Tinne Tuytelaars

Towards a more discriminative and semantic visual vocabulary

We present a novel method for constructing a visual vocabulary that takes into account the class labels of images, thus resulting in better recognition performance and more efficient learning. Our method consists of two stages: Cluster Precision Maximisation (CPM) and Adaptive Refinement. In the first stage, a Reciprocal Nearest Neighbours (RNN) clustering algorithm is guided towards class representative visual words by maximising a new cluster precision criterion. As we are able to optimise the vocabulary without the need for expensive cross-validation, the overall training time is significantly reduced without a negative impact on the results. Next, an adaptive threshold refinement scheme is proposed with the aim of increasing vocabulary compactness while at the same time improving the recognition rate and further increasing the representativeness of the visual words for category-level object recognition. This is a correlation clustering based approach, which works as a meta-clustering and optimises the cut-off threshold for each cluster separately. In the experiments we analyse the recognition rate of different vocabularies for a subset of the Caltech 101 dataset, showing how RNN in combination with CPM selects the optimal codebooks, and how the clustering refinement step succeeds in further increasing the recognition rate.

Shape-from-recognition: Recognition enables meta-data transfer

Low-level cues in an image not only allow to infer higher-level information like the presence of an object, but the inverse is also true. Category-level object recognition has now reached a level of maturity and accuracy that allows to successfully feed back its output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer different kinds of meta-data annotations for images of previously unseen object instances, in particular information on 3D shape. Meta-data can be discrete, real- or vector-valued. Our approach builds on the Implicit Shape Model of Leibe and Schiele [B. Leibe, A. Leonardis, B. Schiele, Robust object detection with interleaved categorization and segmentation, International Journal of Computer Vision 77 (1-3) (2008) 259-289], and extends it to transfer annotations from training images to test images. We focus on the inference of approximative 3D shape information about objects in a single 2D image. In experiments, we illustrate how our method can infer depth maps, surface normals and part labels for previously unseen object instances.

Camera Based Fall Detection Using Multiple Features Validated with Real Life Video

More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again unaided. The lack of timely aid can lead to severe complications such as dehydration, pressure ulcers and death. A camera based fall detection system can provide a solution. In this paper we compare four different fall features extracted from the dominant foreground object, as well as various combinations thereof. All tests are executed using real life data, which has been recorded at the home of 4 elderly, containing 24 falls. Experiments indicate that a fall detector based on a combination of aspect ratio, head speed and fall angle is preferred. The preliminary detector, which still has a substantial false alarm rate with a precision of 0.257(±0.073) and a promising recall of 0.896(±0.194), gives insights for further improvement as is discussed.

Naive bayes image classification: beyond nearest neighbors

Naive Bayes Nearest Neighbor (NBNN) has been proposed as a powerful, learning-free, non-parametric approach for object classification. Its good performance is mainly due to the avoidance of a vector quantization step, and the use of image-to-class comparisons, yielding good generalization. In this paper we study the replacement of the nearest neighbor part with more elaborate and robust (sparse) representations, as well as trading performance for speed for practical purposes. The representations investigated are k-Nearest Neighbors (kNN), Iterative Nearest Neighbors (INN) solving a constrained least squares (LS) problem, Local Linear Embedding (LLE), a Sparse Representation obtained by l1-regularized LS (

Omnidirectional vision based topological navigation

SR_{l_1}

Matching widely separated views based on affinely invariant neighbourhoods

), and a Collaborative Representation obtained as the solution of a l2-regularized LS problem (

Omnidirectional sparse visual path following with occlusion-robust feature tracking

CR_{l_2}

Speeded-UpRobustFeatures(SURF)

). In particular, NIMBLE and K-DES descriptors proved viable alternatives to SIFT and, the NB

Markerless computer vision based localization using automatically generated topological maps

SR_{l_1}

Proceedings of Robotics: Science and Systems IV

and NBINN classifiers provide significant improvements over NBNN, obtaining competitive results on Scene-15, Caltech-101, and PASCAL VOC 2007 datasets, while remaining learning-free approaches (i.e., no parameters need to be learned).