-Assisted Multi-Camera Collaboration for Active Object Tracking