Ground Plane Segmentation Using Artificial Neural Network for Pedestrian Detection

Cândido, Jorge; Marengoni, Maurício

doi:10.1007/978-3-319-59876-5_30

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same channel combination was used in Candido and Marengoni (2017) A pooling process is applied for each channel with the purpose of lowering data dimensionality and improving robustness of the system. In the maximum polling process used here, the highest value inside the window is used to represent the window region.…”

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Pedestrian Detection Using Context Information

Cândido¹,

Marengoni²

2018

Journal of Computer Science

Self Cite

View full text Add to dashboard Cite

Detecting pedestrians among other objects in a digital image is a relevant task in the field of computer vision. This paper presents a method to improve the performance of a pedestrian detection algorithm using context information. A neural network is used to classify the region below pedestrian candidates as being floor or non-floor. We assume that a pedestrian must be standing on a floor area. This scene context information is used to eliminate some of the false-positive pedestrian candidates, therefore improving detector precision. The neural network uses 10 feature channels extracted from the original image to perform the region classification. This method may be used along with a large family of pedestrian-detecting algorithms. We used the ACF-LDCF algorithm to perform the tests in this research. The result shows that this method is very effective. We achieve a gain of 7% in ACF-LDCF algorithm performance on the Caltech pedestrian benchmark.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

“…In the work presented in Candido and Marengoni (2017), a neural network was used to classify an image area into floor or non-floor classes in order to perform a segmentation of the ground plane in outdoor images. Here the same idea was used to enhance pedestrian detector performance in an integrated system.…”

Section: Introductionmentioning

confidence: 99%