We present in this paper a research platform for development and evaluation of embodied visual object recognition strategies. The platform uses a stereoscopic peripheral-foveal camera system and a fast pan-tilt unit to perform saliency-based visual search. This is combined with a classification framework based on the bag-of-features paradigm with the aim of targeting, classifying and recognising objects. Interaction with the system is done via typed commands and speech synthesis. We also report the current classification performance of the system.

In this paper, we study object recognition in the embodied setting. More specifically, we study the problem of whether the recognition system will benefit from acquiring another observation of the object under study, or whether it is time to give up, and report the observed object as unknown. We describe the hardware and software of a system that implements recognition and object permanence as two nested perception-action cycles. We have collected three data sets of observation sequences that allow us to perform controlled evaluation of the system behavior. Our recognition system uses a KNN classifier with bag-of-features prototypes. For this classifier, we have designed and compared three different uncertainty measures for target observation. These measures allow the system to (a) decide whether to continue to observe an object or to move on, and to (b) decide whether the observed object is previously seen or novel. The system is able to successfully reject all novel objects as “unknown”, while still recognizing most of the previously seen objects.

Segmentation is an important preprocessing step in many applications. Compared to colour segmentation, fusion of colour and depth greatly improves the segmentation result. Such a fusion is easy to do by stacking measurements in different value dimensions, but there are better ways. In this paper we perform fusion using the channel representation, and demonstrate how a state-of-the-art segmentation algorithm can be modified to use channel values as inputs. We evaluate segmentation results on data collected using the Microsoft Kinect peripheral for Xbox 360, using the superparamagnetic clustering algorithm. Our experiments show that depth gradients are more useful than depth values for segmentation, and that channel coding both colour and depth gradients makes tuned parameter settings generalise better to novel images.

This paper describes a method for generation of dense stereo ground-truth using a consumer depth sensor such as the Microsoft Kinect. Such ground-truth allows adaptation of stereo algorithms to a specific setting. The method uses a novel residual weighting based on error propagation from image plane measurements to 3D. We use this ground-truth in wide-angle stereo learning by automatically tuning a novel extension of the best-first-propagation (BFP) dense correspondence algorithm. We extend BFP by adding a coarse-to-fine scheme, and a structure measure that limits propagation along linear structures and flat areas. The tuned correspondence algorithm is evaluated in terms of accuracy, robustness, and ability to generalise. Both the tuning cost function, and the evaluation are designed to balance the accuracy-robustness trade-off inherent in patch-based methods such as BFP.