Dariu Gavrila

Learn More
Detecting people in images is key for several important application domains in computer vision. This paper presents an in-depth experimental study on pedestrian classification; multiple feature-classifier combinations are examined with respect to their ROC performance and efficiency. We investigate global versus local and adaptive versus nonadaptive(More)
The ability to recognize humans and their activities by vision is key for a machine to interact intelligently and e ortlessly with a humaninhabited environment. Because of many potentially important applications, \Looking at People" is currently one of the most active application domains in computer vision. This survey identi es a number of promising(More)
Pedestrian detection is a rapidly evolving area in computer vision with key applications in intelligent vehicles, surveillance, and advanced robotics. The objective of this paper is to provide an overview of the current state of the art from both methodological and experimental perspectives. The first part of the paper consists of a survey. We cover the(More)
This paper presents a multi-cue vision system for the real-time detection and tracking of pedestrians from a moving vehicle. The detection component involves a cascade of modules, each utilizing complementary visual criteria to successively narrow down the image search space, balancing robustness and efficiency considerations. Novel is the tight integration(More)
  • Dariu Gavrila
  • IEEE Transactions on Pattern Analysis and Machine…
  • 2007
This paper presents a novel probabilistic approach to hierarchical, exemplar-based shape matching. No feature correspondence is needed among exemplars, just a suitable pairwise similarity measure. The approach uses a template tree to efficiently represent and match the variety of shape exemplars. The tree is generated offline by a bottom-up clustering(More)
This paper presents a prototype system for pedestrian detection on-board a moving vehicle. The system uses a generic two-step approach for efficient object detection. In the first step, contour features are used in a hierarchical template matching approach to efficiently ”lock” onto candidate solutions. Shape matching is based on Distance Transforms. By(More)
This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert classifiers trained on features derived from intensity, depth and motion. To handle partial occlusion, we compute expert weights that are related to the degree of visibility of the(More)
In this paper we describe our work on 3-D model-based tracking and recognition of human movement from real images. Our system has two major components. The rst component takes real image sequences acquired from multiple views and recovers the 3-D body pose at each time instant. The pose-recovery problem is formulated as a search problem and entails nding(More)