People detection based on appearance and motion models

García-Martín, Álvaro; Hauptmann, Alex; Martinez, José M.

doi:10.1109/avss.2011.6027333

Cited by 10 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They have been chosen in order to cover the state of the art classification for people detection that we propose (see section 2.1): Edge [44], HOG [33], ISM [53], TUD [40], DTDP [41], ACF [42] and IMM [28]. …”

Section: Resultsmentioning

confidence: 99%

“…In this case, the motion information is not implicitly part of the person model but it is still useful in order to filter or extrapolate detections over time. On the other hand, [28], [30] not only combine detection and tracking information but also propose the combination of two independent and implicit person models: one model based on appearance and another model based on motion.…”

Section: People Detectionmentioning

confidence: 99%

“…Dataset A includes 29 sequences including the five different complexity categories, whilst B includes 61 sequences of the highest complexity category (C5). Following [28], this dataset B has been divided in train and test sequences in order to evaluate the motion approach and appearance-motion combinations. The test dataset is composed of 36 sequences 1 .…”

Section: Pdds Datasetmentioning

confidence: 99%

“…Finally, every people detector must compare the previously defined/trained person model with the input image and make a final decision according to a similarity criterion. There are some approaches that combine or fuse multiple detectors at decision-level using multi body part detectors [39] or detectors [28].…”

Section: People Detection Post-processingmentioning

confidence: 99%

See 3 more Smart Citations

Post-processing approaches for improving people detection performance

García-Martín

Martínez

2015

Computer Vision and Image Understanding

View full text Add to dashboard Cite

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription 1 Post-processing approaches for improving people detection performancé Alvaro García-Martín and José M. Martínez ! Abstract-Nowadays, people detection in video surveillance environments is a task that has been generating great interest. There are many approaches trying to solve the problem either in controlled scenarios or in very specific surveillance applications. We address one of the main problems of people detection in video sequences: every people detector from the state of the art must maintain a balance between the number of false detections and the number of missing pedestrians. This compromise limits the global detection results. In order to reduce or relax this limitation and improve the detection results, we evaluate two different post-processing subtasks. Firstly, we propose the use of peoplebackground segmentation as a filtering stage in people detection. Then, we evaluate the combination of different detection approaches in order to add robustness to the detection and therefore improve the detection results. And, finally, we evaluate the successive application of both post-processing approaches. Experiments have been performed on two extensive datasets and using different people detectors from the state of the art: the results show the benefits achieved using the proposed post-processing techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: People Detectionmentioning

confidence: 99%

Section: Pdds Datasetmentioning

confidence: 99%

Section: People Detection Post-processingmentioning

confidence: 99%

See 2 more Smart Citations

Post-processing approaches for improving people detection performance

García-Martín

Martínez

2015

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…body parts detection that uses pictorial structures to represent parts configurations is presented in [6]. Another extension of [1] combines appearance and motion information, and introduces the Implicit Motion Model (IMM), a motion person model inspired by the ISM [7].…”

Section: Introductionmentioning

confidence: 99%

People-background segmentation with unequal error cost

García-Martín

Cavallaro

Martinez

2012

2012 19th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: ABSTRACTWe address the problem of segmenting a video in two classes of different semantic value, namely background and people, with the goal of guaranteeing that no people (or body parts) are classified as background. Body parts classified as background are given a higher classification error cost (segmentation with bias on background), as opposed to traditional approaches focused on people detection. To generate the people-background segmentation mask, the proposed approach first combines detection confidence maps of body parts and then extends them in order to derive a background mask, which is finally post-processed using morphological operators. Experiments validate the performance of our algorithm in different complex indoor and outdoor scenes with both static and moving cameras.

show abstract

Tracking People in Crowded Scenes

Boltes

Seyfried

2013

Pedestrian and Evacuation Dynamics 2012

View full text Add to dashboard Cite

People detection based on appearance and motion models

Cited by 10 publications

References 17 publications

Post-processing approaches for improving people detection performance

Post-processing approaches for improving people detection performance

People-background segmentation with unequal error cost

Tracking People in Crowded Scenes

Contact Info

Product

Resources

About