Combination of Feature Extraction Methods for SVM Pedestrian Detection

Alonso, Ignacio Parra; Llorca, David Fernández; Sotelo, Miguel Ángel; Bergasa, Luis M.; Revenga, P.; Nuevo, J.; Ocaña, Manuel; Garrido, Miguel

doi:10.1109/tits.2007.894194

Cited by 144 publications

(69 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also some approaches that try to combine both approaches together [43], [44]. In any case, the result of this stage is the location and dimension (bounding box or blob) of the different objects candidates to be a person.…”

Section: People Detectionmentioning

confidence: 99%

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: People Detectionmentioning

confidence: 99%

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

“…In [3] and [18], it is proposed that ROIs be selected by considering the x-and y-projections of the disparity space following the v-disparity representation [24]. In [1], object hypotheses are obtained by using a subtractive clustering in the 3-D space in world coordinates. Motion information is utilized in [10] as a preprocessing step for ROI generation.…”

Section: Previous Workmentioning

confidence: 99%

“…Previous IV applications have typically used sparse featurebased stereo approaches (e.g., [1], [15], and [30]) because of lower processing cost. However, with recent hardware advances, real-time dense stereo has become feasible [41] (here, we use a hardware implementation of the semiglobal matching (SGM) algorithm [13], [20]).…”

Section: Introductionmentioning

confidence: 99%

The Benefits of Dense Stereo for Pedestrian Detection

Keller

Enzweiler

Rohrbach

et al. 2011

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Abstract-This paper presents a novel pedestrian detection system for intelligent vehicles. We propose the use of dense stereo for both the generation of regions of interest and pedestrian classification. Dense stereo allows the dynamic estimation of camera parameters and the road profile, which, in turn, provides strong scene constraints on possible pedestrian locations. For classification, we extract spatial features (gradient orientation histograms) directly from dense depth and intensity images. Both modalities are represented in terms of individual feature spaces, in which discriminative classifiers (linear support vector machines) are learned. We refrain from the construction of a joint feature space but instead employ a fusion of depth and intensity on the classifier level. Our experiments involve challenging image data captured in complex urban environments (i.e., undulating roads and speed bumps). Our results show a performance improvement by up to a factor of 7.5 at the classification level and up to a factor of 5 at the tracking level (reduction in false alarms at constant detection rates) over a system with static scene constraints and intensity-only classification.

show abstract

“…In [2,10] ROIs are selected considering the x-and y-projections of the disparity space following the v-disparity representation [11]. In [1] object hypotheses are obtained by using a subtractive clustering in the 3D space in world coordinates.…”

Section: Related Workmentioning

confidence: 99%

“…[9,1]) because of lower processing cost. However, with recent hardware advances, real-time dense stereo has become feasible [12] (here we use a hardware implementation of the semi-global matching (SGM) algorithm [7]).…”

Section: Introductionmentioning

confidence: 99%

Dense Stereo-Based ROI Generation for Pedestrian Detection

Keller

Llorca

Gavrila

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper investigates the benefit of dense stereo for the ROI generation stage of a pedestrian detection system. Dense disparity maps allow an accurate estimation of the camera height, pitch angle and vertical road profile, which in turn enables a more precise specification of the areas on the ground where pedestrians are to be expected. An experimental comparison between sparse and dense stereo approaches is carried out on image data captured in complex urban environments (i.e. undulating roads, speed bumps). The ROI generation stage, based on dense stereo and specific camera and road parameter estimation, results in a detection performance improvement of factor five over the stateof-the-art based on ROI generation by sparse stereo. Interestingly, the added processing cost of computing dense disparity maps is at least partially amortized by the fewer ROIs that need to be processed at the system level.

show abstract

Combination of Feature Extraction Methods for SVM Pedestrian Detection

Cited by 144 publications

References 28 publications

Post-processing approaches for improving people detection performance

Post-processing approaches for improving people detection performance

The Benefits of Dense Stereo for Pedestrian Detection

Dense Stereo-Based ROI Generation for Pedestrian Detection

Contact Info

Product

Resources

About