This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes. This problem poses several challenges. People are highly non-rigid objects with a high degree of variability in size, shape, color, and texture. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models...

Recent work on pedestrian detection has relied on the concept of local co-occurences of features to propose higher-order, richer descriptors. While this idea has proven to be benefitial for this detection task, it fails to properly account for a more general and/or holistic representation. In this paper, a novel, flexible, and modular descriptor is proposed which is based on the alternative con...

This paper presents a robust multi-cue approach to the integrated detection and tracking of pedestrians in cluttered urban environment. A novel spatio-temporal object representation is proposed that combines a generative shape model and a discriminative texture classifier, both composed of a mixture of pose-specific submodels. Shape is represented by a set of linear subspace models, an extensio...

In the past decade, object detection has been researched to use a camera, a LIDAR and a RADAR. However, camera-based techniques have heavy image processing and are sensitive for light intensity. LIDAR can measure precise distance from objects, but it is difficult to classify objects. In addition, previous researches were unable to detect partially occluded pedestrian because the data to determi...

Pedestrian detection is one of the most important research contents of road safety. The crucial idea behind such pedestrian safety systems is to protect the driver and pedestrian from any accident. In this paper, a pedestrian feature extraction based on applied log-Gabor filters is presented. The resulting filtered images show desirable segmentation performance which allows support vector machi...

Pedestrian detection is highly valued in intelligent surveillance systems. Most existing pedestrian datasets are autonomously collected from non-surveillance videos, which result in significant data differences between the self-collected data and practical surveillance data. The data differences include: resolution, illumination, view point, and occlusion. Due to the data differences, most exis...

We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists in iteratively improving an appearancebased model built with a Boosting procedure, and the reconstruction of trajectories corresponding to the motion of multiple targets. We demonstrate the efficiency of our procedure...

A perception system for pedestrian detection in urban scenarios using information from a LIDAR and a single camera is presented. Two sensor fusion architectures are described, a centralized and a decentralized one. In the former, the fusion process occurs at the feature level, i.e., features from LIDAR and vision spaces are combined in a single vector for posterior classification using a single...

Histogram of orientated gradient (HOG) is widely used as a local feature descriptor in bag of features (BOF) method, whereas, few studies are conducted to discover the relationship between them. In this paper, we exploit this relationship and reveal that the construction method of descriptor in blocks in HOG can be treated as a variant of BOF method. Based on this interpretation, we propose a n...

This paper addresses the problem of appearance matching across disjoint camera views. Signi cant appearance changes, caused by variations in view angle, illumination and object pose, make the problem challenging. We propose to formulate the appearance matching problem as the task of learning a model that selects the most descriptive features for a speci c class of objects. Learning is performed...