TY - JOUR
T1 - Visual Object Tracking with Discriminative Filters and Siamese Networks
T2 - A Survey and Outlook
AU - Javed, Sajid
AU - Danelljan, Martin
AU - Khan, Fahad Shahbaz
AU - Khan, Muhammad Haris
AU - Felsberg, Michael
AU - Matas, Jiri
N1 - Publisher Copyright:
IEEE
PY - 2022
Y1 - 2022
N2 - Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.
AB - Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image sequence, given only its initial location, and segmentation, or its rough approximation in the form of a bounding box. Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress. Following the rapid evolution of visual object tracking in the last decade, this survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks. First, we present the background theory of both the DCF and Siamese tracking core formulations. Then, we distinguish and comprehensively review the shared as well as specific open research challenges in both these tracking paradigms. Furthermore, we thoroughly analyze the performance of DCF and Siamese trackers on nine benchmarks, covering different experimental aspects of visual tracking: datasets, evaluation metrics, performance, and speed comparisons. We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.
KW - Benchmark testing
KW - Correlation
KW - Discriminative Correlation Filters
KW - Feature extraction
KW - Object tracking
KW - Siamese Networks
KW - Target tracking
KW - Training
KW - Visual Object Tracking
KW - Visualization
UR - http://www.scopus.com/inward/record.url?scp=85139840009&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2022.3212594
DO - 10.1109/TPAMI.2022.3212594
M3 - Article
AN - SCOPUS:85139840009
SN - 0162-8828
SP - 1
EP - 20
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -