Jorge Batista

Learn More
The core component of most modern trackers is a discriminative classifier, tasked with distinguishing between the target and the surrounding environment. To cope with natural image changes, this classifier is typically trained with translated and scaled sample patches. Such sets of samples are riddled with redundancies—any overlapping pixels are(More)
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are 2 Authors Suppressed Due to Excessive Length presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For(More)
Why is pedestrian detection still very challenging in realistic scenes? How much would a successful solution to monocular depth inference aid pedestrian detection? In order to answer these questions we trained a state-of-the-art deformable parts detector using different configurations of optical images and their associated 3D point clouds, in conjunction(More)
Semantic segmentation and object detection are nowadays dominated by methods operating on regions obtained as a result of a bottom-up grouping process (segmentation) but use feature extractors developed for recognition on fixed-form (e.g. rectangular) patches, with full images as a special case. This is most likely suboptimal. In this paper we focus on(More)
We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs object shapes by(More)
Competitive sliding window detectors require vast training sets. Since a pool of natural images provides a nearly endless supply of negative samples, in the form of patches at different scales and locations, training with all the available data is considered impractical. A staple of current approaches is hard negative mining, a method of selecting relevant(More)
This paper describes a framework for analyzing video sequences of a driver and determining his level of attention. The proposed system deals with the computation of eyelid movement parameters and head (face) orientation estimation. The system relies on pupil detection to robustly track the driver’s head pose and monitoring its level of fatigue. Visual(More)
An active vision system has to enable the implementation of reactive visual processes and of elementary visual behaviors in real time. In this paper we describe the real-time implementation of several visual behaviors in an active vision system. Issues related to the real-time implementation are discussed, namely in what concerns the modelling of the(More)
The development of computational solutions for simulation of visual behavior deals with the problem of integration and co-operation between different computational processes for control of active vision systems. In general these computational processes could emulate different and specific artificial visual behavior and their integration presents distinct(More)
In this paper we describe an active binocular tracking system integrating peripheral motion detection. The system is made up of a binocular active system used to track the objects and a xed camera providing wide angle images of the environment. The system can cope with changes in lighting conditions by adjusting aperture and focus. Binocular ow enables(More)