An Evaluation of Local Shape-Based Features for Pedestrian Detection

@inproceedings{Seemann2005AnEO,
  title={An Evaluation of Local Shape-Based Features for Pedestrian Detection},
  author={Edgar Seemann and B. Leibe and Krystian Mikolajczyk and Bernt Schiele},
  booktitle={BMVC},
  year={2005}
}
Pedestrian detection in real world scenes is a challenging problem. In recent years a variety of approaches have been proposed, and impressive results have been reported on a variety of databases. This paper systematically evaluates (1) various local shape descriptors, namely Shape Context and Local Chamfer descriptor and (2) four different interest point detectors for the detection of pedestrians. Those results are compared to the standard global Chamfer matching approach. A main result of the… 
Evaluation of Keypoint Descriptors Applied in the Pedestrian Detection in Low Quality Images
TLDR
This article aims to present a systematic and comparative study of the performance these local features detectors and descriptors in pedestrian detection in four real databases, all in an urban environment.
Cross-Articulation Learning for Robust Detection of Pedestrians
TLDR
This work proposes an approach, which aims for a suitable trade-off for recognizing categories of articulated objects in real-world scenarios and is made more discriminant by explicitly distinguishing typical object shapes.
Asymmetric Learning for Pedestrian Detection Based on Joint Local Orientation Histograms
TLDR
A cost-sensitive learning framework for pedestrian detection in still images based on the novel Joint Local Orientation Histograms (JLOH) features and the proposed Asymmetric Gentle AdaBoost takes account of the situation that the rare positive targets have to be distinguished from enormous negative patterns in practical applications.
Learning model for object detection based on local edge features
TLDR
A learning model for object detection that uses a novel local edge features motivated by the scheme that use the chamfer distance as a shape comparison measure and can be extended to detect other objects such as airplanes or pedestrian.
Pedestrian Detection: An Evaluation of the State of the Art
TLDR
An extensive evaluation of the state of the art in a unified framework of monocular pedestrian detection using sixteen pretrained state-of-the-art detectors across six data sets and proposes a refined per-frame evaluation methodology.
Evaluation of local features for person re-identification in image sequences
  • M. Bäuml, R. Stiefelhagen
  • Computer Science
    2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
  • 2011
TLDR
The results indicate that there are significant differences between the evaluated descriptors, with GLOH and SIFT outperforming both Shape Context and SURF descriptors.
Pedestrian detection in far infrared images
TLDR
An in-depth evaluation of several combinations of features and classifiers, which include features previously used for daylight scenarios, as well as a new descriptor HOPE --Histograms of Oriented Phase Energy, specifically targeted to infrared images, and a new adaptation of a latent variable SVM approach to FIR images are presented.
Multi-Aspect Detection of Articulated Objects
TLDR
An important property of this new approach is to share local appearance across different articulations and viewpoints, therefore requiring relatively few training samples, and the effectiveness of the approach is shown and compared to previous approaches.
Towards Robust Pedestrian Detection in Crowded Image Sequences
TLDR
This work presents a generative object model that is capable to scale from a general object class model to a more specific object-instance model that allows to detect class instances as well as to distinguish between individual object instances reliably.
How Good are Local Features for Classes of Geometric Objects
  • Michael Stark, B. Schiele
  • Mathematics, Computer Science
    2007 IEEE 11th International Conference on Computer Vision
  • 2007
TLDR
This paper compares, on a novel data collection of 10 geometric object classes, various shape-based features with appearance-based descriptors such as SIFT, which includes a direct comparison of feature statistics as well as results within standard recognition frameworks, which are partly intuitive, but sometimes surprising.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Pedestrian detection in crowded scenes
TLDR
Qualitative and quantitative results on a large data set confirm that the core part of the method is the combination of local and global cues via probabilistic top-down segmentation that allows examining and comparing object hypotheses with high precision down to the pixel level.
Stereo- and neural network-based pedestrian detection
  • Liang Zhao, C. Thorpe
  • Computer Science
    Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383)
  • 1999
TLDR
A real-time pedestrian detection system that uses a pair of moving cameras to detect both stationary and moving pedestrians in crowded environments through stereo-based segmentation and neural network-based recognition is presented.
Pedestrian detection using wavelet templates
TLDR
This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes and shows how the invariant properties and computational efficiency of the wavelet template make it an effective tool for object detection.
Human Detection Based on a Probabilistic Assembly of Robust Part Detectors
We describe a novel method for human detection in single images which can detect full bodies as well as close-up views in the presence of clutter and occlusion. Humans are modeled as flexible
Pedestrian Detection from a Moving Vehicle
TLDR
This paper presents a prototype system for pedestrian detection on-board a moving vehicle that uses a generic two-step approach for efficient object detection using a hierarchical template matching approach and achieves very large speed-ups compared to a brute-force method.
Detecting pedestrians using patterns of motion and appearance
TLDR
This paper describes a pedestrian detection system that integrates image intensity information with motion information, and is the first to combine both sources of information in a single detector.
A Performance Evaluation of Local Descriptors
TLDR
It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
Example-Based Object Detection in Images by Components
TLDR
Results suggest that the improvement in performance is due to the component-based approach and the ACC data classification architecture, which is capable of locating partially occluded views of people and people whose body parts have little contrast with the background.
A Trainable System for Object Detection
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in
Combined Object Categorization and Segmentation With an Implicit Shape Model
We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure- ground segmentation is available prior to recognition.
...
1
2
3
...