Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends

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 comprises 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, 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. In order 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 eleven different challenges in OTTC, and three 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 visual object tracking field.

arXiv comment27pages, 26 figures. arXiv admin note: substantial text overlap with arXiv:1802.03098

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Computing the Stereo Matching Cost with a Convolutional Neural Network
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
• DCFNet: Discriminant Correlation Filters Network for Visual Tracking
• Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
• Dual Deep Network for Visual Tracking
• Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Large Margin Object Tracking with Circulant Feature Maps
• Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking
• Dual coordinate solvers for large-scale structural SVMs
• Real-time visual tracking by deep reinforced decision making
• Globally Optimal Object Tracking with Fully Convolutional Networks