Álvaro García-Martín

Robust Real Time Moving People Detection in Surveillance Scenarios

In this paper an improved real time algorithm for detectingpedestrians in surveillance video is proposed. Thealgorithm is based on people appearance and defines a personmodel as the union of four models of body parts. Firstly,motion segmentation is performed to detect moving pixels.Then, moving regions are extracted and tracked. Finally,the detected moving objects are classified as human or nonhumanobjects. In order to test and validate the algorithm,we have developed a dataset containing annotated surveillancesequences of different complexity levels focused onthe pedestrians detection. Experimental results over thisdataset show that our approach performs considerably wellat real time and even better than other real and non-realtime approaches from the state of art.

On collaborative people detection and tracking in complex scenarios

The main contributions of this paper covers two different aspects: people detection and tracking. A whole detection/tracking system that integrates appearance, motion and tracking information is presented. This system uses the information provided by each of the independent tasks to improve the final result of the system. The tracking information is integrated in the detection task improving the detection results and vice versa. The experimental results over an extensive and challenging video dataset point out the state of the art limitations in complex or realistic scenarios, and show that the proposed collaborative system significantly reduces these limitations and improves the results in this kind of scenarios.

People detection based on appearance and motion models

The main contribution of this paper is a new people detection algorithm based on motion information. The algorithm builds a people motion model based on the Implicit Shape Model (ISM) Framework and the MoSIFT descriptor. We also propose a detection system that integrates appearance, motion and tracking information. Experimental results over sequences extracted from the TRECVID dataset show that our new people motion detector produces results comparable to the state of the art and that the proposed multimodal fusion system improves the obtained results combining the three information sources.

A corpus for benchmarking of people detection algorithms

This paper describes a corpus, dataset and associated ground-truth, for the evaluation of people detection algorithms in surveillance video scenarios, along with the design procedure followed to generate it. Sequences from scenes with different levels of complexity have been manually annotated. Each person present at a scene has been labeled frame by frame, in order to automatically obtain a people detection ground-truth for each sequence. Sequences have been classified into different complexity categories depending on critical factors that typically affect the behavior of detection algorithms. The resulting corpus, which exceeds other public pedestrian datasets in the amount of video sequences and its complexity variability, is freely available for benchmarking and research purposes under a license agreement.

People detection in surveillance: Classification and evaluation

This paper is a postprint of a paper submitted to and accepted for publication in IET Computer Vision and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library and at IEEE Xplore.

A multi-configuration part-based person detector

People detection is a task that has generated a great interest in the computer vision and specially in the surveillance community. One of the main problems of this task in crowded scenarios is the high number of occlusions deriving from persons appearing in groups. In this paper, we address this problem by combining individual body part detectors in a statistical driven way in order to be able to detect persons even in case of failure of any detection of the body parts, i.e., we propose a generic scheme to deal with partial occlusions. We demonstrate the validity of our approach and compare it with other state of the art approaches on several public datasets. In our experiments we consider sequences with different complexities in terms of occupation and therefore with different number of people present in the scene, in order to highlight the benefits and difficulties of the approaches considered for evaluation. The results show that our approach improves the results provided by state of the art approaches specially in the case of crowded scenes.

People-background segmentation with unequal error cost

We 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.

The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results

The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2015 is the first benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2015 challenge is based on the VOT2013 challenge, but introduces the following novelties: (i) the newly collected LTIR (Link -- ping TIR) dataset is used, (ii) the VOT2013 attributes are adapted to TIR data, (iii) the evaluation is performed using insights gained during VOT2013 and VOT2014 and is similar to VOT2015.

Hierarchical detection of persons in groups

In this paper, we address one of the most typical problems of person detection: scenarios with the presence of groups of persons. In this kind of scenarios, traditional person detectors have difficulties as they have to deal with several simultaneous occlusions. In order to try to solve this problem, we propose the use of two different hierarchies. The first one consists of a hierarchy of persons, i.e., the use of the detection of different persons belonging to a group in order to refine the individual’s detections. The second one consists of a hierarchy of parts, i.e., the use of different combinations of body parts in order to refine the final detections. Experimental results over several video sequences show that the proposed hierarchies significantly improve the results with respect to different approaches from the state of the art.

Post-processing approaches for improving people detection performance

Abstract 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 people-background 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.