Learning Mobile CNN Feature Extraction Toward Fast Computation of Visual Object Tracking
This work addresses the challenge of fast visual object tracking for mobile or resource-constrained devices, representing an incremental improvement over existing methods.
The paper tackles the problem of applying CNN-based object tracking in low computation resource environments by using MobileNetV3 and a new architecture for feature extraction, achieving high-precision and high-speed tracking as confirmed on the Visual Tracker Benchmark.
In this paper, we construct a lightweight, high-precision and high-speed object tracking using a trained CNN. Conventional methods with trained CNNs use VGG16 network which requires powerful computational resources. Therefore, there is a problem that it is difficult to apply in low computation resources environments. To solve this problem, we use MobileNetV3, which is a CNN for mobile terminals.Based on Feature Map Selection Tracking, we propose a new architecture that extracts effective features of MobileNet for object tracking. The architecture requires no online learning but only offline learning. In addition, by using features of objects other than tracking target, the features of tracking target are extracted more efficiently. We measure the tracking accuracy with Visual Tracker Benchmark and confirm that the proposed method can perform high-precision and high-speed calculation even in low computation resource environments.