Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning

About

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle tracking and camera control tasks separately, and the resulting system is difficult to tune jointly. These methods also require significant human efforts for image labeling and expensive trial-and-error system tuning in the real world. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning. A ConvNet-LSTM function approximator is adopted for the direct frame-to-action prediction. We further propose an environment augmentation technique and a customized reward function, which are crucial for successful training. The tracker trained in simulators (ViZDoom and Unreal Engine) demonstrates good generalization behaviors in the case of unseen object moving paths, unseen object appearances, unseen backgrounds, and distracting objects. The system is robust and can restore tracking after occasional lost of the target being tracked. We also find that the tracking ability, obtained solely from simulators, can potentially transfer to real-world scenarios. We demonstrate successful examples of such transfer, via experiments over the VOT dataset and the deployment of a real-world robot using the proposed active tracker trained in simulation.

Wenhan Luo, Peng Sun, Fangwei Zhong, Wei Liu, Tong Zhang, Yizhou Wang• 2018

Related benchmarks

TaskDatasetResultRank
Visual Active TrackingUnrealCV Parking Lot scene
EL237
21
Embodied Visual TrackingSimpleRoom Unseen Virtual Environment
EL500
16
Embodied Visual TrackingUrbanCity Unseen Virtual Environment
EL471
16
Visual Active TrackingUnrealCV UrbanRoad scene
EL378
11
Visual Active TrackingUnrealCV Snow Village scene
EL318
11
Visual Active TrackingUnrealCV
EL394
11
Visual Active TrackingUnrealCV UrbanCity 4D
EL221
10
Visual Active TrackingUnrealCV ComplexRoom 4D
EL263
10
Visual Active TrackingUnrealCV Average - Distractor Environments
EL240
10
Visual Active TrackingDAT citystreet
CR49
4
Showing 10 of 15 rows

Other info

Follow for update