Handcrafted and Deep Trackers

Abstract

In recent years, visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year. It is because tracking has wide applications in various real-world problems such as human-computer interaction, autonomous vehicles, robotics, surveillance, and security just to name a few. In the current study, we review latest trends and advances in the tracking area and evaluate the robustness of different trackers based on the feature extraction methods. The first part of this work includes a comprehensive survey of the recently proposed trackers. We broadly categorize trackers into Correlation Filter based Trackers (CFTs) and Non-CFTs. Each category is further classified into various types based on the architecture and the tracking mechanism. In the second part of this work, we experimentally evaluated 24 recent trackers for robustness and compared handcrafted and deep feature based trackers. We observe that trackers using deep features performed better, though in some cases a fusion of both increased performance significantly. To overcome the drawbacks of the existing benchmarks, a new benchmark Object Tracking and Temple Color (OTTC) has also been proposed and used in the evaluation of different algorithms. We analyze the performance of trackers over 11 different challenges in OTTC and 3 other benchmarks. Our study concludes that Discriminative Correlation Filter (DCF) based trackers perform better than the others. Our study also reveals that inclusion of different types of regularizations over DCF often results in boosted tracking performance. Finally, we sum up our study by pointing out some insights and indicating future trends in the visual object tracking field.

Adaptive Aggregation of Arbitrary Online Trackers with a Regret Bound

“…Roughly speaking, this trick uses a tentative value Z instead of T + D. Thus, the parameter η is initially set as η = ln N/Z. Then, if the actual value of T + D reaches Z at the current frame t, 4 the value of Z is doubled and η is updated using the new value of Z.…”

Global Motion-Aware Robust Visual Object Tracking for Electro Optical Targeting Systems

“…Recently, visual tracking received much attention from researchers, resulting in significant improvements of the tracking algorithms. These improvements are reflected in the large number of tracking benchmarks [1][2][3][4][5][6][7]. The subfield of visual tracking focuses on thermal infrared (TIR) tracking, which is less developed than the RGB based short term tracking.…”

Benchmarking Deep Trackers on Aerial Videos

“…Several review papers exist in the literature that overview visual object tracking research [9,10,56,57]. Li et al [56] studied deep learning trackers based on network architecture, network training, and network function and ran experiments on OTB100, TC-128 [46], and VOT2015 [41] to compare different deep learning based trackers.…”

“…Li et al [56] studied deep learning trackers based on network architecture, network training, and network function and ran experiments on OTB100, TC-128 [46], and VOT2015 [41] to compare different deep learning based trackers. Fiaz et al [57] performed an extensive review that compared various trackers based on different feature extraction methods. Trackers based on both deep learning and hand crafted features were evaluated on benchmarks, such as OTB 2015, OTB 2013 [38], TC-128, OTTC [57], and VOT 2017 [39].…”

“…Fiaz et al [57] performed an extensive review that compared various trackers based on different feature extraction methods. Trackers based on both deep learning and hand crafted features were evaluated on benchmarks, such as OTB 2015, OTB 2013 [38], TC-128, OTTC [57], and VOT 2017 [39]. VOT challenges compare many different trackers and provide a good overview of the performance of recent trackers.…”