SiamVGG: Visual Tracking using Deeper Siamese Networks

7 Feb 2019  ยท  Yuhong Li, Xiaofan Zhang, Deming Chen ยท

Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlation Filters (DCF) to extract semantic features and successfully deliver the state-of-the-art tracking accuracy. However, these solutions are highly compute-intensive, which require long processing time, resulting unsecured real-time performance. To deliver both high accuracy and reliable real-time performance, we propose a novel tracker called SiamVGG\footnote{https://github.com/leeyeehoo/SiamVGG}. It combines a Convolutional Neural Network (CNN) backbone and a cross-correlation operator, and takes advantage of the features from exemplary images for more accurate object tracking. The architecture of SiamVGG is customized from VGG-16 with the parameters shared by both exemplary images and desired input video frames. We demonstrate the proposed SiamVGG on OTB-2013/50/100 and VOT 2015/2016/2017 datasets with the state-of-the-art accuracy while maintaining a decent real-time performance of 50 FPS running on a GTX 1080Ti. Our design can achieve 2% higher Expected Average Overlap (EAO) compared to the ECO and C-COT in VOT2017 Challenge.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Object Tracking OTB-2013 SiamVGG AUC 0.665 # 4
Visual Object Tracking OTB-2015 SiamVGG AUC 0.654 # 11
Visual Object Tracking OTB-50 SiamVGG AUC 0.61 # 1
Visual Object Tracking VOT2016 SiamVGG Expected Average Overlap (EAO) 0.351 # 5
Visual Object Tracking VOT2017 SiamVGG Expected Average Overlap (EAO) 0.286 # 3

Methods