A Novel Scale Insensitive KCF Tracker Based on HOG and Color Features

Kernelized Correlation Filters (KCF) for visual tracking have received much attention due to their fast speed and outstanding performances in real scenarios. However, the KCF sometimes still fails to track the targets with different scales, and it may drift because the target response is fixed and the original histogram of orientation gradient (HOG) features cannot represent the targets well. In this paper, we propose a novel fast tracker, which is based on KCF and insensitive to scale changes by learning two independent correlation filters (CFs) where one filter is designed for position estimation and the other is for scale estimation. In addition, it can adaptively change the target response and multiple features are integrated to improve the performance for our tracker. Finally, we employ an adaptive high confidence filters updating scheme to avoid errors. Evaluated on the popular OTB50 and OTB100 datasets, our proposed trackers show superior performances in terms of efficiency and accuracy compared to the existing methods.

The ATLAS Fast TracKer—Architecture, Status and High-Level Data Quality Monitoring Framework

The Fast Tracker (FTK) is a highly parallel processor dedicated to a quick and efficient reconstruction of tracks in the Pixel and Semiconductor Tracker (SCT) detectors of the ATLAS experiment at LHC. It is designed to identify charged particle tracks with transverse momentum above 1 GeV and reconstruct their parameters at an event rate of up to 100 kHz. The average latency of the processing is below 100 μs at the expected collision intensities. This performance is achieved by using custom ASIC chips with associative memory for pattern matching, while modern FPGAs calculate the track parameters. This paper describes the architecture, the current status and a High-Level Data Quality Monitoring framework of the FTK system. This monitoring framework provides an online comparison of the FTK hardware output with the FTK functional simulation, which is run on the pixel and SCT detector data at a low rate, allowing the detection of non-expected outputs of the FTK system.

The Impact of Applying Wildcards to Disabled Modules for Ftk Pattern Banks on Efficiency and Data Flow

Online selection is an essential step to collect the most relevant collisions from the very large number of collisions inside the ATLAS detector at the Large Hadron Collider (LHC). The Fast TracKer (FTK) is a hardware based track finder, built to greatly improve the ATLAS trigger system capabilities for identifying interesting physics processes through track-based signatures. The FTK is reconstructing after each Level-1 trigger all tracks with pT > 1 GeV, such that the high-level trigger system gains access to track information at an early stage. FTK track reconstruction starts with a pattern recognition step. Patterns are found with hits in seven out of eight possible detector layers. Disabled detector modules, as often encountered during LHC operation, lead to efficiency losses. To recover efficiency, WildCards (WC) algorithms are implemented in the FTK system. The WC algorithm recovers inefficiency but also causes high combinatorial background and thus increased data volumes in the FTK system, possibly exceeding hardware limitations. To overcome this, a refined algorithm to select patterns is developed and investigated in this article.

Software Based Control and Monitoring of a Hardware Based Track Reconstruction System for the ATLAS Experiment

During Run 2 of the Large Hadron Collider (LHC) the instantaneous luminosity exceeded the nominal value of 1034 cm−2 s−1 with a 25 ns bunch crossing period and the number of overlapping proton-proton interactions per bunch crossing increased to a maximum of about 80. These conditions pose a challenge to the trigger system of the experiments that has to manage rates while keeping a good efficiency for interesting physics events. This document summarizes the software based control and monitoring of a hardware-based track reconstruction system for the ATLAS experiment, called Fast Tracker (FTK), composed of associative memories and FPGAs operating at the rate of 100 kHz and providing high quality track information within the available latency to the high-level trigger. In particular, we will detail the commissioning of the FTK within the ATLAS online software system presenting the solutions adopted for scaling up the system and ensuring robustness and redundancy. We will also describe the solutions to challenges such as controlling the occupancy of the buffers, managing the heterogeneous and large configuration, and providing monitoring information at sufficient rate.