Object Detection

Object detection for real world applications is still a challenging problem. While increased data can partly solve the problem, the ability of detectors to process large data sets in reasonable time becomes another important issue besides accuracy.

A family of methods that can handle large amount of training data efficiently, and that are inherently suited for multi-class problems, are based on random forests, which are ensembles of randomized decision trees that can be applied to regression or classification tasks. Since object detection involves both classifying patches belonging to an object and using them to regress the location and scale of the object, random forests for object detection need to be trained to satisfy both objectives [].

While object detection based on Hough forests allows parts observed in different training instances to support a single object hypothesis, it also produces false positives by accumulating votes that are consistent in location but inconsistent in other properties like pose, color, shape or type. To address this problem, Hough forests can be augmented with latent variables in order to enforce consistency among votes []. To this end, only votes that agree on the assignment of the latent variable are allowed to support a single hypothesis.

In order to avoid an expensive manual labeling process, or to learn object classes autonomously without human intervention, we propose a framework for object discovery in activity-labeled videos []. Since small objects like pens are difficult to discover only based on appearance, we introduce similarity based on object functionality, which can be estimated from relative human-object motion during the activity. We show that functionality is an important cue for discovering objects from activities in RGB(D) video datasets.

Members

Perceiving Systems

Abhilash Srikantha

Perceiving Systems

Jürgen Gall

Publications

Perceiving Systems Conference Paper Human Pose as Context for Object Detection Srikantha, A., Gall, J. British Machine Vision Conference, British Machine Vision Conference, September 2015

Abstract ›

Detecting small objects in images is a challenging problem particularly when they are often occluded by hands or other body parts. Recently, joint modelling of human pose and objects has been proposed to improve both pose estimation as well as object detection. These approaches, however, focus on explicit interaction with an object and lack the flexibility to combine both modalities when interaction is not obvious. We therefore propose to use human pose as an additional context information for object detection. To this end, we represent an object category by a tree model and train regression forests that localize parts of an object for each modality separately. Predictions of the two modalities are then combined to detect the bounding box of the object. We evaluate our approach on three challenging datasets which vary in the amount of object interactions and the quality of automatically extracted human poses.

pdf abstract BibTeX

Perceiving Systems Conference Paper Hough-based Object Detection with Grouped Features Srikantha, A., Gall, J. International Conference on Image Processing, 1653-1657, Paris, France, IEEE International Conference on Image Processing , October 2014

Abstract ›

Hough-based voting approaches have been successfully applied to object detection. While these methods can be efficiently implemented by random forests, they estimate the probability for an object hypothesis for each feature independently. In this work, we address this problem by grouping features in a local neighborhood to obtain a better estimate of the probability. To this end, we propose oblique classification-regression forests that combine features of different trees. We further investigate the benefit of combining independent and grouped features and evaluate the approach on RGB and RGB-D datasets.

pdf poster DOI BibTeX

Perceiving Systems Conference Paper Discovering Object Classes from Activities Srikantha, A., Gall, J. In European Conference on Computer Vision, 8694:415-430, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, 13th European Conference on Computer Vision, September 2014

Abstract ›

In order to avoid an expensive manual labeling process or to learn object classes autonomously without human intervention, object discovery techniques have been proposed that extract visual similar objects from weakly labelled videos. However, the problem of discovering small or medium sized objects is largely unexplored. We observe that videos with activities involving human-object interactions can serve as weakly labelled data for such cases. Since neither object appearance nor motion is distinct enough to discover objects in these videos, we propose a framework that samples from a space of algorithms and their parameters to extract sequences of object proposals. Furthermore, we model similarity of objects based on appearance and functionality, which is derived from human and object motion. We show that functionality is an important cue for discovering objects from activities and demonstrate the generality of the model on three challenging RGB-D and RGB datasets.

pdf anno poster DOI BibTeX

Perceiving Systems Book Chapter Class-Specific Hough Forests for Object Detection Gall, J., Lempitsky, V. In Decision Forests for Computer Vision and Medical Image Analysis, 143-157, 11, (Editors: Criminisi, A. and Shotton, J.), Springer, 2013 code BibTeX

Perceiving Systems Book Chapter An Introduction to Random Forests for Multi-class Object Detection Gall, J., Razavi, N., van Gool, L. In Outdoor and Large-Scale Real-World Scene Analysis, 7474:243-263, LNCS, (Editors: Dellaert, Frank and Frahm, Jan-Michael and Pollefeys, Marc and Rosenhahn, Bodo and Leal-Taix’e, Laura), Springer, 2012 code for Hough forest publisher's site pdf BibTeX

Perceiving Systems Conference Paper Interactive Object Detection Yao, A., Gall, J., Leistner, C., van Gool, L. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3242-3249, IEEE, Providence, RI, USA, 2012 video pdf BibTeX

Perceiving Systems Conference Paper Latent Hough Transform for Object Detection Razavi, N., Gall, J., Kohli, P., van Gool, L. In European Conference on Computer Vision (ECCV), 7574:312-325, LNCS, Springer, 2012 pdf BibTeX

Perceiving Systems Conference Paper Local Context Priors for Object Proposal Generation Ristin, M., Gall, J., van Gool, L. In Asian Conference on Computer Vision (ACCV), 7724:57-70, LNCS, Springer-Verlag, 2012 pdf DOI BibTeX

Perceiving Systems Conference Paper Sparsity Potentials for Detecting Objects with the Hough Transform Razavi, N., Alvar, N., Gall, J., van Gool, L. In British Machine Vision Conference (BMVC), 11.1-11.10, (Editors: Bowden, Richard and Collomosse, John and Mikolajczyk, Krystian), BMVA Press, 2012 pdf BibTeX