Template matching using fast normalized cross correlation

By Kai Briechle, Uwe D. Hanebeck. SPIE Defense + Commercial Sensing, 2001

716 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/3632776737dc58adf0e278f9a7cafbeb6c1ec734

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Martin Danelljan
2. Fahad Shahbaz Khan
3. Michael Felsberg
4. Ming-Hsuan Yang
5. Jianke Zhu
6. Gustav Häger
7. Fatih Murat Porikli
8. Jiri Matas

In Artificial Intelligence

1. Ming-Hsuan Yang
2. Philip H. S. Torr
3. Fahad Shahbaz Khan
4. Ali Farhadi
5. Bernt Schiele
6. Sergey Levine
7. Li Fei-Fei
8. Martin Danelljan

Citations in the corpus

• Siamese Instance Search for Tracking (2016, background): “We rather focus on the matching function alone, similar to the simplicity of the normalized cross-correlation (NCC) tracker [7, 2].”
• Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, methodology): “Based on the proposals of Normalised Cross Correlation (NCC) [38] and Minimum Output Sum of Squared Error (MOSSE) filter [7], Henriques et al. improved MOSSE by introducing circulant structure [11], which enabled efficient calculation of filter learning with element-wise operations.”
• Visual Tracking: an Experimental Survey (2013, neutral): “An array of brightness values is still the most often used paradigm like in NCC [50], STR [71] and many others.”
• MSMO: Multimodal Summarization with Multimodal Output (2018, neutral): “Fourier Analysis template matching (Briechle and Hanebeck, 2001).”
• A Fast Normalized Cross-Correlation Calculation Method for Motion Estimation (2010, positive): “, reference window) and obtain substantial computational gains over the fft-based methods [33], [34].”
• A Novel Performance Evaluation Methodology for Single-Target Trackers (2015, background): “IMPNCC (an improvement of the NCC tracker [65]), two”
• Watching the World Go By: Representation Learning from Unlabeled Videos (2020, methodology): “This process is similar to template matching [4] but in deep feature space.”
• The Visual Object Tracking VOT2017 Challenge Results (2017, methodology): “The tracker KFebT [57] fuses the result of three out-of-the box trackers: a mean-shift tracker that uses colour histogram (ASMS) [73], a kernelized correlation filter (KCF) [26] and the Normalized CrossCorrelation (NCC) [8] by using a Kalman filter.”
• Fast normalized cross correlation for defect detection (2003, background): “Briechle and Hanebeck (2001) further presented a sum table-based algorithm for fast calculation of the NCC, and applied it to the problem of object recognition.”
• UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking (2016, background): “We rather focus on the matching function alone, similar to the simplicity of the normalized cross-correlation (NCC) tracker [7, 2].”