Visual tracking via dynamic saliency discriminative correlation filter

SiamOT: An Improved Siamese Network with Online Training for Visual Tracking

As a prevailing solution for visual tracking, Siamese networks manifest high performance via convolution neural networks and weight-sharing schemes. Most existing Siamese networks have adopted various offline training strategies to realize precise tracking by comparing the extracted target features with template features. However, their performances may degrade when dealing with unknown targets. The tracker is unable to learn background information through offline training, and it is susceptible to background interference, which finally leads to tracking failure. In this paper, we propose a twin-branch architecture (dubbed SiamOT) to mitigate the above problem in existing Siamese networks, wherein one branch is a classical Siamese network, and the other branch is an online training branch. Especially, the proposed online branch utilizes feature fusion and attention mechanism, which is able to capture and update both the target and the background information so as to refine the description of the target. Extensive experiments have been carried out on three mainstream benchmarks, along with an ablation study, to validate the effectiveness of SiamOT. It turns out that SiamOT achieves superior performance with stronger target discrimination abilities.

A practical evaluation of correlation filter-based object trackers with new features

Visual object tracking is a critical problem in the field of computer vision. The visual object tracker methods can be divided into Correlation Filters (CF) and non-correlation filters trackers. The main advantage of CF-based trackers is that they have an accepted real-time tracking response. In this article, we will focus on CF-based trackers, due to their key role in online applications such as an Unmanned Aerial Vehicle (UAV), through two contributions. In the first contribution, we proposed a set of new video sequences to address two uncovered issues of the existing standard datasets. The first issue is to create two video sequence that is difficult to be tracked by a human being for the movement of the Amoeba under the microscope; these two proposed video sequences include a new feature that combined background clutter and occlusion features in a unique way; we called it hard-to-follow-by-human. The second issue is to increase the difficulty of the existing sequences by increasing the displacement of the tracked object. Then, we proposed a thorough, practical evaluation of eight CF-base trackers, with the top performance, on the existing sequence features such as out-of-view, background clutters, and fast motion. The evaluation utilized the well-known OTB-2013 dataset as well as the proposed video sequences. The overall assessment of the eight trackers on the standard evaluation metrics, e.g., precision and success rates, revealed that the Large Displacement Estimation of Similarity transformation (LDES) tracker is the best CF-based tracker among the trackers of comparison. On the contrary, with a deeper analysis, the results of the proposed video sequences show an average performance of the LDES tracker among the other trackers. The eight trackers failed to capture the moving objects in every frame of the proposed Amoeba movement video sequences while the same trackers managed to capture the object in almost every frame of the sequences of the standard dataset. These results outline the need to improve the CF-based object trackers to be able to process sequences with the proposed feature (i.e., hard-to-follow-by-human).