Cross-View People Tracking by Scene-Centered Spatio-Temporal Parsing

Authors: Yuanlu Xu, Xiaobai Liu, Lei Qin, Song-Chun Zhu

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In experiments, we validate our method on one public dataset and create another new dataset that records people s daily life in public, e.g., food court, office reception and plaza, each of which includes 3-4 cameras. We evaluate the proposed method on these challenging videos and achieve promising multi-view tracking results.
Researcher Affiliation Academia 1Dept. Computer Science and Statistics, University of California, Los Angeles (UCLA) 2Dept. Computer Science, San Diego State University (SDSU) 3Inst. Computing Technology, Chinese Academy of Sciences
Pseudocode Yes Algorithm 1: Sketch of our inference algorithm
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes To evaluate the proposed method, we compare with other state-of-the-arts using two datasets: (1) CAMPUS dataset (Xu et al. 2016). This is a newly published dataset targeting multi-view tracking.
Dataset Splits No The paper states, 'For both datasets, we incorporate 10% of the videos as augmented training set and the rest as testing set,' providing training and testing splits but not explicitly mentioning a separate validation split or its proportion.
Hardware Specification Yes We implement the proposed method with MATLAB and test it on a workstation with I7 3.0GHz CPU, 32GB memory and GTX1080 GPU.
Software Dependencies No The paper mentions software like MATLAB, fast r-cnn, and Caffe, but does not provide specific version numbers for these dependencies.
Experiment Setup Yes The pruning threshold is set to 0.3. We apply Sequential Shortest Path (SSP) (Pirsiavash, Ramanan, and Fowlkes 2011) to initialize tracklets. The sampling is set to finish after 1000 iterations, which achieves decent results. All parameters are fixed in the experiment.