Pedestrian detection by using a spatio-temporal histogram of oriented gradients

C Hua, Y Makihara, Y Yagi - IEICE Transactions on Information and …, 2013 - search.ieice.org
In this paper, we propose a pedestrian detection algorithm based on both appearance and
motion features to achieve high detection accuracy when applied to complex scenes. Here …

Onboard monocular pedestrian detection by combining spatio-temporal hog with structure from motion algorithm

C Hua, Y Makihara, Y Yagi, S Iwasaki… - Machine Vision and …, 2015 - Springer
In this paper, we brought out a novel pedestrian detection framework for the advanced driver
assistance system of mobile platform under the normal urban street environment. Different …

Target-driven video summarization in a camera network

SC Chen, K Lin, SY Lin, KW Chen… - … on Image Processing, 2013 - ieeexplore.ieee.org
Nowadays, ever expanding camera network makes it difficult to find the suspect from lengthy
video records. This paper proposes a target-driven video summarization framework which …

[HTML][HTML] On-line inverse multiple instance boosting for classifier grids

S Sternig, PM Roth, H Bischof - Pattern recognition letters, 2012 - Elsevier
Classifier grids have shown to be a considerable choice for object detection from static
cameras. By applying a single classifier per image location the classifier's complexity can be …

Extending the performance of human classifiers using a viewpoint specific approach

E Dibra, J Maye, O Diamanti, R Siegwart… - 2015 IEEE Winter …, 2015 - ieeexplore.ieee.org
This paper describes human classifiers that are'viewpoint specific', meaning specific to
subjects being observed by a particular camera in a particular scene. The advantages of the …

Contextualisation d'un détecteur de piétons: application à la surveillance d'espaces publics

T Chesnais - 2013 - theses.hal.science
La démocratisation de la «vidéosurveillance intelligente» nécessite le développement
d'outils automatiques et temps réel d'analyse vidéo. Parmi ceux-ci, la détection de piétons …

Adaptation of boosted pedestrian detectors by feature reselection

Z Liu, G Duan, H Ai, T Yamashita - 2012 19th IEEE …, 2012 - ieeexplore.ieee.org
Adaptation of pre-trained boosted pedestrian detectors to specific scenes is an important yet
difficult task in computer vision. To address this problem, a feature reselection strategy is …

Automated generation of high-quality training data for appearance-based object models

S Becker, A Voelker, H Kieritz… - … in Security and …, 2013 - spiedigitallibrary.org
Methods for automated person detection and person tracking are essential core components
in modern security and surveillance systems. Most state-of-the-art person detectors follow a …

Towards autonomous training of scene-specific pedestrian detectors in visual surveillance environments

MS Chowdhury - 2019 - trid.trb.org
Pedestrian detection is of paramount importance for intelligent visual surveillance of people.
Despite over two decades of extensive research, the performance of generic pedestrian …

[PDF][PDF] Sabine Sternig

H Bischof - Citeseer
Object detection or object tracking are often the first steps towards an automatic video
analysis. Numerous applications, such as visual surveillance, industrial applications or …