CVIVDec 30, 2021

SFU-HW-Tracks-v1: Object Tracking Dataset on Raw Video Sequences

arXiv:2112.14934v13 citations
Originality Synthesis-oriented
AI Analysis

This provides a resource for researchers in video processing and computer vision to benchmark tracking algorithms and analyze compression impacts, but it is incremental as it adds annotations to existing sequences.

The authors introduced SFU-HW-Tracks-v1, a dataset with object annotations and unique IDs for 13 HEVC video sequences, enabling evaluation of object tracking on uncompressed video and study of compression effects.

We present a dataset that contains object annotations with unique object identities (IDs) for the High Efficiency Video Coding (HEVC) v1 Common Test Conditions (CTC) sequences. Ground-truth annotations for 13 sequences were prepared and released as the dataset called SFU-HW-Tracks-v1. For each video frame, ground truth annotations include object class ID, object ID, and bounding box location and its dimensions. The dataset can be used to evaluate object tracking performance on uncompressed video sequences and study the relationship between video compression and object tracking.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes