AI Paper Atlas

Research map / 3D vision / Human pose estimation

A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking

Henning Tjaden, Ulrich Schwanecke, Elmar Schömer, Daniel Cremers

TPAMI 2018 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 112 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Gauss-Newton-like second-order optimization instead of first-order gradient descentPWP3D · screwdriver 360 degree rotation sequencetracking successImproved
use region-based Gauss-Newton with tclc-histograms instead of PWP3DPWP3D · OPT dataset (Bike)AUC: 5.358 -> 11.903Improved
use proposed method instead of ORB-SLAM2 on weakly textured objectsORB-SLAM2 · OPT dataset (Bike)AUC: 10.410 -> 11.903Improved
use proposed method instead of ORB-SLAM2 on well-textured objectsORB-SLAM2 · OPT dataset (House)AUC: 17.283 -> 10.150Hurt
use proposed method instead of ORB-SLAM2 on SodaORB-SLAM2 · OPT dataset (Soda)AUC: 13.444 -> 8.861Hurt
replace previous Gauss-Newton-like scheme with systematic Gauss-Newton on reweighted least squaresprevious tclc-histogram tracker · RBOT regular (Ape)tracking success (%): 62.1 -> 85.0Improved
replace previous scheme with proposed methodprevious tclc-histogram tracker · RBOT regular (Glue)tracking success (%): 20.2 -> 38.9Improved
replace previous scheme with proposed methodprevious tclc-histogram tracker · RBOT regular (Cat)tracking success (%): 96.7 -> 95.9Hurt
replace previous scheme with proposed methodprevious tclc-histogram tracker · RBOT noisy + dynamic light (Egg Box)tracking success (%): 2.3 -> 11.2Improved
replace previous scheme with proposed methodprevious tclc-histogram tracker · RBOT unmodelled occlusion (Cube)tracking success (%): 39.6 -> 68.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy