Online Multi-Object Tracking by Quadratic Pseudo-Boolean Optimization

Authors: Long Lan, Dacheng Tao, Chen Gong, Naiyang Guan, Zhigang Luo

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on publicly available datasets from both static and moving cameras demonstrate the superiority of our method.
Researcher Affiliation Academia College of Computer, National University of Defense Technology Centre for Quantum Computation & Intelligent Systems, FEIT, University of Technology, Sydney
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code No The paper mentions 'Our non-optimized codes run at around 3-12 fps' but does not provide any concrete access information, such as a specific repository link or an explicit code release statement, for the methodology described.
Open Datasets Yes Extensive experiments on publicly available datasets from both static and moving cameras demonstrate the superiority of our method. The datasets adopted here include PETS-S2L12, TUDCrossing, TUD-Campus [Andriluka et al., 2008], ETHbahnhof, and ETH-sunny [Ess et al., 2008]. 2http://www.cvg.reading.ac.uk/PETS2009/a.html
Dataset Splits No The paper uses terms like 'train' and 'validation' in a general context but does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for its experiments.
Hardware Specification Yes We perform our experiments on a 3.45GHz PC with 6.0 GB memory with codes implemented in C++.
Software Dependencies No The paper mentions 'codes implemented in C++' but does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment.
Experiment Setup Yes We set = 1 and β = 100 empirically. We set h = 100 and it has no obvious influence to the tracking performances. We use the deformable part-based detector [Felzenszwalb et al., 2010] to obtain hypotheses for each frame... Fj is the classifier score of Fj on di, we adopt the well-proven LBP and color features [Shu et al., 2012] in our appearance model and build the classifier similar to [Shu et al., 2012].