2016

A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

Keuper, Margret, Tang, Siyu, Zhongjie, Yu et al.

Understand

Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios.

Both tasks benefit from decomposing a graphical model into an optimal number of connected components based on attractive and repulsive pairwise terms.
The two tasks are formulated on different levels of granularity and, accordingly, leverage mostly local information for motion segmentation and mostly high-level information for multi-target tracking.
In this paper we argue that point trajectories and their local relationships can contribute to the high-level task of multi-target tracking and also argue that high-level cues from object detection and tracking are helpful to solve motion segmentation.

Built on

An efficient heuristic procedure for partitioning graphs
B. W. Kernighan, S.L.: · 1970
Earlier work this paper cites.
The partition problem
Chopra, S., Rao, M.: · 1993
Earlier work this paper cites.
Geometry of Cuts and Metrics
Deza, M.M., Laurent, M.: · 1997
Earlier work this paper cites.
Correlation clustering in general weighted graphs
Demaine, E.D., Emanuel, D., Fiat, A., Immorlica, N.: · 2006
Earlier work this paper cites.
Robust object tracking by hierarchical association of detection responses
Huang, C., Wu, B., Nevatia, R.: · 2008
Earlier work this paper cites.
People-tracking-by-detection and people-detection-by-tracking
Andriluka, M., Roth, S., Schiele, B.: · 2008
Earlier work this paper cites.
Shape priors in variational image segmentation: Convexity, lipschitz continuity and globally optimal solutions
Cremers, D., Schmidt, F.R., Barthel, F.: · 2008
Earlier work this paper cites.
Non-negative matrix factorization of partial track data for motion segmentation
Cheriyadat, A., Radke, R.: · 2009
Earlier work this paper cites.
Monocular 3d scene modeling and inference: Understanding multi-object traffic scenes
Wojek, C., Roth, S., Schindler, K., Schiele, B.: · 2010
Earlier work this paper cites.
Monocular 3d pose estimation and tracking by detection
Andriluka, M., Roth, S., Schiele, B.: · 2010
Earlier work this paper cites.
Object segmentation by long term analysis of point trajectories
Brox, T., Malik, J.: · 2010
Earlier work this paper cites.
Object detection with discriminatively trained part-based models
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: · 2010
Earlier work this paper cites.
Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement
Fragkiadaki, K., Shi, J.: · 2011
Earlier work this paper cites.
Probabilistic image segmentation with closedness constraints
Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: · 2011
Earlier work this paper cites.
Globally optimal image partitioning by multicuts
Kappes, J.H., Speth, M., Andres, B., Reinelt, G., Schnörr, C.: · 2011
Earlier work this paper cites.
Globally-optimal greedy algorithms for tracking a variable number of objects
Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: · 2011
Earlier work this paper cites.
Tracking multiple people under global appearance constraints
Shitrit, H.B., Berclaz, J., Fleuret, F., Fua, P.: · 2011
Earlier work this paper cites.
Globally-optimal greedy algorithms for tracking a variable number of objects
Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: · 2011
Earlier work this paper cites.
Track to the future: Spatio-temporal video segmentation with long-range motion cues
Lezama, J., Alahari, K., Sivic, J., Laptev, I.: · 2011
Earlier work this paper cites.
Large displacement optical flow: descriptor matching in variational motion estimation
Brox, T., Malik, J.: · 2011
Earlier work this paper cites.

Similar

Level-set person segmentation and tracking with multi-region appearance models and top-down shape information
E. Horbert, K. Rematas, B.L.: · 2011
Cited alongside, same era.
Two-granularity tracking: Mediating trajectory and detection graphs for tracking under occlusions
Fragkiadaki, K., Zhang, W., Zhang, G., Shi, J.: · 2012
Cited alongside, same era.
GMCP-Tracker: Global multi-object tracking using generalized minimum clique graphs
Zamir, A.R., Dehghan, A., Shah, M.: · 2012
Cited alongside, same era.
Higher order motion models and spectral clustering
Ochs, P., Brox, T.: · 2012
Cited alongside, same era.
Globally optimal closed-surface segmentation for connectomics
Andres, B., Kröger, T., Briggman, K.L., Denk, W., Korogod, N., Knott, G., Köthe, U., Hamprecht, F.A.: · 2012
Cited alongside, same era.
Discrete-continuous optimization for multi-target tracking
Andriyenko, A., Schindler, K., Roth, S.: · 2012
Cited alongside, same era.
Multi-scale clustering of frame-to-frame correspondences for motion segmentation
Dragon, R., Rosenhahn, B.and Ostermann, J.: · 2012
Cited alongside, same era.
Latent data association: Bayesian model selection for multi-target tracking
Segal, A.V., Reid, I.: · 2013
Cited alongside, same era.
Monocular visual scene understanding: Understanding multi-object traffic scenes
Wojek, C., Walk, S., Roth, S., Schindler, K., Schiele, B.: · 2013
Cited alongside, same era.
Robust trajectory clustering for motion segmentation
Shi, F., Zhou, Z., Xiao, J., Wu, W.: · 2013
Cited alongside, same era.
A Video Representation Using Temporal Superpixels
Chang, J., Wei, D., III, J.W.F.: · 2013
Cited alongside, same era.
Perspective motion segmentation via collaborative clustering
Li, Z., Guo, J., Cheong, L., Zhou, S.: · 2013
Cited alongside, same era.

Then

Robust motion segmentation with unknown correspondences
Ji, P., Li, H., Salzmann, M., Dai, Y.: · 2014
Later among the works it cites.
Tracking interacting objects optimally using integer programming
Wang, X., Turetken, E., Fleuret, F., Fua, P.: · 2014
Later among the works it cites.
Tracking interacting objects optimally using integer programming
Wang, X., Turetken, E., Fleuret, F., Fua, P.: · 2014
Later among the works it cites.
Fast segmentation of sparse 3d point trajectories using group theoretical invariants
Zografos, V., Lenz, R., Ringaby, E., Felsberg, M., Nordberg, K.: · 2014
Later among the works it cites.
LSDA: Large scale detection through adaptation
Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., Saenko, K.: · 2014
Later among the works it cites.
Cut, glue, & cut: A fast, approximate solver for multicut partitioning
Beier, T., Kroeger, T., Kappes, J., Kothe, U., Hamprecht, F.: · 2014
Later among the works it cites.
Motion trajectory segmentation via minimum cost multicuts
Keuper, M., Andres, B., Brox, T.: · 2015
Later among the works it cites.
High-for-low and low-for-high: Efficient boundary detection from deep object features and its applications to high-level vision
Original
Bertasius, G., Shi, J., Torresani, L.: · 2015
Later among the works it cites.
Learning to segment moving objects in videos
Fragkiadaki, K., Arbelaez, P., Felsen, P., Malik, J.: · 2015
Later among the works it cites.
Joint tracking and segmentation of multiple targets
Milan, A., Leal-Taix, L., Schindler, K., Reid, I.: · 2015
Later among the works it cites.
Efficient decomposition of image and mesh graphs by lifted multicuts
Keuper, M., Levinkov, E., Bonneel, N., Lavoue, G., Brox, T., Andres, B.: · 2015
Later among the works it cites.
Subgraph decomposition for multi-object tracking
Tang, S., Andres, B., Andriluka, M., Schiele, B.: · 2015
Later among the works it cites.
Faster R-CNN: Towards real-time object detection with region proposal networks
Ren, S., He, K., Girshick, R., Sun, J.: · 2015
Later among the works it cites.
Fusion moves for correlation clustering
Beier, T., Hamprecht, F.A., Kappes, J.H.: · 2015
Later among the works it cites.
Motchallenge 2015: Towards a benchmark for multi-target tracking
Original
Leal-Taixé, L., Milan, A., Reid, I., Roth, S., Schindler, K.: · 2015
Later among the works it cites.
Semantic image segmentation with deep convolutional nets and fully connected crfs
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: · 2015
Later among the works it cites.
Weakly- and semi-supervised learning of a dcnn for semantic image segmentation
Original
Papandreou, G., Chen, L.C., Murphy, K., Yuille, A.L.: · 2015
Later among the works it cites.
Fast r-cnn
Girshick, R.: · 2015
Later among the works it cites.
Near-online multi-target tracking with aggregated local flow descriptor
Choi, W.: · 2015
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…