Perceiving Temporal Environment for Correlation Filters in Real-Time UAV Tracking

Discriminative correlation filter (DCF)-based methods applied for UAV object tracking have received widespread attention due to their high efficiency. However, these methods are usually troubled by the boundary effect. Besides, the violent environment variations severely confuse trackers that neglect temporal environmental changes among consecutive frames, leading to unwanted tracking drift. In this letter, we propose a novel DCF-based tracking method to promote the insensitivity of the tracker under uncertain environmental changes. Specifically, a regularization term is proposed to learn the environment residual between two adjacent frames, which can enhance the discrimination and insensitivity of the filter in fickle tracking scenarios. Further, we design an efficient strategy to acquire the environment information based on the current observation without additional computation. Exhausted experiments are conducted on two well-known UAV benchmarks, i.e. , UAV123_10fps and DTB70. Results verify that the proposed tracker has comparable performance with other 22 state-of-the-art trackers while running at ∼ 53 FPS on a low-cost CPU.

As One of the most vital members in the visual system of the unmanned aerial vehicle (UAV), visual tracking has attracted increasing research interest [1]–[2][3] in recent years. Its task is to estimate the target position in subsequent videos under the condition that the ground truth in the first frame is known. Discriminative correlation filter (DCF)-based trackers [1]–[2][3][4][5][6][7], especially with handcrafted features [3]–[4][5][6], have been active in UAV tracking community on account of their high efficiency on a single CPU. However, UAV-specific issues, e.g., fast object motion, camera viewpoint change, and limited resources, require the tracker to possess high performance as well as low energy loss.