1 / 1

Tracklet-global Motion Cost Model

GMCP-Tracker : Global Multi-object Tracking Using Generalized Minimum Clique Graphs Amir Roshan Zamir, Afshin Dehghan, Mubarak Shah ({ aroshan | adehghan | shah @cs.ucf.edu} , University of Central Florida). Frame 1. Frame 2. Frame 3. Frame 1. Frame 2. Frame 3. Frame 1.

johnda
Download Presentation

Tracklet-global Motion Cost Model

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique GraphsAmir Roshan Zamir, Afshin Dehghan, Mubarak Shah ({aroshan| adehghan | shah @cs.ucf.edu} , University of Central Florida) Frame 1 Frame 2 Frame 3 Frame 1 Frame 2 Frame 3 Frame 1 Frame 2 Frame 3 Frame 1 Frame 1 Frame 2 Frame 2 Frame 3 Frame 3 Frame 2 UCF ECCV ‘12 Frame 5 Frame 6 Frame 4 Frame 5 Frame 6 Frame 4 Frame 5 Frame 5 Frame 6 Frame 6 Frame 4 Frame 4 Frame 5 4. Finding Tracklets Using GMCP: • Problem: • Tracking by Detection • Key Contributions: • A new tool in Computer Vision: • Generalized Minimum Clique Problem (GMCP): • Typically useful where there are multiple possibilities for some subproblems, as well as a global criterion to satisfy. • GMCP utilized for computing tracklets and trajectories. • A new temporally globalapproach to Data Association • A new tracklet-global motion cost model. • Shifting approximation from Time Domain to Object Domain: • Finding tracklets/trajectories in a temporally global way. • Finding the tracklet/trajectory of one object at a time (greedy). • Found Tracklets in Different Segments: Frame 5 Frame 6 Frame 4 Input Detections Merging Tracklets into Trajectories: Input Graph G Trajectories Minimum Clique Input Tracklets Occlusion Handling using HN • Tracklet-global Motion Cost Model Bipartite Matching vs. GMCP 2. Block Diagram: Experimental Results Minimum Clique 3. Generalized Minimum Clique Problem (GMCP): Generalized Minimum Clique Input to GMCP Project Page: http://vision.eecs.ucf.edu/ projects/GMCP-Tracker/ Occlusion Handling Using HN • Occlusion Handling Using Hypothetical Nodes: Project Page • Definition: • (nodes≡detections)(clusters≡frames) (GMCP solution=tracklet of one Object) YouTube

More Related